Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier feature representations. In this paper, we develop a novel variational non-local network-based outlier rejection framework for robust alignment. By reformulating the non-local feature learning with variational Bayesian inference, the Bayesian-driven long-range dependencies can be modeled to aggregate discriminative geometric context information for inlier/outlier distinction. Specifically, to achieve such Bayesian-driven contextual dependencies, each query/key/value component in our nonlocal network predicts a prior feature distribution and a posterior one. Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative. Thus, pushing the prior to be close to the discriminative posterior in the training step enables the features sampled from this prior at test time to model highquality long-range dependencies. Notably, to achieve effective posterior feature guidance, a specific probabilistic graphical model is designed over our non-local model, which lets us derive a variational low bound as our optimization objective for model training. Finally, we propose a voting-based inlier searching strategy to cluster the high-quality hypothetical inliers for transformation estimation. Extensive experiments on 3DMatch, 3DLoMatch, and KITTI datasets verify the effectiveness of our method. Code is available at https://github.com/Jiang-HB/VBReg.

Person retrieval largely relies on the appearance features of pedestrians. This task is rather more difficult in surveillance videos due to the limitations of extracting robust appearance features brought by the cross-view and cross-camera data with lower image resolution, motion blur, occlusion and other kinds of image degradation. To build up a more reliable person retrieval system, recent works introduced appearance attribute models to describe and distinguish different persons with high-level semantic concepts. Despite the progress of previous works, the value of utilizing appearance attributes is still under-explored. On one hand, existing methods lack for concise and precise attribute representations that are specific for each attribute category and, in the meantime, are able to filter noisy information in irrelevant spatial locations and useless patterns. On the other hand, correlation and reasoning between different attributes are neglected, which could generate more useful information and add more robustness to the retrieval system. In this paper, we propose an Attribute Mining and Reasoning (AMR) framework which is capable to handle the issues in question. The AMR makes better use of appearance attributes with two main components. First, the AMR disentangles the representations of different attributes by localizing their spatial positions and identifying their effective patterns in a weakly supervised manner. To achieve more reliable localization, we propose the Attribute Localization Ensemble (ALE) module that is consisted of multiple localization heads and a voting mechanism. Second, we introduce the Attribute Reasoning (AR) module to correlate different attributes together with the global appearance features and discover their latent relations to generate more comprehensive descriptions of pedestrians. Extensive experiments on DukeMTMC-ReID and Market-1501 datasets demonstrate the effectiveness of the proposed AMR framework as well as its superiority over the existing state-of-the-art methods. The AMR model also shows great generalization ability on the unseen CUHK03 dataset when it is only trained on Market-1501 dataset.

Person retrieval aims at effectively matching the pedestrian images over an extensive database given a specified identity. As extracting effective features is crucial in a high-performance retrieval system, recent significant progress was achieved by part-based models that have constructed robust local representations on top of vertically striped part features. However, this kind of models use predefined partitioning strategies, making the number and size of each partition identical even when input images vary a lot. This unchangeable setting usually leads to less flexibility and robustness in capturing visual variance. The primary reason for such a negative effect is that a fixed partitioning strategy is unable to deal with (a) the significant variance from pose, illumination and viewpoint which is common in a pedestrian image dataset, and (b) also the inference error and misalignment of human bodies introduced by the prepositive pedestrian detection module or human pose estimation module. In this paper, we tackle this problem via introducing the novel Adaptive Partition Network (APN). The APN utilizes deep reinforcement learning and applies an agent to generate optimal partitioning strategies dynamically for different input images. The agent inside the APN is optimized with the policy gradient algorithm and maximizes the reward of choosing the best partition setting. By leveraging the supervision cues from the objective partitioning strategies that are generated on a set of held-out training images, the agent is trained jointly with other parts of APN, which ensures the APN's robustness and generalization ability. Extensive experimental results on multiple datasets, including CUHK03, DukeMTMC and Market-1501, demonstrate the superiority of APN over the state-of-the-art models.

Semantic segmentation is an important computer vision task, which aims to allocate a semantic label to each pixel in an image. When training a segmentation model, it is common to fine-tune a classification network pre-trained on a large-scale dataset. However, as an intrinsic property of the classification model, invariance to spatial perturbation resulting from the lose of detail-sensitivity prevents segmentation networks from achieving high performance. The use of standard poolings is one of the key factors for this invariance. The most common standard poolings are max and average pooling. Max pooling can increase both the invariance to spatial perturbations and the non-linearity of the networks. Average pooling, on the other hand, is sensitive to spatial perturbations, but is a linear function. For semantic segmentation, we prefer both the preservation of detailed cues within a local feature region and non-linearity that increases a network's functional complexity. In this work, we propose a polynomial pooling (P-pooling) function that finds an intermediate form between max and average pooling to provide an optimally balanced and self-adjusted pooling strategy for semantic segmentation. The P-pooling is differentiable and can be applied into a variety of pre-trained networks. Extensive studies on the PASCAL VOC, Cityscapes and ADE20k datasets demonstrate the superiority of P-pooling over other poolings. Experiments on various network architectures and state-of-the-art training strategies also show that models with P-pooling layers consistently outperform those directly fine-tuned using pre-trained classification models.

