Benefiting from the quick development of deep convolutional neural networks, especially fully convolutional neural networks (FCNs), remarkable progresses have been achieved on salient object detection recently. Nevertheless, these FCNs based methods are still challenging to generate high resolution saliency maps, and also not applicable for subsequent applications due to their heavy model weights. In this paper, we propose a compact and efficient deep network with high accuracy for salient object detection. Firstly, we propose two strategies for initial prediction, one is a new designed multi-scale context module, the other is incorporating hand-crafted saliency priors. Secondly, we employ residual learning to refine it progressively by only learning the residual in each side-output, which can be achieved with few convolutional parameters, therefore leads to high compactness and high efficiency. Finally, we further design a novel reverse attention block to guide side-output residual learning in a top-down manner. Specifically, the current predicted salient regions are erased from each side-output feature, thus the missing object parts and details can be efficiently learned from these unerased regions, which results in high resolution and accuracy. Extensive experimental results on seven benchmark datasets demonstrate that the proposed network performs favorably against the state-of-the-art methods, and with advantages in terms of simplicity, efficiency and model size.

Salient object detection is usually used as a preprocessing step to facilitate a variety of subsequent applications which should take little time cost. With the quick development of deep learning recently, profound progresses have been made to achieve a new state-of-the-art performance. However, the learned features of the existing deep learning-based methods are not accurate enough thus leading to unsatisfactory detection in complex scenes, such as low contrast or very similar between salient object and background region and multiple (small) salient objects with diverse characteristics. In addition, some post-processing techniques are usually needed for refinement, which is time consuming. To address these issues, this paper presents an efficient fully convolutional salient object detection network. Specifically, we first introduce a visual attention mechanism to guide feature learning in side output layers. In detail, attention weight is employed in a top-down manner which can bridge high level semantic information to help shallow layers better locate salient objects and also filter out noisy response in the background region. Second, we propose a residual refinement network to fuse the learned multilevel features gradually. Not to simply add or concatenate them step by step as previous works, we introduce a second-order term into element-wise addition to learn stage-wise residual features for refinement. Such a second-order term not only benefits efficient gradient propagation but also increases network nonlinearity. Extensive experiments on seven standard benchmarks demonstrate that the proposed approach achieves consistently superior performance and performs well on small salient object detection in comparison with the very recent state-of-the-arts, especially in the metric of structure-measure.

Crowds often appear in surveillance videos in public places, from which anomaly detection is of great importance to public safety. Since the abnormal cases are rare, variable and unpredictable, autoencoders with encoder and decoder structures using only normal samples have become a hot topic among various approaches for anomaly detection. However, since autoencoders have excessive generalization ability, they can sometimes still reconstruct abnormal cases very well. Recently, some researchers construct memory modules under normal conditions and use these normal memory items to reconstruct test samples during inference to increase the reconstruction errors for anomalies. However, in practice, the errors of reconstructing normal samples with the memory items often increase as well, which makes it still difficult to distinguish between normal and abnormal cases. In addition, the memory-based autoencoder is usually available only in the specific scene where the memory module is constructed and almost loses the prospect of cross-scene applications. We mitigate the overgeneralization of autoencoders from a different perspective, namely, by reducing the prediction errors for normal cases rather than increasing the prediction errors for abnormal cases. To this end, we propose an autoencoder based on hybrid attention and motion constraint for anomaly detection. The hybrid attention includes the channel attention used in the encoding process and spatial attention added to the skip connection between the encoder and decoder. The hybrid attention is introduced to reduce the weight of the feature channels and regions representing the background in the feature matrix, which makes the autoencoder features more focused on optimizing the representation of the normal targets during training. Furthermore, we introduce motion constraint to improve the autoencoder’s ability to predict normal activities in crowded scenes. We conduct experiments on real-world surveillance videos, UCSD, CUHK Avenue, and ShanghaiTech datasets. The experimental results indicate that the prediction errors of the proposed method for frequent normal crowd activities are smaller than those of other approaches, which increases the gap between the prediction errors for normal frames and the prediction errors for abnormal frames. In addition, the proposed method does not depend on a specific scene. Therefore, it balances good anomaly detection performance and strong cross-scene capability.