Showing papers by "Harbin Institute of Technology published in 2019"

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Abstract: Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophisticated attention modules for achieving better performance, which inevitably increase model complexity. To overcome the paradox of performance and complexity trade-off, this paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain. By dissecting the channel attention module in SENet, we empirically show avoiding dimensionality reduction is important for learning channel attention, and appropriate cross-channel interaction can preserve performance while significantly decreasing model complexity. Therefore, we propose a local cross-channel interaction strategy without dimensionality reduction, which can be efficiently implemented via $1D$ convolution. Furthermore, we develop a method to adaptively select kernel size of $1D$ convolution, determining coverage of local cross-channel interaction. The proposed ECA module is efficient yet effective, e.g., the parameters and computations of our modules against backbone of ResNet50 are 80 vs. 24.37M and 4.7e-4 GFLOPs vs. 3.86 GFLOPs, respectively, and the performance boost is more than 2% in terms of Top-1 accuracy. We extensively evaluate our ECA module on image classification, object detection and instance segmentation with backbones of ResNets and MobileNetV2. The experimental results show our module is more efficient while performing favorably against its counterparts.

Deep Learning for Hyperspectral Image Classification: An Overview

Abstract: Hyperspectral image (HSI) classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of hyperspectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, hyperspectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In recent years, deep learning has been recognized as a powerful feature-extraction tool to effectively address nonlinear problems and widely used in a number of image processing tasks. Motivated by those successful applications, deep learning has also been introduced to classify HSIs and demonstrated good performance. This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies for this topic. Specifically, we first summarize the main challenges of HSI classification which cannot be effectively overcome by traditional machine learning methods, and also introduce the advantages of deep learning to handle these problems. Then, we build a framework which divides the corresponding works into spectral-feature networks, spatial-feature networks, and spectral-spatial-feature networks to systematically review the recent achievements in deep learning-based HSI classification. In addition, considering the fact that available training samples in the remote sensing field are usually very limited and training deep networks require a large number of samples, we include some strategies to improve classification performance, which can provide some guidelines for future studies on this topic. Finally, several representative deep learning-based classification methods are conducted on real HSIs in our experiments.

Toward Convolutional Blind Denoising of Real Photographs

Abstract: While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. The main reason is that their learned models are easy to overfit on the simplified AWGN model which deviates severely from the complicated real-world noise model. In order to improve the generalization ability of deep CNN denoisers, we suggest training a convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs. On the one hand, both signal-dependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBDNet. To further provide an interactive strategy to rectify denoising result conveniently, a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Extensive experimental results on three datasets of real-world noisy pho- tographs clearly demonstrate the superior performance of CBDNet over state-of-the-arts in terms of quantitative met- rics and visual quality. The code has been made available at https://github.com/GuoShi28/CBDNet.

Persulfate Activation on Crystallographic Manganese Oxides: Mechanism of Singlet Oxygen Evolution for Nonradical Selective Degradation of Aqueous Contaminants.

Abstract: Minerals and transitional metal oxides of earth-abundant elements are desirable catalysts for in situ chemical oxidation in environmental remediation. However, catalytic activation of peroxydisulfate (PDS) by manganese oxides was barely investigated. In this study, one-dimension manganese dioxides (α- and β-MnO2) were discovered as effective PDS activators among the diverse manganese oxides for selective degradation of organic contaminants. Compared with other chemical states and crystallographic structures of manganese oxide, β-MnO2 nanorods exhibited the highest phenol degradation rate (0.044 min-1, 180 min) by activating PDS. A comprehensive study was conducted utilizing electron paramagnetic resonance, chemical probes, radical scavengers, and different solvents to identity the reactive oxygen species (ROS). Singlet oxygen (1O2) was unveiled to be the primary ROS, which was generated by direct oxidation or recombination of superoxide ions and radicals from a metastable manganese intermediate at neutral pH. The study dedicates to the first mechanistic study into PDS activation over manganese oxides and provides a novel catalytic system for selective removal of organic contaminants in wastewater.

The sixth visual object tracking VOT2018 challenge results

Abstract: The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new long-term tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net).