In the literature of video analysis, most researches, such as retrieval and recognition, hypothesize that each input video contains at least one complete semantic entity, e.g. an activity, action and event.However, this hypothesis does not hold in many realistic scenarios due to two main reasons. First, complete videos whose qualities are good enough for automatic analysis are not always accessible because of heavy motion blur, occlusions, interruptions, etc. % Second, extracting features from complete videos always fails to meet up with speed and storage requirements in large-scale use cases.To tackle these challenges, incomplete videos are more useful, but researches on them are seldom mentioned. In this paper, we propose a novel and effective hashing framework specialized in large-scale incomplete video analysis called Generative Reconstructive Hashing (GRH). To begin with, an adversarial generative network that is specially designed to map incomplete video features to the feature distributions of complete videos, so that features of incomplete videos become indistinguishable from those of complete videos. Then, the discriminative hashing module further fills the gap between full video features and estimated features from partial videos by projecting both features into a common binary feature space, which allows improvement in efficiency compared with real-value based methods. GRH is the first end-to-end framework for incomplete video analysis. Extensive experiments on various datasets demonstrate GRH's superior effectiveness and efficiency on retrieval and recognition tasks. GRH outperforms the recent state-of-the-art methods by 5.44/3.22/4.82 in terms of MAPs on HMDB51/UCF101/CCV datasets, respectively.

In this paper, we propose a design scheme for deep learning networks in face parsing task with promising accuracy and real-time inference speed. By analyzing the differences between general image parsing task and face parsing task, we first revisit the structure of traditional FCN and make improvements to adapt to the unique properties of face parsing task. Especially, the concept of Normalized Receptive Field is proposed to give more insights on designing the network. Then a novel loss function called Statistical Contextual Loss is introduced, which integrates richer contextual information and regularizes features during training. For further model acceleration, we propose a semi-supervised distillation scheme that effectively transfers the learned knowledge to a lighter network. Extensive experiments on LFW and Helen dataset demonstrate the significant superiority of the new design scheme on both efficacy and efficiency.

In this paper, we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks. Unlike previous work which placed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the network's backbone and operates on feature maps. Feature maps are inflated or shrunk by the new layer, thereby changing the receptive fields in the following layers. By use of end-to-end training, the whole framework is data-driven, without laborious manual intervention. The proposed method is generic across datasets and different tasks. We have conducted extensive experiments on both general image parsing tasks, and face parsing tasks as concrete examples, to demonstrate the method's superior ability to regulate over manual designs.

Image retargeting has been applied to display images of any size via devices with various resolutions (e.g., cell phone, TV monitors). To fit an image with the target resolution, certain unimportant regions need to be deleted or distorted and the key problem is to determine the importance of each pixel. Existing methods predict pixel-wise importance in a bottom-up manner via eye fixation estimation or saliency detection. In contrast, the proposed algorithm estimates the pixel-wise importance based on a top-down criterion where the target image maintains the semantic meaning of the original image. To this end, several semantic components corresponding to foreground objects, action contexts, and background regions are extracted. The semantic component maps are integrated by a classification guided fusion network. Specifically, the deep network classifies the original image as object or scene-oriented, and fuses the semantic component maps according to classification results. The network output, referred to as the semantic collage with the same size as the original image, is then fed into any existing optimization method to generate the target image. Extensive experiments are carried out on the RetargetMe dataset and S-Retarget database developed in this work. Experimental results demonstrate the merits of the proposed algorithm over the state-of-the-art image retargeting methods.

In this paper, we introduce a novel approach to regulate receptive field in deep image parsing network automatically. Unlike previous works which have stressed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the networks backbone and operates on feature maps. Feature maps will be inflated/shrinked by the new layer and therefore receptive fields in following layers are changed accordingly. By end-to-end training, the whole framework is data-driven without laborious manual intervention. The proposed method is generic across dataset and different tasks. We conduct extensive experiments on both general parsing task and face parsing task as concrete examples to demonstrate the methods superior regulation ability over manual designs.