Dong Wang

Zoey Guo, Yiwen Tang, Ray Zhang et al.

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality and fail to weigh the relative importance of different views. In this paper, we propose ViewRefer, a multi-view framework for 3D visual grounding exploring how to grasp the view knowledge from both text and 3D modalities. For the text branch, ViewRefer leverages the diverse linguistic knowledge of large-scale language models, e.g., GPT, to expand a single grounding text to multiple geometry-consistent descriptions. Meanwhile, in the 3D modality, a transformer fusion module with inter-view attention is introduced to boost the interaction of objects across views. On top of that, we further present a set of learnable multi-view prototypes, which memorize scene-agnostic knowledge for different views, and enhance the framework from two perspectives: a view-guided attention module for more robust text features, and a view-guided scoring strategy during the final prediction. With our designed paradigm, ViewRefer achieves superior performance on three benchmarks and surpasses the second-best by +2.8%, +1.5%, and +1.35% on Sr3D, Nr3D, and ScanRefer. Code is released at https://github.com/Ivan-Tang-3D/ViewRefer3D.

Xiaokang Peng, Yake Wei, Andong Deng et al.

Multimodal learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even when the multimodal model outperforms its uni-modal counterpart. Specifically, in this paper we point out that existing multimodal discriminative models, in which uniform objective is designed for all modalities, could remain under-optimized uni-modal representations, caused by another dominated modality in some scenarios, e.g., sound in blowing wind event, vision in drawing picture event, etc. To alleviate this optimization imbalance, we propose on-the-fly gradient modulation to adaptively control the optimization of each modality, via monitoring the discrepancy of their contribution towards the learning objective. Further, an extra Gaussian noise that changes dynamically is introduced to avoid possible generalization drop caused by gradient modulation. As a result, we achieve considerable improvement over common fusion methods on different multimodal tasks, and this simple strategy can also boost existing multimodal methods, which illustrates its efficacy and versatility. The source code is available at \url{https://github.com/GeWu-Lab/OGM-GE_CVPR2022}.

Dong Wang, Zhao Zhang, Ziwei Zhao et al.

This paper explores the point set representation for tubular structure extraction tasks. Compared with the traditional mask representation, the point set representation enjoys its flexibility and representation ability, which would not be restricted by the fixed grid as the mask. Inspired by this, we propose PointScatter, an alternative to the segmentation models for the tubular structure extraction task. PointScatter splits the image into scatter regions and parallelly predicts points for each scatter region. We further propose the greedy-based region-wise bipartite matching algorithm to train the network end-to-end and efficiently. We benchmark the PointScatter on four public tubular datasets, and the extensive experiments on tubular structure segmentation and centerline extraction task demonstrate the effectiveness of our approach. Code is available at https://github.com/zhangzhao2022/pointscatter.

Mingqi Yuan, Man-on Pun, Dong Wang

One of the most critical challenges in deep reinforcement learning is to maintain the long-term exploration capability of the agent. To tackle this problem, it has been recently proposed to provide intrinsic rewards for the agent to encourage exploration. However, most existing intrinsic reward-based methods proposed in the literature fail to provide sustainable exploration incentives, a problem known as vanishing rewards. In addition, these conventional methods incur complex models and additional memory in their learning procedures, resulting in high computational complexity and low robustness. In this work, a novel intrinsic reward module based on the Rényi entropy is proposed to provide high-quality intrinsic rewards. It is shown that the proposed method actually generalizes the existing state entropy maximization methods. In particular, a $k$-nearest neighbor estimator is introduced for entropy estimation while a $k$-value search method is designed to guarantee the estimation accuracy. Extensive simulation results demonstrate that the proposed Rényi entropy-based method can achieve higher performance as compared to existing schemes.

