Zhenhua Wang

Kaining Ying, Qing Zhong, Weian Mao et al.

The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS). Instance embedding learning is directly supervised by the contrastive loss computed upon the contrastive items (CIs), which are sets of anchor/positive/negative embeddings. Recent online VIS methods leverage CIs sourced from one reference frame only, which we argue is insufficient for learning highly discriminative embeddings. Intuitively, a possible strategy to enhance CIs is replicating the inference phase during training. To this end, we propose a simple yet effective training strategy, called Consistent Training for Online VIS (CTVIS), which devotes to aligning the training and inference pipelines in terms of building CIs. Specifically, CTVIS constructs CIs by referring inference the momentum-averaged embedding and the memory bank storage mechanisms, and adding noise to the relevant embeddings. Such an extension allows a reliable comparison between embeddings of current instances and the stable representations of historical instances, thereby conferring an advantage in modeling VIS challenges such as occlusion, re-identification, and deformation. Empirically, CTVIS outstrips the SOTA VIS models by up to +5.0 points on three VIS benchmarks, including YTVIS19 (55.1% AP), YTVIS21 (50.1% AP) and OVIS (35.5% AP). Furthermore, we find that pseudo-videos transformed from images can train robust models surpassing fully-supervised ones.

Xiaoyan Li, Gang Zhang, Hongyu Pan et al.

LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms. Previous point-based or sparse voxel-based methods are far away from real-time applications since time-consuming neighbor searching or sparse 3D convolution are employed. Recent 2D projection-based methods, including range view and multi-view fusion, can run in real time, but suffer from lower accuracy due to information loss during the 2D projection. Besides, to improve the performance, previous methods usually adopt test time augmentation (TTA), which further slows down the inference process. To achieve a better speed-accuracy trade-off, we propose Cascade Point-Grid Fusion Network (CPGNet), which ensures both effectiveness and efficiency mainly by the following two techniques: 1) the novel Point-Grid (PG) fusion block extracts semantic features mainly on the 2D projected grid for efficiency, while summarizes both 2D and 3D features on 3D point for minimal information loss; 2) the proposed transformation consistency loss narrows the gap between the single-time model inference and TTA. The experiments on the SemanticKITTI and nuScenes benchmarks demonstrate that the CPGNet without ensemble models or TTA is comparable with the state-of-the-art RPVNet, while it runs 4.7 times faster.

Zhenhua Wang, Kaining Ying, Jiajun Meng et al.

A comprehensive understanding of interested human-to-human interactions in video streams, such as queuing, handshaking, fighting and chasing, is of immense importance to the surveillance of public security in regions like campuses, squares and parks. Different from conventional human interaction recognition, which uses choreographed videos as inputs, neglects concurrent interactive groups, and performs detection and recognition in separate stages, we introduce a new task named human-to-human interaction detection (HID). HID devotes to detecting subjects, recognizing person-wise actions, and grouping people according to their interactive relations, in one model. First, based on the popular AVA dataset created for action detection, we establish a new HID benchmark, termed AVA-Interaction (AVA-I), by adding annotations on interactive relations in a frame-by-frame manner. AVA-I consists of 85,254 frames and 86,338 interactive groups, and each image includes up to 4 concurrent interactive groups. Second, we present a novel baseline approach SaMFormer for HID, containing a visual feature extractor, a split stage which leverages a Transformer-based model to decode action instances and interactive groups, and a merging stage which reconstructs the relationship between instances and groups. All SaMFormer components are jointly trained in an end-to-end manner. Extensive experiments on AVA-I validate the superiority of SaMFormer over representative methods. The dataset and code will be made public to encourage more follow-up studies.

Songlin Wei, Guodong Chen, Wenzheng Chi et al.

Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of Structure-From-Motion (SfM) simultaneously predict depth and camera relative pose. However, dynamically moving objects in the scene violate the static world assumption, resulting in inaccurate depths of dynamic objects. In this work, we propose a new method to address such dynamic object movements through monocular 3D object detection. Specifically, we first detect 3D objects in the images and build the per-pixel correspondence of the dynamic pixels with the detected object pose while leaving the static pixels corresponding to the rigid background to be modeled with camera motion. In this way, the depth of every pixel can be learned via a meaningful geometry model. Besides, objects are detected as cuboids with absolute scale, which is used to eliminate the scale ambiguity problem inherent in monocular vision. Experiments on the KITTI depth dataset show that our method achieves State-of-The-Art performance for depth estimation. Furthermore, joint training of depth, camera motion and object pose also improves monocular 3D object detection performance. To the best of our knowledge, this is the first work that allows a monocular 3D object detection network to be fine-tuned in a self-supervised manner.

Dongyan Guo, Yanyan Shao, Ying Cui et al.

Siamese network based trackers formulate the visual tracking task as a similarity matching problem. Almost all popular Siamese trackers realize the similarity learning via convolutional feature cross-correlation between a target branch and a search branch. However, since the size of target feature region needs to be pre-fixed, these cross-correlation base methods suffer from either reserving much adverse background information or missing a great deal of foreground information. Moreover, the global matching between the target and search region also largely neglects the target structure and part-level information. In this paper, to solve the above issues, we propose a simple target-aware Siamese graph attention network for general object tracking. We propose to establish part-to-part correspondence between the target and the search region with a complete bipartite graph, and apply the graph attention mechanism to propagate target information from the template feature to the search feature. Further, instead of using the pre-fixed region cropping for template-feature-area selection, we investigate a target-aware area selection mechanism to fit the size and aspect ratio variations of different objects. Experiments on challenging benchmarks including GOT-10k, UAV123, OTB-100 and LaSOT demonstrate that the proposed SiamGAT outperforms many state-of-the-art trackers and achieves leading performance. Code is available at: https://git.io/SiamGAT

Zhenhua Wang, Paul A. Parker, Scott H. Holan

Small area estimation models are essential for estimating population characteristics in regions with limited sample sizes, thereby supporting policy decisions, demographic studies, and resource allocation, among other use cases. The spatial Fay-Herriot model is one such approach that incorporates spatial dependence to improve estimation by borrowing strength from neighboring regions. However, this approach often requires substantial computational resources, limiting its scalability for high-dimensional datasets, especially when considering multiple (multivariate) responses. This paper proposes two methods that integrate the multivariate spatial Fay-Herriot model with spatial random effects, learned through variational autoencoders, to efficiently leverage spatial structure. Importantly, after training the variational autoencoder to represent spatial dependence for a given set of geographies, it may be used again in future modeling efforts, without the need for retraining. Additionally, the use of the variational autoencoder to represent spatial dependence results in extreme improvements in computational efficiency, even for massive datasets. We demonstrate the effectiveness of our approach using 5-year period estimates from the American Community Survey over all census tracts in California.

Zhenhua Wang, Guang Xu, Ming Ren

With the ascent of large language models (LLM), natural language processing has witnessed enhancements, such as LLM-based data augmentation. Nonetheless, prior research harbors two primary concerns: firstly, a lack of contemplation regarding whether the natural language generated by LLM (LLMNL) truly aligns with human natural language (HNL), a critical foundational question; secondly, an oversight that augmented data is randomly generated by LLM, implying that not all data may possess equal training value, that could impede the performance of classifiers. To address these challenges, we introduce the scaling laws to intrinsically calculate LLMNL and HNL. Through extensive experiments, we reveal slight deviations (approximately 0.2 Mandelbrot exponent) from Mandelbrot's law in LLMNL, underscore a complexity advantage in HNL, and supplement an interpretive discussion on language style. This establishes a solid foundation for LLM's expansion. Further, we introduce a novel data augmentation method for few-shot text classification, termed ZGPTDA, which leverages fuzzy computing mechanisms driven by the conformity to scaling laws to make decisions about GPT-4 augmented data. Extensive experiments, conducted in real-world scenarios, confirms the effectiveness (improving F1 of Bert and RoBerta by 7-10%) and competitiveness (surpassing recent AugGPT and GENCO methods by about 2% accuracy on DeBerta) of ZGPTDA. In addition, we reveal some interesting insights, e.g., Hilberg's law and Taylor's law can impart more benefits to text classification, etc.