AttGAN: Facial Attribute Editing by Only Changing What You Want

Abstract: Facial attribute editing aims to manipulate single or multiple attributes on a given face image, i.e., to generate a new face image with desired attributes while preserving other details. Recently, the generative adversarial net (GAN) and encoder–decoder architecture are usually incorporated to handle this task with promising results. Based on the encoder–decoder architecture, facial attribute editing is achieved by decoding the latent representation of a given face conditioned on the desired attributes. Some existing methods attempt to establish an attribute-independent latent representation for further attribute editing. However, such attribute-independent constraint on the latent representation is excessive because it restricts the capacity of the latent representation and may result in information loss, leading to over-smooth or distorted generation. Instead of imposing constraints on the latent representation, in this work, we propose to apply an attribute classification constraint to the generated image to just guarantee the correct change of desired attributes, i.e., to change what you want. Meanwhile, the reconstruction learning is introduced to preserve attribute-excluding details, in other words, to only change what you want. Besides, the adversarial learning is employed for visually realistic editing. These three components cooperate with each other forming an effective framework for high quality facial attribute editing, referred as AttGAN . Furthermore, the proposed method is extended for attribute style manipulation in an unsupervised manner. Experiments on two wild datasets, CelebA and LFW, show that the proposed method outperforms the state-of-the-art on realistic attribute editing with other facial details well preserved.

Pre-Training with Whole Word Masking for Chinese BERT

Abstract: Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks. Recently, an upgraded version of BERT has been released with Whole Word Masking (WWM), which mitigate the drawbacks of masking partial WordPiece tokens in pre-training BERT. In this technical report, we adapt whole word masking in Chinese text, that masking the whole word instead of masking Chinese characters, which could bring another challenge in Masked Language Model (MLM) pre-training task. The proposed models are verified on various NLP tasks, across sentence-level to document-level, including machine reading comprehension (CMRC 2018, DRCD, CJRC), natural language inference (XNLI), sentiment classification (ChnSentiCorp), sentence pair matching (LCQMC, BQ Corpus), and document classification (THUCNews). Experimental results on these datasets show that the whole word masking could bring another significant gain. Moreover, we also examine the effectiveness of the Chinese pre-trained models: BERT, ERNIE, BERT-wwm, BERT-wwm-ext, RoBERTa-wwm-ext, and RoBERTa-wwm-ext-large. We release all the pre-trained models: \url{this https URL

Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency.

Abstract: We address the problem of adversarial attacks on text classification, which is rarely studied comparing to attacks on image classification. The challenge of this task is to generate adversarial examples that maintain lexical correctness, grammatical correctness and semantic similarity. Based on the synonyms substitution strategy, we introduce a new word replacement order determined by both the word saliency and the classification probability, and propose a greedy algorithm called probability weighted word saliency (PWWS) for text adversarial attack. Experiments on three popular datasets using convolutional as well as LSTM models show that PWWS reduces the classification accuracy to the most extent, and keeps a very low word substitution rate. A human evaluation study shows that our generated adversarial examples maintain the semantic similarity well and are hard for humans to perceive. Performing adversarial training using our perturbed datasets improves the robustness of the models. At last, our method also exhibits a good transferability on the generated adversarial examples.

Intercellular interaction dictates cancer cell ferroptosis via NF2–YAP signalling

Abstract: Ferroptosis, a cell death process driven by cellular metabolism and iron-dependent lipid peroxidation, has been implicated in diseases such as ischaemic organ damage and cancer1,2. The enzyme glutathione peroxidase 4 (GPX4) is a central regulator of ferroptosis, and protects cells by neutralizing lipid peroxides, which are by-products of cellular metabolism. The direct inhibition of GPX4, or indirect inhibition by depletion of its substrate glutathione or the building blocks of glutathione (such as cysteine), can trigger ferroptosis3. Ferroptosis contributes to the antitumour function of several tumour suppressors such as p53, BAP1 and fumarase4–7. Counterintuitively, mesenchymal cancer cells—which are prone to metastasis, and often resistant to various treatments—are highly susceptible to ferroptosis8,9. Here we show that ferroptosis can be regulated non-cell-autonomously by cadherin-mediated intercellular interactions. In epithelial cells, such interactions mediated by E-cadherin suppress ferroptosis by activating the intracellular NF2 (also known as merlin) and Hippo signalling pathway. Antagonizing this signalling axis allows the proto-oncogenic transcriptional co-activator YAP to promote ferroptosis by upregulating several ferroptosis modulators, including ACSL4 and TFRC. This finding provides mechanistic insights into the observations that cancer cells with mesenchymal or metastatic property are highly sensitive to ferroptosis8. Notably, a similar mechanism also modulates ferroptosis in some non-epithelial cells. Finally, genetic inactivation of the tumour suppressor NF2, a frequent tumorigenic event in mesothelioma10,11, rendered cancer cells more sensitive to ferroptosis in an orthotopic mouse model of malignant mesothelioma. Our results demonstrate the role of intercellular interactions and intracellular NF2–YAP signalling in dictating ferroptotic death, and also suggest that malignant mutations in NF2–YAP signalling could predict the responsiveness of cancer cells to future ferroptosis-inducing therapies. Ferroptosis in cancer cells can be regulated by cadherin-mediated intercellular contacts, NF2–Hippo signalling, and activity of the YAP transcription co-activator.