AnLan Sun, Zhao Zhang, Meng Lei et al. · pku

Breast ultrasound videos contain richer information than ultrasound images, therefore it is more meaningful to develop video models for this diagnosis task. However, the collection of ultrasound video datasets is much harder. In this paper, we explore the feasibility of enhancing the performance of ultrasound video classification using the static image dataset. To this end, we propose KGA-Net and coherence loss. The KGA-Net adopts both video clips and static images to train the network. The coherence loss uses the feature centers generated by the static images to guide the frame attention in the video model. Our KGA-Net boosts the performance on the public BUSV dataset by a large margin. The visualization results of frame attention prove the explainability of our method. The codes and model weights of our method will be made publicly available.

Ziwei Zhao, Dong Wang, Yihong Chen et al.

Detecting mass in mammogram is significant due to the high occurrence and mortality of breast cancer. In mammogram mass detection, modeling pairwise lesion correspondence explicitly is particularly important. However, most of the existing methods build relatively coarse correspondence and have not utilized correspondence supervision. In this paper, we propose a new transformer-based framework CL-Net to learn lesion detection and pairwise correspondence in an end-to-end manner. In CL-Net, View-Interactive Lesion Detector is proposed to achieve dynamic interaction across candidates of cross views, while Lesion Linker employs the correspondence supervision to guide the interaction process more accurately. The combination of these two designs accomplishes precise understanding of pairwise lesion correspondence for mammograms. Experiments show that CL-Net yields state-of-the-art performance on the public DDSM dataset and our in-house dataset. Moreover, it outperforms previous methods by a large margin in low FPI regime.

Dong Wang, Giovanni Beltrame

Traditional reinforcement learning (RL) methods typically employ a fixed control loop, where each cycle corresponds to an action. This rigidity poses challenges in practical applications, as the optimal control frequency is task-dependent. A suboptimal choice can lead to high computational demands and reduced exploration efficiency. Variable Time Step Reinforcement Learning (VTS-RL) addresses these issues by using adaptive frequencies for the control loop, executing actions only when necessary. This approach, rooted in reactive programming principles, reduces computational load and extends the action space by including action durations. However, VTS-RL's implementation is often complicated by the need to tune multiple hyperparameters that govern exploration in the multi-objective action-duration space (i.e., balancing task performance and number of time steps to achieve a goal). To overcome these challenges, we introduce the Multi-Objective Soft Elastic Actor-Critic (MOSEAC) method. This method features an adaptive reward scheme that adjusts hyperparameters based on observed trends in task rewards during training. This scheme reduces the complexity of hyperparameter tuning, requiring a single hyperparameter to guide exploration, thereby simplifying the learning process and lowering deployment costs. We validate the MOSEAC method through simulations in a Newtonian kinematics environment, demonstrating high task and training performance with fewer time steps, ultimately lowering energy consumption. This validation shows that MOSEAC streamlines RL algorithm deployment by automatically tuning the agent control loop frequency using a single parameter. Its principles can be applied to enhance any RL algorithm, making it a versatile solution for various applications.

Haoran He, Chenjia Bai, Kang Xu et al.

Diffusion models have demonstrated highly-expressive generative capabilities in vision and NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are also powerful in modeling complex policies or trajectories in offline datasets. However, these works have been limited to single-task settings where a generalist agent capable of addressing multi-task predicaments is absent. In this paper, we aim to investigate the effectiveness of a single diffusion model in modeling large-scale multi-task offline data, which can be challenging due to diverse and multimodal data distribution. Specifically, we propose Multi-Task Diffusion Model (\textsc{MTDiff}), a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis in multi-task offline settings. \textsc{MTDiff} leverages vast amounts of knowledge available in multi-task data and performs implicit knowledge sharing among tasks. For generative planning, we find \textsc{MTDiff} outperforms state-of-the-art algorithms across 50 tasks on Meta-World and 8 maps on Maze2D. For data synthesis, \textsc{MTDiff} generates high-quality data for testing tasks given a single demonstration as a prompt, which enhances the low-quality datasets for even unseen tasks.

Ying Shi, Dong Wang, Lantian Li et al.