Zhenhua Wang, Simin He, Guang Xu et al.

Nowadays, the omnipresence of the Internet has fostered a subculture that congregates around the contemporary milieu. The subculture artfully articulates the intricacies of human feelings by ardently pursuing the allure of novelty, a fact that cannot be disregarded in the sentiment analysis. This paper aims to enrich data through the lens of subculture, to address the insufficient training data faced by sentiment analysis. To this end, a new approach of subculture-based data augmentation (SCDA) is proposed, which engenders enhanced texts for each training text by leveraging the creation of specific subcultural expression generators. The extensive experiments attest to the effectiveness and potential of SCDA. The results also shed light on the phenomenon that disparate subcultural expressions elicit varying degrees of sentiment stimulation. Moreover, an intriguing conjecture arises, suggesting the linear reversibility of certain subcultural expressions.

Zhenhua Wang, Olanrewaju Akande, Jason Poulos et al.

Multiple imputation (MI) is a popular approach for dealing with missing data arising from non-response in sample surveys. Multiple imputation by chained equations (MICE) is one of the most widely used MI algorithms for multivariate data, but it lacks theoretical foundation and is computationally intensive. Recently, missing data imputation methods based on deep learning models have been developed with encouraging results in small studies. However, there has been limited research on evaluating their performance in realistic settings compared to MICE, particularly in big surveys. We conduct extensive simulation studies based on a subsample of the American Community Survey to compare the repeated sampling properties of four machine learning based MI methods: MICE with classification trees, MICE with random forests, generative adversarial imputation networks, and multiple imputation using denoising autoencoders. We find the deep learning imputation methods are superior to MICE in terms of computational time. However, with the default choice of hyperparameters in the common software packages, MICE with classification trees consistently outperforms, often by a large margin, the deep learning imputation methods in terms of bias, mean squared error, and coverage under a range of realistic settings.

Kaiqi Chen, Jialing Liu, Qinying Chen et al.

Current pandemic has caused the medical system to operate under high load. To relieve it, robots with high autonomy can be used to effectively execute contactless operations in hospitals and reduce cross-infection between medical staff and patients. Although semantic Simultaneous Localization and Mapping (SLAM) technology can improve the autonomy of robots, semantic object association is still a problem that is worthy of being studied. The key to solving this problem is to correctly associate multiple object measurements of one object landmark by using semantic information, and to refine the pose of object landmark in real time. To this end, we propose a hierarchical object association strategy and a pose-refinement approach. The former one consists of two levels, i.e., a short-term object association and a global one. In the first level, we employ the multiple-object-tracking for short-term object association, through which the incorrect association among objects whose locations are close and appearances are similar can be avoided. Moreover, the short-term object association can provide more abundant object appearance and more robust estimation of object pose for the global object association in the second level. To refine the object pose in the map, we develop an approach to choose the optimal object pose from all object measurements associated with an object landmark. The proposed method is comprehensively evaluated on seven simulated hospital sequences1, a real hospital environment and the KITTI dataset. Experimental results show that our method has an obviously improvement in terms of robustness and accuracy for the object association and the trajectory estimation in the semantic SLAM.

Zhenhua Wang, Jiajun Meng, Dongyan Guo et al.

Compared with the progress made on human activity classification, much less success has been achieved on human interaction understanding (HIU). Apart from the latter task is much more challenging, the main cause is that recent approaches learn human interactive relations via shallow graphical models, which is inadequate to model complicated human interactions. In this paper, we propose a consistency-aware graph network, which combines the representative ability of graph network and the consistency-aware reasoning to facilitate the HIU task. Our network consists of three components, a backbone CNN to extract image features, a factor graph network to learn third-order interactive relations among participants, and a consistency-aware reasoning module to enforce labeling and grouping consistencies. Our key observation is that the consistency-aware-reasoning bias for HIU can be embedded into an energy function, minimizing which delivers consistent predictions. An efficient mean-field inference algorithm is proposed, such that all modules of our network could be trained jointly in an end-to-end manner. Experimental results show that our approach achieves leading performance on three benchmarks.