Advances in designs and mechanisms of semiconducting metal oxide nanostructures for high-precision gas sensors operated at room temperature

Abstract: High-precision gas sensors operated at room temperature are attractive for various real-time gas monitoring applications, with advantages including low energy consumption, cost effectiveness and device miniaturization/flexibility. Studies on sensing materials, which play a key role in good gas sensing performance, are currently focused extensively on semiconducting metal oxide nanostructures (SMONs) used in the conventional resistance type gas sensors. This topical review highlights the designs and mechanisms of different SMONs with various patterns (e.g. nanoparticles, nanowires, nanosheets, nanorods, nanotubes, nanofilms, etc.) for gas sensors to detect various hazardous gases at room temperature. The key topics include (1) single phase SMONs including both n-type and p-type ones; (2) noble metal nanoparticle and metal ion modified SMONs; (3) composite oxides of SMONs; (4) composites of SMONs with carbon nanomaterials. Enhancement of the sensing performance of SMONs at room temperature can also be realized using a photo-activation effect such as ultraviolet light. SMON based mechanically flexible and wearable room temperature gas sensors are also discussed. Various mechanisms have been discussed for the enhanced sensing performance, which include redox reactions, heterojunction generation, formation of metal sulfides and the spillover effect. Finally, major challenges and prospects for the SMON based room temperature gas sensors are highlighted.

Defect-Rich Heterogeneous MoS2/NiS2 Nanosheets Electrocatalysts for Efficient Overall Water Splitting.

Abstract: Designing and constructing bifunctional electrocatalysts is vital for water splitting. Particularly, the rational interface engineering can effectively modify the active sites and promote the electronic transfer, leading to the improved splitting efficiency. Herein, free-standing and defect-rich heterogeneous MoS2/NiS2 nanosheets for overall water splitting are designed. The abundant heterogeneous interfaces in MoS2/NiS2 can not only provide rich electroactive sites but also facilitate the electron transfer, which further cooperate synergistically toward electrocatalytic reactions. Consequently, the optimal MoS2/NiS2 nanosheets show the enhanced electrocatalytic performances as bifunctional electrocatalysts for overall water splitting. This study may open up a new route for rationally constructing heterogeneous interfaces to maximize their electrochemical performances, which may help to accelerate the development of nonprecious electrocatalysts for overall water splitting.

Locality Preserving Matching

Abstract: Seeking reliable correspondences between two feature sets is a fundamental and important task in computer vision. This paper attempts to remove mismatches from given putative image feature correspondences. To achieve the goal, an efficient approach, termed as locality preserving matching (LPM), is designed, the principle of which is to maintain the local neighborhood structures of those potential true matches. We formulate the problem into a mathematical model, and derive a closed-form solution with linearithmic time and linear space complexities. Our method can accomplish the mismatch removal from thousands of putative correspondences in only a few milliseconds. To demonstrate the generality of our strategy for handling image matching problems, extensive experiments on various real image pairs for general feature matching, as well as for point set registration, visual homing and near-duplicate image retrieval are conducted. Compared with other state-of-the-art alternatives, our LPM achieves better or favorably competitive performance in accuracy while intensively cutting time cost by more than two orders of magnitude.

Observer-Based Fuzzy Adaptive Event-Triggered Control for Pure-Feedback Nonlinear Systems With Prescribed Performance

Abstract: This paper studies the problem of fuzzy adaptive event-triggered control for a class of pure-feedback nonlinear systems, which contain unknown smooth functions and unmeasured states. Fuzzy logic systems are adopted to approximate unknown smooth functions and a fuzzy state observer is designed to estimate unmeasured states. Via the event-triggered control technique, the control signal of the fixed threshold strategy is obtained. By converting the tracking error into a new virtual error variable, an observer-based fuzzy adaptive event-triggered prescribed performance control strategy is designed. The key advantage is that the proposed method does not require a $priori$ knowledge of partial derivatives of system functions, i.e., it relaxes the restrictive condition that the partial derivatives of system functions need to be known for pure-feedback nonlinear systems. Simulation results confirm the efficiency of the proposed method.

Biomaterials for bone tissue engineering scaffolds: a review

Abstract: Bone tissue engineering has been continuously developing since the concept of “tissue engineering” has been proposed. Biomaterials that are used as the basic material for the fabrication of scaffolds play a vital role in bone tissue engineering. This paper first introduces a strategy for literature search. Then, it describes the structure, mechanical properties and materials of natural bone and the strategies of bone tissue engineering. Particularly, it focuses on the current knowledge about biomaterials used in the fabrication of bone tissue engineering scaffolds, which includes the history, types, properties and applications of biomaterials. The effects of additives such as signaling molecules, stem cells, and functional materials on the performance of the scaffolds are also discussed.

Pyramid Feature Attention Network for Saliency Detection

Abstract: Saliency detection is one of the basic challenges in computer vision. Recently, CNNs are the most widely used and powerful techniques for saliency detection, in which feature maps from different layers are always integrated without distinction. However, instinctively, the different feature maps of CNNs and the different features in the same maps should play different roles in saliency detection. To address this problem, a novel CNN named pyramid feature attention network (PFAN) is proposed to enhance the high-level context features and the low-level spatial structural features. In the proposed PFAN, a context-aware pyramid feature extraction (CPFE) module is designed for multi-scale high-level feature maps to capture the rich context features. A channel-wise attention (CA) model and a spatial attention (SA) model are respectively applied to the CPFE feature maps and the low-level feature maps, and then fused to detect salient regions. Finally, an edge preservation loss is proposed to get the accurate boundaries of salient regions. The proposed PFAN is extensively evaluated on five benchmark datasets and the experimental results demonstrate that the proposed network outperforms the state-of-the-art approaches under different evaluation metrics.

Progressive Image Deraining Networks: A Better and Simpler Baseline

Abstract: Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new deraining networks. To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions. Specifically, by repeatedly unfolding a shallow ResNet, progressive ResNet (PRN) is proposed to take advantage of recursive computation. A recurrent layer is further introduced to exploit the dependencies of deep features across stages, forming our progressive recurrent network (PReNet). Furthermore, intra-stage recursive computation of ResNet can be adopted in PRN and PReNet to notably reduce network parameters with unsubstantial degradation in deraining performance. For network input and output, we take both stage-wise result and original rainy image as input to each ResNet and finally output the prediction of residual image. As for loss functions, single MSE or negative SSIM losses are sufficient to train PRN and PReNet. Experiments show that PRN and PReNet perform favorably on both synthetic and real rainy images. Considering its simplicity, efficiency and effectiveness, our models are expected to serve as a suitable baseline in future deraining research. The source codes are available at https://github.com/csdwren/PReNet.

Reconfigurable magnetic microrobot swarm: Multimode transformation, locomotion, and manipulation.

Abstract: Swimming microrobots that are energized by external magnetic fields exhibit a variety of intriguing collective behaviors, ranging from dynamic self-organization to coherent motion; however, achieving multiple, desired collective modes within one colloidal system to emulate high environmental adaptability and enhanced tasking capabilities of natural swarms is challenging. Here, we present a strategy that uses alternating magnetic fields to program hematite colloidal particles into liquid, chain, vortex, and ribbon-like microrobotic swarms and enables fast and reversible transformations between them. The chain is characterized by passing through confined narrow channels, and the herring school-like ribbon procession is capable of large-area synchronized manipulation, whereas the colony-like vortex can aggregate at a high density toward coordinated handling of heavy loads. Using the developed discrete particle simulation methods, we investigated generation mechanisms of these four swarms, as well as the "tank-treading" motion of the chain and vortex merging. In addition, the swarms can be programmed to steer in any direction with excellent maneuverability, and the vortex's chirality can be rapidly switched with high pattern stability. This reconfigurable microrobot swarm can provide versatile collective modes to address environmental variations or multitasking requirements; it has potential to investigate fundamentals in living systems and to serve as a functional bio-microrobot system for biomedicine.

The Seventh Visual Object Tracking VOT2019 Challenge Results

Abstract: The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOTST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" shortterm tracking in RGB, (iii) VOT-LT2019 focused on longterm tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard shortterm, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website.

Gene2vec: gene subsequence embedding for prediction of mammalian N6-methyladenosine sites from mRNA.

Abstract: N6-Methyladenosine (m6A) refers to methylation modification of the adenosine nucleotide acid at the nitrogen-6 position. Many conventional computational methods for identifying N6-methyladenosine sites are limited by the small amount of data available. Taking advantage of the thousands of m6A sites detected by high-throughput sequencing, it is now possible to discover the characteristics of m6A sequences using deep learning techniques. To the best of our knowledge, our work is the first attempt to use word embedding and deep neural networks for m6A prediction from mRNA sequences. Using four deep neural networks, we developed a model inferred from a larger sequence shifting window that can predict m6A accurately and robustly. Four prediction schemes were built with various RNA sequence representations and optimized convolutional neural networks. The soft voting results from the four deep networks were shown to outperform all of the state-of-the-art methods. We evaluated these predictors mentioned above on a rigorous independent test data set and proved that our proposed method outperforms the state-of-the-art predictors. The training, independent, and cross-species testing data sets are much larger than in previous studies, which could help to avoid the problem of overfitting. Furthermore, an online prediction web server implementing the four proposed predictors has been built and is available at http://server.malab.cn/Gene2vec/.

Blind Super-Resolution With Iterative Kernel Correction

Abstract: Deep learning based methods have dominated super-resolution (SR) field due to their remarkable performance in terms of effectiveness and efficiency. Most of these methods assume that the blur kernel during downsampling is predefined/known (e.g., bicubic). However, the blur kernels involved in real applications are complicated and unknown, resulting in severe performance drop for the advanced SR methods. In this paper, we propose an Iterative Kernel Correction (IKC) method for blur kernel estimation in blind SR problem, where the blur kernels are unknown. We draw the observation that kernel mismatch could bring regular artifacts (either over-sharpening or over-smoothing), which can be applied to correct inaccurate blur kernels. Thus we introduce an iterative correction scheme -- IKC that achieves better results than direct kernel estimation. We further propose an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD. Extensive experiments on synthetic and real-world images show that the proposed IKC method with SFTMD can provide visually favorable SR results and the state-of-the-art performance in blind SR problem.

Recent Advances in Aptamer Discovery and Applications.

Abstract: Aptamers are short, single-stranded DNA, RNA, or synthetic XNA molecules that can be developed with high affinity and specificity to interact with any desired targets. They have been widely used in facilitating discoveries in basic research, ensuring food safety and monitoring the environment. Furthermore, aptamers play promising roles as clinical diagnostics and therapeutic agents. This review provides update on the recent advances in this rapidly progressing field of research with particular emphasis on generation of aptamers and their applications in biosensing, biotechnology and medicine. The limitations and future directions of aptamers in target specific delivery and real-time detection are also discussed.

Double-negative-index ceramic aerogels for thermal superinsulation

Abstract: Ceramic aerogels are attractive for thermal insulation but plagued by poor mechanical stability and degradation under thermal shock. In this study, we designed and synthesized hyperbolic architectured ceramic aerogels with nanolayered double-pane walls with a negative Poisson’s ratio (−0.25) and a negative linear thermal expansion coefficient (−1.8 × 10 −6 per °C). Our aerogels display robust mechanical and thermal stability and feature ultralow densities down to ~0.1 milligram per cubic centimeter, superelasticity up to 95%, and near-zero strength loss after sharp thermal shocks (275°C per second) or intense thermal stress at 1400°C, as well as ultralow thermal conductivity in vacuum [~2.4 milliwatts per meter-kelvin (mW/m·K)] and in air (~20 mW/m·K). This robust material system is ideal for thermal superinsulation under extreme conditions, such as those encountered by spacecraft.

Progressive Image Deraining Networks: A Better and Simpler Baseline

Abstract: Along with the deraining performance improvement of deep networks, their structures and learning become more and more complicated and diverse, making it difficult to analyze the contribution of various network modules when developing new deraining networks. To handle this issue, this paper provides a better and simpler baseline deraining network by considering network architecture, input and output, and loss functions. Specifically, by repeatedly unfolding a shallow ResNet, progressive ResNet (PRN) is proposed to take advantage of recursive computation. A recurrent layer is further introduced to exploit the dependencies of deep features across stages, forming our progressive recurrent network (PReNet). Furthermore, intra-stage recursive computation of ResNet can be adopted in PRN and PReNet to notably reduce network parameters with graceful degradation in deraining performance. For network input and output, we take both stage-wise result and original rainy image as input to each ResNet and finally output the prediction of {residual image}. As for loss functions, single MSE or negative SSIM losses are sufficient to train PRN and PReNet. Experiments show that PRN and PReNet perform favorably on both synthetic and real rainy images. Considering its simplicity, efficiency and effectiveness, our models are expected to serve as a suitable baseline in future deraining research. The source codes are available at this https URL.