Tao Zhang

Tao Zhang, Shiqing Wei, Shunping Ji

Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of hand-crafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512*512 images on an NVIDIA A6000 GPU. Code will be released at https://github.com/zhang-tao-whu/e2ec.

Tao Zhang, Xingye Tian, Yu Wu et al.

Video instance segmentation (VIS) is a critical task with diverse applications, including autonomous driving and video editing. Existing methods often underperform on complex and long videos in real world, primarily due to two factors. Firstly, offline methods are limited by the tightly-coupled modeling paradigm, which treats all frames equally and disregards the interdependencies between adjacent frames. Consequently, this leads to the introduction of excessive noise during long-term temporal alignment. Secondly, online methods suffer from inadequate utilization of temporal information. To tackle these challenges, we propose a decoupling strategy for VIS by dividing it into three independent sub-tasks: segmentation, tracking, and refinement. The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement. We introduce a novel referring tracker and temporal refiner to construct the \textbf{D}ecoupled \textbf{VIS} framework (\textbf{DVIS}). DVIS achieves new SOTA performance in both VIS and VPS, surpassing the current SOTA methods by 7.3 AP and 9.6 VPQ on the OVIS and VIPSeg datasets, which are the most challenging and realistic benchmarks. Moreover, thanks to the decoupling strategy, the referring tracker and temporal refiner are super light-weight (only 1.69\% of the segmenter FLOPs), allowing for efficient training and inference on a single GPU with 11G memory. The code is available at \href{https://github.com/zhang-tao-whu/DVIS}{https://github.com/zhang-tao-whu/DVIS}.

Tao Zhang, Xingye Tian, Haoran Wei et al.

Video panoptic segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. We believe that the decoupling strategy proposed by DVIS enables more effective utilization of temporal information for both "thing" and "stuff" objects. In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation. Finally, our method achieved a VPQ score of 51.4 and 53.7 in the development and test phases, respectively, and ultimately ranked 1st in the VPS track of the 2nd PVUW Challenge. The code is available at https://github.com/zhang-tao-whu/DVIS

Jilan Xu, Junlin Hou, Yuejie Zhang et al.

Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to boost the activation values of the integral object regions. To this end, we introduce class-specific foreground and background context embeddings as cluster centroids. A CAM-guided momentum preservation strategy is developed to learn the context embeddings during training. At the inference stage, the re-activation mapping is formulated as a parameter estimation problem under Gaussian Mixture Model, which can be solved by deriving an unsupervised Expectation-Maximization based soft-clustering algorithm. By simply integrating CREAM into various WSOL approaches, our method significantly improves their performance. CREAM achieves the state-of-the-art performance on CUB, ILSVRC and OpenImages benchmark datasets. Code will be available at https://github.com/Jazzcharles/CREAM.

Ye Wang, Xinxin Liu, Wenxin Hu et al.

Document-level relation extraction (RE) aims to identify relations between entities across multiple sentences. Most previous methods focused on document-level RE under full supervision. However, in real-world scenario, it is expensive and difficult to completely label all relations in a document because the number of entity pairs in document-level RE grows quadratically with the number of entities. To solve the common incomplete labeling problem, we propose a unified positive-unlabeled learning framework - shift and squared ranking loss positive-unlabeled (SSR-PU) learning. We use positive-unlabeled (PU) learning on document-level RE for the first time. Considering that labeled data of a dataset may lead to prior shift of unlabeled data, we introduce a PU learning under prior shift of training data. Also, using none-class score as an adaptive threshold, we propose squared ranking loss and prove its Bayesian consistency with multi-label ranking metrics. Extensive experiments demonstrate that our method achieves an improvement of about 14 F1 points relative to the previous baseline with incomplete labeling. In addition, it outperforms previous state-of-the-art results under both fully supervised and extremely unlabeled settings as well.

Long Wei, Haodong Feng, Yuchen Yang et al.

The control problems of complex physical systems have broad applications in science and engineering. Previous studies have shown that generative control methods based on diffusion models offer significant advantages for solving these problems. However, existing generative control approaches face challenges in both performance and efficiency when extended to the closed-loop setting, which is essential for effective control. In this paper, we propose an efficient Closed-Loop Diffusion method for Physical systems Control (CL-DiffPhyCon). By employing an asynchronous denoising framework for different physical time steps, CL-DiffPhyCon generates control signals conditioned on real-time feedback from the system with significantly reduced computational cost during sampling. Additionally, the control process could be further accelerated by incorporating fast sampling techniques, such as DDIM. We evaluate CL-DiffPhyCon on two tasks: 1D Burgers' equation control and 2D incompressible fluid control. The results demonstrate that CL-DiffPhyCon achieves superior control performance with significant improvements in sampling efficiency. The code can be found at https://github.com/AI4Science-WestlakeU/CL_DiffPhyCon.

Ye Wang, Huazheng Pan, Tao Zhang et al.

The goal of document-level relation extraction (RE) is to identify relations between entities that span multiple sentences. Recently, incomplete labeling in document-level RE has received increasing attention, and some studies have used methods such as positive-unlabeled learning to tackle this issue, but there is still a lot of room for improvement. Motivated by this, we propose a positive-augmentation and positive-mixup positive-unlabeled metric learning framework (P3M). Specifically, we formulate document-level RE as a metric learning problem. We aim to pull the distance closer between entity pair embedding and their corresponding relation embedding, while pushing it farther away from the none-class relation embedding. