Due to object detection’s close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles that combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy, and optimization function. In this paper, we provide a review of deep learning-based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely, the convolutional neural network. Then, we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection, and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.

Object Detection With Deep Learning: A Review

Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement. The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy -- pixel-, patch- and map- level -- by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersection-over-Union (IoU) losses. Equipped with the hybrid loss, the proposed predict-refine architecture is able to effectively segment the salient object regions and accurately predict the fine structures with clear boundaries. Experimental results on six public datasets show that our method outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Our method runs at over 25 fps on a single GPU. The code is available at: https://github.com/NathanUA/BASNet.

/pdf/basnet-boundary-aware-salient-object-detection-13wvhaxy88.pdf

BASNet: Boundary-Aware Salient Object Detection

Saliency in Context (SALICON) is an ongoing effort that aims at understanding and predicting visual attention. Conventional saliency models typically rely on low-level image statistics to predict human fixations. While these models perform significantly better than chance, there is still a large gap between model prediction and human behavior. This gap is largely due to the limited capability of models in predicting eye fixations with strong semantic content, the so-called semantic gap. This paper presents a focused study to narrow the semantic gap with an architecture based on Deep Neural Network (DNN). It leverages the representational power of high-level semantics encoded in DNNs pretrained for object recognition. Two key components are fine-tuning the DNNs fully convolutionally with an objective function based on the saliency evaluation metrics, and integrating information at different image scales. We compare our method with 14 saliency models on 6 public eye tracking benchmark datasets. Results demonstrate that our DNNs can automatically learn features particularly for saliency prediction that surpass by a big margin the state-of-the-art. In addition, our model ranks top to date under all seven metrics on the MIT300 challenge set.

/pdf/salicon-reducing-the-semantic-gap-in-saliency-prediction-by-3rx6xe71p7.pdf

SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks

Deep networks have been proved to encode high level semantic features and delivered superior performance in saliency detection. In this paper, we go one step further by developing a new saliency model using recurrent fully convolutional networks (RFCNs). Compared with existing deep network based methods, the proposed network is able to incorporate saliency prior knowledge for more accurate inference. In addition, the recurrent architecture enables our method to automatically learn to refine the saliency map by correcting its previous errors. To train such a network with numerous parameters, we propose a pre-training strategy using semantic segmentation data, which simultaneously leverages the strong supervision of segmentation tasks for better training and enables the network to capture generic representations of objects for saliency detection. Through extensive experimental evaluations, we demonstrate that the proposed method compares favorably against state-of-the-art approaches, and that the proposed recurrent deep model as well as the pre-training method can significantly improve performance.

/pdf/saliency-detection-with-recurrent-fully-convolutional-2f5mzhfiwm.pdf

Saliency Detection with Recurrent Fully Convolutional Networks

In this paper, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although convolutional neural networks (CNNs) have made substantial improvement on human attention prediction, it is still needed to improve the CNN-based attention models by efficiently leveraging multi-scale features. Our visual attention network is proposed to capture hierarchical saliency information from deep, coarse layers with global saliency information to shallow, fine layers with local saliency response. Our model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields. Final saliency prediction is achieved via the cooperation of those global and local predictions. Our model is learned in a deep supervision manner, where supervision is directly fed into multi-level layers, instead of previous approaches of providing supervision only at the output layer and propagating this supervision back to earlier layers. Our model thus incorporates multi-level saliency predictions within a single network, which significantly decreases the redundancy of previous approaches of learning multiple network streams with different input scales. Extensive experimental analysis on various challenging benchmark data sets demonstrate our method yields the state-of-the-art performance with competitive inference time. 1 1 Our source code is available at https://github.com/wenguanwang/deepattention .

Deep Visual Attention Prediction

Learning to predict eye fixations for semantic contents using multi-layer sparse network

In recent decades, webpages are becoming an increasingly important visual information source. Compared with natural images, webpages are different in many ways. For example, webpages are usually rich in semantically meaningful visual media (text, pictures, logos, and animations), which make the direct application of some traditional low-level saliency models ineffective. Besides, distinct web-viewing patterns such as top-left bias and banner blindness suggest different ways for predicting attention deployment on a webpage. In this study, we utilize a new scheme of low-level feature extraction pipeline and combine it with high-level representations from deep neural networks. The proposed model is evaluated on a newly published webpage saliency dataset with three popular evaluation metrics. Results show that our model outperforms other existing saliency models by a large margin and both low- and high-level features play an important role in predicting fixations on webpage.

Predicting Eye Fixations on Webpage With an Ensemble of Early Features and High-Level Representations from Deep Network

In this paper, ultrasound imaging is utilized to detect the anatomical structure of the lumbar spine based on which an image processing algorithm will search for key features to identify the optimal needle insertion site. The key challenge lies in the nature of ultrasound images which are obscure and have low spatial resolution, induced by contamination from random speckle noises. In order to improve the interpretability of ultrasound images, a modified version of local normalization using the Difference of Gaussian algorithm is first used for pre-processing to filter the speckle noise and extract the main anatomical structure in the raw images obtained. Meanwhile, local means induced by non-uniform wave reflection rate is also successfully removed by the proposed pre-processing algorithm, thus a potential element that may degrade the image recognition accuracy is excluded. In the second stage, a template matching algorithm, augmented with a position correlation function, automatically identifies the key features of interest and thus the insertion site. The approach has been tested on more than 200 ultrasound images with a 100% success rate. The proposed system allows the anesthetist to use the approach efficiently without the burden of interpreting real time ultrasound images.

Chengyao Shen

Papers

SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks

Learning to predict eye fixations for semantic contents using multi-layer sparse network

Predicting Eye Fixations on Webpage With an Ensemble of Early Features and High-Level Representations from Deep Network

Ultrasound guided automatic localization of needle insertion site for epidural anesthesia

Geometrically local embedding in manifolds for dimension reduction