Dongyan Guo, Jun Wang, Ying Cui et al.

By decomposing the visual tracking task into two subproblems as classification for pixel category and regression for object bounding box at this pixel, we propose a novel fully convolutional Siamese network to solve visual tracking end-to-end in a per-pixel manner. The proposed framework SiamCAR consists of two simple subnetworks: one Siamese subnetwork for feature extraction and one classification-regression subnetwork for bounding box prediction. Our framework takes ResNet-50 as backbone. Different from state-of-the-art trackers like Siamese-RPN, SiamRPN++ and SPM, which are based on region proposal, the proposed framework is both proposal and anchor free. Consequently, we are able to avoid the tricky hyper-parameter tuning of anchors and reduce human intervention. The proposed framework is simple, neat and effective. Extensive experiments and comparisons with state-of-the-art trackers are conducted on many challenging benchmarks like GOT-10K, LaSOT, UAV123 and OTB-50. Without bells and whistles, our SiamCAR achieves the leading performance with a considerable real-time speed.

Dongyan Guo, Jun Wang, Weixuan Zhao et al.

According to observations, different visual objects have different salient features in different scenarios. Even for the same object, its salient shape and appearance features may change greatly from time to time in a long-term tracking task. Motivated by them, we proposed an end-to-end feature fusion framework based on Siamese network, named FF-Siam, which can effectively fuse different features for adaptive visual tracking. The framework consists of four layers. A feature extraction layer is designed to extract the different features of the target region and search region. The extracted features are then put into a weight generation layer to obtain the channel weights, which indicate the importance of different feature channels. Both features and the channel weights are utilized in a template generation layer to generate a discriminative template. Finally, the corresponding response maps created by the convolution of the search region features and the template are applied with a fusion layer to obtain the final response map for locating the target. Experimental results demonstrate that the proposed framework achieves state-of-the-art performance on the popular Temple-Color, OTB50 and UAV123 benchmarks.

Jason Kuen, Zhenhua Wang, Gang Wang

Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional convolutional-deconvolution network (RACDNN). Using spatial transformer and recurrent network units, RACDNN is able to iteratively attend to selected image sub-regions to perform saliency refinement progressively. Besides tackling the scale problem, RACDNN can also learn context-aware features from past iterations to enhance saliency refinement in future iterations. Experiments on several challenging saliency detection datasets validate the effectiveness of RACDNN, and show that RACDNN outperforms state-of-the-art saliency detection methods.

Wenzheng Chen, Huan Wang, Yangyan Li et al.

Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance on the task of 2D pose estimation from a single image, by training on images with 2D annotations collected by crowd sourcing. This suggests that similar success could be achieved for direct estimation of 3D poses. However, 3D poses are much harder to annotate, and the lack of suitable annotated training images hinders attempts towards end-to-end solutions. To address this issue, we opt to automatically synthesize training images with ground truth pose annotations. Our work is a systematic study along this road. We find that pose space coverage and texture diversity are the key ingredients for the effectiveness of synthetic training data. We present a fully automatic, scalable approach that samples the human pose space for guiding the synthesis procedure and extracts clothing textures from real images. Furthermore, we explore domain adaptation for bridging the gap between our synthetic training images and real testing photos. We demonstrate that CNNs trained with our synthetic images out-perform those trained with real photos on 3D pose estimation tasks.

Qinfeng Shi, Mark Reid, Tiberio Caetano et al.

We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs). We provide a sufficient condition for when the hybrid loss is Fisher consistent for classification. This condition depends on a measure of dominance between labels--specifically, the gap between the probabilities of the best label and the second best label. We also prove Fisher consistency is necessary for parametric consistency when learning models such as CRFs. We demonstrate empirically that the hybrid loss typically performs least as well as--and often better than--both of its constituent losses on a variety of tasks, such as human action recognition. In doing so we also provide an empirical comparison of the efficacy of probabilistic and margin based approaches to multiclass and structured prediction.