Energy-based latent variable models (EBLVMs) are more expressive than conventional energy-based models. However, its potential on visual tasks are limited by its training process based on maximum likelihood estimate that requires sampling from two intractable distributions. In this paper, we propose Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs. Particularly, we lead a decoupled EBLVM consisting of a marginal energy-based distribution and a structural posterior to handle the difficulties when learning deep EBLVMs on images. By choosing a symmetric KL divergence in the lower level of our framework, a compact BiDVL for visual tasks can be obtained. Our model achieves impressive image generation performance over related works. It also demonstrates the significant capacity of testing image reconstruction and out-of-distribution detection.
Batch normalization (BN) is a milestone technique in deep learning. It normalizes the activation using mini-batch statistics during training but the estimated population statistics during inference. This paper focuses on investigating the estimation of population statistics. We define the estimation shift magnitude of BN to quantitatively measure the difference between its estimated population statistics and expected ones. Our primary observation is that the estimation shift can be accumulated due to the stack of BN in a network, which has detriment effects for the test performance. We further find a batch-free normalization (BFN) can block such an accumulation of estimation shift. These observations motivate our design of XBNBlock that replace one BN with BFN in the bottleneck block of residual-style networks. Experiments on the ImageNet and COCO benchmarks show that XBNBlock consistently improves the performance of different architectures, including ResNet and ResNeXt, by a significant margin and seems to be more robust to distribution shift.
Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from both visual and textual modality. Nevertheless, due to the complexity of high-dimensional data, the unconstrained mapping paradigms are not able to properly catch discriminative clues about the corresponding person while drop the misaligned information. Intuitively, the information contained in visual data can be divided into person information (PI) and surroundings information (SI), which are mutually exclusive from each other. To this end, we propose a novel Deep Surroundings-person Separation Learning (DSSL) model in this paper to effectively extract and match person information, and hence achieve a superior retrieval accuracy. A surroundings-person separation and fusion mechanism plays the key role to realize an accurate and effective surroundings-person separation under a mutually exclusion constraint. In order to adequately utilize multi-modal and multi-granular information for a higher retrieval accuracy, five diverse alignment paradigms are adopted. Extensive experiments are carried out to evaluate the proposed DSSL on CUHK-PEDES, which is currently the only accessible dataset for text-base person retrieval task. DSSL achieves the state-of-the-art performance on CUHK-PEDES. To properly evaluate our proposed DSSL in the real scenarios, a Real Scenarios Text-based Person Reidentification (RSTPReid) dataset is constructed to benefit future research on text-based person retrieval, which will be publicly available.
Recommender systems are an essential component of e-commerce marketplaces, helping consumers navigate massive amounts of inventory and find what they need or love. In this paper, we present an approach for generating personalized item recommendations in an e-commerce marketplace by learning to embed items and users in the same vector space. In order to alleviate the considerable cold-start problem present in large marketplaces, item and user embeddings are computed using content features and multi-modal onsite user activity respectively. Data ablation is incorporated into the offline model training process to improve the robustness of the production system. In offline evaluation using a dataset collected from eBay traffic, our approach was able to improve the Recall@k metric over the Recently-Viewed-Item (RVI) method. This approach to generating personalized recommendations has been launched to serve production traffic, and the corresponding scalable engineering architecture is also presented. Initial A/B test results show that compared to the current personalized recommendation module in production, the proposed method increases the surface rate by $\sim$6\% to generate recommendations for 90\% of listing page impressions.
Temporal action proposal generation, coming from temporal action recognition, is an important and challenging problem in computer vision. Because of the big capacity of video files, the speed of temporal action recognition is difficult for both researchers and companies. To training a convolutional neural network (CNN) for temporal action recognition, a lot of videos are required to put into the CNN. A speed-up for the task should be proposed for the training process to achieve the faster response of temporal action recognition system. To address it, we implement ring parallel architecture by Massage Passing Interface (MPI). Different from traditional parameter server architecture, total data transmission is reduced by adding a connection between multiple computing load in our new architecture. Compared to parameter server architecture, our parallel architecture has higher efficiency on temporal action proposal generation task with multiple GPUs, which is significant to dealing with large-scale video database. And based on the absence of evaluating time consumption in a distributed deep learning system, we proposed a concept of training time metrics which can assess the performance in the distributed training process.
