Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

/pdf/deep-learning-for-generic-object-detection-a-survey-1j2k8px4h1.pdf

Deep Learning for Generic Object Detection: A Survey

Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are...

A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures

Deep neural networks have been successfully used in diverse emerging domains to solve real world complex problems with may more deep learning(DL) architectures, being developed to date. To achieve these state-of-the-art performances, the DL architectures use activation functions (AFs), to perform diverse computations between the hidden layers and the output layers of any given DL architecture. This paper presents a survey on the existing AFs used in deep learning applications and highlights the recent trends in the use of the activation functions for deep learning applications. The novelty of this paper is that it compiles majority of the AFs used in DL and outlines the current trends in the applications and usage of these functions in practical deep learning deployments against the state-of-the-art research results. This compilation will aid in making effective decisions in the choice of the most suitable and appropriate activation function for any given application, ready for deployment. This paper is timely because most research papers on AF highlights similar works and results while this paper will be the first, to compile the trends in AF applications in practice against the research results from literature, found in deep learning research to date.

Activation Functions: Comparison of trends in Practice and Research for Deep Learning

In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by using procedurally generated environments to construct distinct training and test sets. Most notably, we introduce a new environment called CoinRun, designed as a benchmark for generalization in RL. Using CoinRun, we find that agents overfit to surprisingly large training sets. We then show that deeper convolutional architectures improve generalization, as do methods traditionally found in supervised learning, including L2 regularization, dropout, data augmentation and batch normalization.

/pdf/quantifying-generalization-in-reinforcement-learning-qiqztnodaw.pdf

Quantifying Generalization in Reinforcement Learning

A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention from both industry and academia in the past few years. The existing reviews mainly focus on CNN's applications in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide some novel ideas and prospects in this fast-growing field. Besides, not only 2-D convolution but also 1-D and multidimensional ones are involved. First, this review introduces the history of CNN. Second, we provide an overview of various convolutions. Third, some classic and advanced CNN models are introduced; especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for functions and hyperparameter selection. Fifth, the applications of 1-D, 2-D, and multidimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed as guidelines for future work. 

/pdf/a-survey-of-convolutional-neural-networks-analysis-1hzyfrmo.pdf

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

Constructing effective representations is a critical but challenging problem in multimedia understanding. The traditional handcraft features often rely on domain knowledge, limiting the performances of exiting methods. This paper discusses a novel computational architecture for general image feature mining, which assembles the primitive filters (i.e. Gabor wavelets) into compositional features in a layer-wise manner. In each layer, we produce a number of base classifiers (i.e. regression stumps) associated with the generated features, and discover informative compositions by using the boosting algorithm. The output compositional features of each layer are treated as the base components to build up the next layer. Our framework is able to generate expressive image representations while inducing very discriminate functions for image classification. The experiments are conducted on several public datasets, and we demonstrate superior performances over state-of-the-art approaches.

Deep Boosting: Layered Feature Mining for General Image Classification

To further reduce the cost of semi-supervised domain adaptation (SSDA) labeling, a more effective way is to use active learning (AL) to annotate a selected subset with specific properties. However, domain adaptation tasks are always addressed in two interactive aspects: domain transfer and the enhancement of discrimination, which requires the selected data to be both uncertain under the model and diverse in feature space. Contrary to active learning in classification tasks, it is usually challenging to select pixels that contain both the above properties in segmentation tasks, leading to the complex design of pixel selection strategy. To address such an issue, we propose a novel Active Domain Adaptation scheme with Multi-level Contrastive Units (ADA-MCU) for semantic image segmentation. A simple pixel selection strategy followed with the construction of multi-level contrastive units is introduced to optimize the model for both domain adaptation and active supervised learning. In practice, MCUs are constructed from intra-image, cross-image, and cross-domain levels by using both labeled and unlabeled pixels. At each level, we define contrastive losses from center-to-center and pixel-to-pixel manners, with the aim of jointly aligning the category centers and reducing outliers near the decision boundaries. In addition, we also introduce a categories correlation matrix to implicitly describe the relationship between categories, which are used to adjust the weights of the losses for MCUs. Extensive experimental results on standard benchmarks show that the proposed method achieves competitive performance against state-of-the-art SSDA methods with 50% fewer labeled pixels and significantly outperforms state-of-the-art with a large margin by using the same level of annotation cost.

Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation

In recent years, the Transformer architecture has shown its superiority in the video-based person re-identification task. Inspired by video representation learning, these methods mainly focus on designing modules to extract informative spatial and temporal features. However, they are still limited in extracting local attributes and global identity information, which are critical for the person re-identification task. In this paper, we propose a novel Multi-Stage Spatial-Temporal Aggregation Transformer (MSTAT) with two novel designed proxy embedding modules to address the above issue. Specifically, MSTAT consists of three stages to encode the attribute-associated, the identity-associated, and the attribute-identity-associated information from the video clips, respectively, achieving the holistic perception of the input person. We combine the outputs of all the stages for the final identification. In practice, to save the computational cost, the Spatial-Temporal Aggregation (STA) modules are first adopted in each stage to conduct the self-attention operations along the spatial and temporal dimensions separately. We further introduce the Attribute-Aware and Identity-Aware Proxy embedding modules (AAP and IAP) to extract the informative and discriminative feature representations at different stages. All of them are realized by employing newly designed self-attention operations with specific meanings. Moreover, temporal patch shuffling is also introduced to further improve the robustness of the model. Extensive experimental results demonstrate the effectiveness of the proposed modules in extracting the informative and discriminative information from the videos, and illustrate the MSTAT can achieve state-of-the-art accuracies on various standard benchmarks.

/pdf/multi-stage-spatio-temporal-aggregation-transformer-for-3grkjm7e.pdf

Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification

Scheduling the training procedure of deep neural networks (DNNs) such as tuning the learning rates is crucial to the successes of deep learning. Previous strategies such as piecewise and exponential learning rate schedulers have different arguments (hyper-parameters) that need to be tuned manually. With the expanding of data scale and model computation, searching for these arguments spends lots of empirical efforts. To address this issue, this work proposes policy schedular that determines the arguments of learning rate (lr) by reinforcement learning, significantly reducing costs to tune them. The policy schedular possesses several appealing benefits. First, instead of manually defining the values of initial lr and ultimate lr, it autonomously determines these values in training. Second, rather than using predefined functions to update lr, it adaptively oscillates lr by monitoring learning curves without human intervention. Third, it is able to select lr for each block or layer of a DNN. Experiments show that the DNNs trained with policy schedular achieve superior performances, outperforming previous work on various tasks and benchmarks such as ImageNet, COCO, and learning-to-learn.

Scheduling Large-scale Distributed Training via Reinforcement Learning

Provided are a normalization method, apparatus and device for a deep neural network, and a storage medium. The method comprises: inputting an input data set into a deep neural network, wherein the input data set comprises at least one piece of input data (110); normalizing a feature graph set output by a network layer in the deep neural network from at least one dimension, thereby obtaining at least one dimension variance and at least one dimension mean value (120); and determining a normalized target feature graph set based on the at least one dimension variance and the at least one dimension mean value (130). Based on the method, the normalization is carried out in the at least one dimension, and statistical information of each dimension of the normalization operation is covered, so that good robustness is achieved for statistics of each dimension while not excessively relying on the batch size.

Zhanglin Peng

Papers

Deep Boosting: Layered Feature Mining for General Image Classification

Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation

Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification

Scheduling Large-scale Distributed Training via Reinforcement Learning

Normalization method, apparatus and device for deep neural network, and storage medium