Most existing keyword spotting research focuses on conditions with slight or moderate noise. In this paper, we try to tackle a more challenging task: detecting keywords buried under strong interfering speech (10 times higher than the keyword in amplitude), and even worse, mixed with other keywords. We propose a novel Mix Training (MT) strategy that encourages the model to discover low-energy keywords from noisy and mixed speech. Experiments were conducted with a vanilla CNN and two EfficientNet (B0/B2) architectures. The results evaluated with the Google Speech Command dataset demonstrated that the proposed mix training approach is highly effective and outperforms standard data augmentation and mixup training.

Mingqi Yuan, Mon-on Pun, Dong Wang et al.

Maintaining the long-term exploration capability of the agent remains one of the critical challenges in deep reinforcement learning. A representative solution is to leverage reward shaping to provide intrinsic rewards for the agent to encourage exploration. However, most existing methods suffer from vanishing intrinsic rewards, which cannot provide sustainable exploration incentives. Moreover, they rely heavily on complex models and additional memory to record learning procedures, resulting in high computational complexity and low robustness. To tackle this problem, entropy-based methods are proposed to evaluate the global exploration performance, encouraging the agent to visit the state space more equitably. However, the sample complexity of estimating the state visitation entropy is prohibitive when handling environments with high-dimensional observations. In this paper, we introduce a novel metric entitled Jain's fairness index (JFI) to replace the entropy regularizer, which solves the exploration problem from a brand new perspective. In sharp contrast to the entropy regularizer, JFI is more computable and robust and can be easily applied generalized into arbitrary tasks. Furthermore, we leverage a variational auto-encoder (VAE) model to capture the life-long novelty of states, which is combined with the global JFI score to form multimodal intrinsic rewards. Finally, extensive simulation results demonstrate that our multimodal reward shaping (MMRS) method can achieve higher performance than other benchmark schemes.

Dong Wang, Yuewei Yang, Chenyang Tao et al.

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance on exploiting non-causal visual cues that strongly correlate with the target label in training data. As such, deep neural nets suffer compromised generalization to novel inputs collected from different sources, and the reverse engineering of their decision rules offers limited interpretability. To overcome these limitations, we present a novel contrastive learning strategy called {\it Proactive Pseudo-Intervention} (PPI) that leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability. To demonstrate the utility of our proposals, we benchmark on both standard natural images and challenging medical image datasets. PPI-enhanced models consistently deliver superior performance relative to competing solutions, especially on out-of-domain predictions and data integration from heterogeneous sources. Further, our causally trained saliency maps are more succinct and meaningful relative to their non-causal counterparts.

Dong Wang, Xiaoqian Qin, Fengyi Song et al.

Generative adversarial networks (GANs), famous for the capability of learning complex underlying data distribution, are however known to be tricky in the training process, which would probably result in mode collapse or performance deterioration. Current approaches of dealing with GANs' issues almost utilize some practical training techniques for the purpose of regularization, which on the other hand undermines the convergence and theoretical soundness of GAN. In this paper, we propose to stabilize GAN training via a novel particle-based variational inference -- Langevin Stein variational gradient descent (LSVGD), which not only inherits the flexibility and efficiency of original SVGD but aims to address its instability issues by incorporating an extra disturbance into the update dynamics. We further demonstrate that by properly adjusting the noise variance, LSVGD simulates a Langevin process whose stationary distribution is exactly the target distribution. We also show that LSVGD dynamics has an implicit regularization which is able to enhance particles' spread-out and diversity. At last we present an efficient way of applying particle-based variational inference on a general GAN training procedure no matter what loss function is adopted. Experimental results on one synthetic dataset and three popular benchmark datasets -- Cifar-10, Tiny-ImageNet and CelebA validate that LSVGD can remarkably improve the performance and stability of various GAN models.

Dong Wang, Feng Zhou, Zheng Yan et al.