Objective: Schizophrenia seriously affects the quality of life. To date, both simple (linear discriminant analysis) and complex (deep neural network) machine learning methods have been utilized to identify schizophrenia based on functional connectivity features. The existing simple methods need two separate steps (i.e., feature extraction and classification) to achieve the identification, which disables simultaneous tuning for the best feature extraction and classifier training. The complex methods integrate two steps and can be simultaneously tuned to achieve optimal performance, but these methods require a much larger amount of data for model training. Methods: To overcome the aforementioned drawbacks, we proposed a multi-kernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure. Kernels were set to match with partition sizes of brain anatomical structure in order to capture interregional connectivities at the varying scales. With the inspiration of widely-used dropout strategy in deep learning, we developed vector dropout in the capsule layer to prevent overfitting of the model. Results: The comparison results showed that the proposed method outperformed the state-of-the-art methods. Besides, we compared performances using different parameters and illustrated the routing process to reveal characteristics of the proposed method. Conclusion: MKCapsnet is promising for schizophrenia identification. Significance: Our study not only proposed a multi-kernel capsule network but also provided useful information in the parameter setting, which is informative for further studies using a capsule network for neurophysiological signal classification.
Temporal action proposal generation is an important and challenging problem in computer vision. The biggest challenge for the task is generating proposals with precise temporal boundaries. To address these difficulties, we improved the algorithm based on boundary sensitive network. The popular temporal convolution network today overlooked the original meaning of the single video feature vector. We proposed a new temporal convolution network called Multipath Temporal ConvNet (MTN), which consists of two parts i.e. Multipath DenseNet and SE-ConvNet, can extract more useful information from the video database. Besides, to respond to the large memory occupation and a large number of videos, we abandon traditional parameter server parallel architecture and introduce high performance computing into temporal action proposal generation. To achieve this, we implement ring parallel architecture by Massage Passing Interface (MPI) acting on our method. Compared to parameter server architecture, our parallel architecture has higher efficiency on temporal action detection task with multiple GPUs, which is significant to dealing with large-scale video database. We conduct experiments on ActivityNet-1.3 and THUMOS14, where our method outperforms other state-of-art temporal action detection methods with high recall and high temporal precision.
It is challenging to detect the anomaly in crowded scenes for quite a long time. In this paper, a self-supervised framework, abnormal event detection network (AED-Net), which is composed of PCAnet and kernel principal component analysis (kPCA), is proposed to address this problem. Using surveillance video sequences of different scenes as raw data, PCAnet is trained to extract high-level semantics of crowd's situation. Next, kPCA,a one-class classifier, is trained to determine anomaly of the scene. In contrast to some prevailing deep learning methods,the framework is completely self-supervised because it utilizes only video sequences in a normal situation. Experiments of global and local abnormal event detection are carried out on UMN and UCSD datasets, and competitive results with higher EER and AUC compared to other state-of-the-art methods are observed. Furthermore, by adding local response normalization (LRN) layer, we propose an improvement to original AED-Net. And it is proved to perform better by promoting the framework's generalization capacity according to the experiments.
As an important research topic in computer vision, fine-grained classification which aims to recognition subordinate-level categories has attracted significant attention. We propose a novel region based ensemble learning network for fine-grained classification. Our approach contains a detection module and a module for classification. The detection module is based on the faster R-CNN framework to locate the semantic regions of the object. The classification module using an ensemble learning method, which trains a set of sub-classifiers for different semantic regions and combines them together to get a stronger classifier. In the evaluation, we implement experiments on the CUB-2011 dataset and the result of experiments proves our method s efficient for fine-grained classification. We also extend our approach to remote scene recognition and evaluate it on the NWPU-RESISC45 dataset.
In the real-life environments, due to the sudden appearance of windows, lights, and objects blocking the light source, the visual SLAM system can easily capture the low-contrast images caused by over-exposure or over-darkness. At this time, the direct method of estimating camera motion based on pixel luminance information is infeasible, and it is often difficult to find enough valid feature points without image processing. This paper proposed HE-SLAM, a new method combining histogram equalization and ORB feature extraction, which can be robust in more scenes, especially in stages with low-contrast images. Because HE-SLAM uses histogram equalization to improve the contrast of images, it can extract enough valid feature points in low-contrast images for subsequent feature matching, keyframe selection, bundle adjustment, and loop closure detection. The proposed HE-SLAM has been tested on the popular datasets (such as KITTI and EuRoc), and the real-time performance and robustness of the system are demonstrated by comparing system runtime and the mean square root error (RMSE) of absolute trajectory error (ATE) with state-of-the-art methods like ORB-SLAM2.