Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key to accurate person ReID, because many identities can be differentiated only when looking into these fine-grained differences. However, most state-of-the-art person ReID approaches, typically driven by a triplet loss, fail to effectively learn the fine-grained features as they are focused more on differentiating large appearance differences. To address this issue, we introduce a novel pairwise loss function that enables ReID models to learn the fine-grained features by adaptively enforcing an exponential penalization on the images of small differences and a bounded penalization on the images of large differences. The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches. Experimental results on four benchmark datasets show that the proposed loss substantially outperforms a number of popular loss functions by large margins; and it also enables significantly improved data efficiency.

This article investigates the problem of enhancing underwater visual observations for the purpose of accurate underwater object detection. Most existing underwater visual enhancement algorithms tend to follow human vision preference but do not necessarily favor the effectiveness of an object detection algorithm. We observe that it should not be the human vision preference but the object detection algorithm that knows what underwater visual enhancement configuration is most beneficial to the detection tasks. In light of this observation, we propose a reinforcement learning paradigm of configuring visual enhancement for object detection in underwater scenes. Specifically, we use underwater image features as states and object detection score increments as rewards. We set up a collection of extensible actions that consist of multiple visual enhancement algorithms. The optimal policy is learned in the form of an action sequence, which characterizes a stepwise process of visual enhancement. Experimental results validate that the sequence of visual enhancement algorithms configured with respect to the object detection algorithm is in favor of improving the detection results.

At present, effectively aggregating and transferring the local features of point cloud is still an unresolved technological conundrum. In this study, we propose a new space-cover convolutional neural network (SC-CNN) for tasks such as point cloud classification and segmentation. The core of this network is space-cover convolution (SC-Conv), which implements depthwise separable convolution on the point cloud. In addition, a newly designed space-cover operator (SCOP) replaces depthwise convolution. The key to SC-Conv is constructing anisotropic spatial geometry in the local point cloud. The SCOP achieves this by utilizing the positional and feature relationships to learn the high-order relationship expression between points. First, data-driven adaptive learning from the 3-D coordinate relationship between the local points is used to determine the weight of the SCOP. Then, the edge feature of the neighboring point relative to the sampling point is used as the input of the SCOP. Finally, a deformable spatial geometry is constructed in the feature space between local points to aggregate the local high-order features. By stacking SC-Conv to construct SC-CNN with a hierarchical network structure for point cloud analysis, we can better perceive the shape information of point cloud and improve network robustness. Finally, we provide numerous experiments to verify that SC-CNN parallels or even outperforms advanced methods in shape classification, part segmentation, and large-scale indoor scene segmentation tasks. The open-source code was published at https://github.com/changshuowang/SC-CNN .

Speckle noise is an inherent but annoying property in the synthetic aperture radar (SAR) imaging. In this paper we investigate the influence of speckle on the classical convolutional neural network (CNN) for SAR target classification. Then a dual stage coupled CNN architecture, named despeckling and classification coupled CNNs (DCC-CNNs), is proposed to distinguish multiple categories of ground targets in SAR images with strong and varying speckle. It first applies the despeckling sub-network for noise reduction. After that, residual speckle features as well as target information would be learned by the classification sub-network in order to solve the noise robustness problem of CNN. Besides, a new quantitative measure is developed for the quality assessment of SAR target images. It takes into account structural properties of the speckled SAR image of the target of interest and consistency with visual perception. Finally, a series of comparative experiments and discussions are carried out to validate the proposed assessment criterion and DCC-CNNs. Using synthetic SAR images based on the public MSTAR datasets, results show that the overall classification accuracy for ten ground target classes could be higher than 82% at a variety of speckle noise levels.

Compared with color or grayscale images, hyperspectral images deliver more informative representation of ground objects and enhance the performance of many recognition and classification applications. However, hyperspectral images are normally corrupted by various types of noises, which have a serious impact on the subsequent image processing tasks. In this paper, we propose a novel hyperspectral image denoising method based on tucker decomposition to model the nonlocal similarity across the spatial domain and global similarity along the spectral domain. In this method, 3-D full band patches extracted from a hyperspectral image are grouped to form a third-order tensor by utilizing the nonlocal similarity in a proper window size. In this way, the task of image denoising is transformed into a high-order tensor approximation problem, which can be solved by nonnegative tucker decomposition. Instead of a traditional alternative least square based tucker decomposition, we propose a hierarchical least square based nonnegative tucker decomposition method to reduce the computational cost and improve the denoising effect. In addition, an iterative denoising strategy is adopted to achieve better denoising outcome in practice. Experimental results on three datasets show that the proposed method outperforms several state-of-the-art methods and significantly enhances the quality of the corrupted hyperspectral image.