Considering the inherent stochasticity and uncertainty, predicting future video frames is exceptionally challenging. In this work, we study the problem of video prediction by combining interpretability of stochastic state space models and representation learning of deep neural networks. Our model builds upon an variational encoder which transforms the input video into a latent feature space and a Luenberger-type observer which captures the dynamic evolution of the latent features. This enables the decomposition of videos into static features and dynamics in an unsupervised manner. By deriving the stability theory of the nonlinear Luenberger-type observer, the hidden states in the feature space become insensitive with respect to the initial values, which improves the robustness of the overall model. Furthermore, the variational lower bound on the data log-likelihood can be derived to obtain the tractable posterior prediction distribution based on the variational principle. Finally, the experiments such as the Bouncing Balls dataset and the Pendulum dataset are provided to demonstrate the proposed model outperforms concurrent works.

Benlin Hu, Cheng Lei, Dong Wang et al.

Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is expensive in practice. Data augmentation is one of themethods to alleviate this problem. In this paper, we conduct apreliminary study on how three variables (augmentation method,augmentation rate and size of basic dataset per label) can affectthe accuracy of deep learning for image classification. The studyprovides some guidelines: (1) it is better to use transformationsthat alter the geometry of the images rather than those justlighting and color. (2) 2-3 times augmentation rate is good enoughfor training. (3) the smaller amount of data, the more obviouscontributions could have.

Dong Wang, Xiaoyang Tan

Learning a good distance metric in feature space potentially improves the performance of the KNN classifier and is useful in many real-world applications. Many metric learning algorithms are however based on the point estimation of a quadratic optimization problem, which is time-consuming, susceptible to overfitting, and lack a natural mechanism to reason with parameter uncertainty, an important property useful especially when the training set is small and/or noisy. To deal with these issues, we present a novel Bayesian metric learning method, called Bayesian NCA, based on the well-known Neighbourhood Component Analysis method, in which the metric posterior is characterized by the local label consistency constraints of observations, encoded with a similarity graph instead of independent pairwise constraints. For efficient Bayesian optimization, we explore the variational lower bound over the log-likelihood of the original NCA objective. Experiments on several publicly available datasets demonstrate that the proposed method is able to learn robust metric measures from small size dataset and/or from challenging training set with labels contaminated by errors. The proposed method is also shown to outperform a previous pairwise constrained Bayesian metric learning method.

Lantian Li, Dong Wang, Chao Xing et al.

The popular i-vector model represents speakers as low-dimensional continuous vectors (i-vectors), and hence it is a way of continuous speaker embedding. In this paper, we investigate binary speaker embedding, which transforms i-vectors to binary vectors (codes) by a hash function. We start from locality sensitive hashing (LSH), a simple binarization approach where binary codes are derived from a set of random hash functions. A potential problem of LSH is that the randomly sampled hash functions might be suboptimal. We therefore propose an improved Hamming distance learning approach, where the hash function is learned by a variable-sized block training that projects each dimension of the original i-vectors to variable-sized binary codes independently. Our experiments show that binary speaker embedding can deliver competitive or even better results on both speaker verification and identification tasks, while the memory usage and the computation cost are significantly reduced.

Dong Wang, Xiaoyang Tan

In this paper, we investigate the problem of learning feature representation from unlabeled data using a single-layer K-means network. A K-means network maps the input data into a feature representation by finding the nearest centroid for each input point, which has attracted researchers' great attention recently due to its simplicity, effectiveness, and scalability. However, one drawback of this feature mapping is that it tends to be unreliable when the training data contains noise. To address this issue, we propose a SVDD based feature learning algorithm that describes the density and distribution of each cluster from K-means with an SVDD ball for more robust feature representation. For this purpose, we present a new SVDD algorithm called C-SVDD that centers the SVDD ball towards the mode of local density of each cluster, and we show that the objective of C-SVDD can be solved very efficiently as a linear programming problem. Additionally, traditional unsupervised feature learning methods usually take an average or sum of local representations to obtain global representation which ignore spatial relationship among them. To use spatial information we propose a global representation with a variant of SIFT descriptor. The architecture is also extended with multiple receptive field scales and multiple pooling sizes. Extensive experiments on several popular object recognition benchmarks, such as STL-10, MINST, Holiday and Copydays shows that the proposed C-SVDDNet method yields comparable or better performance than that of the previous state of the art methods.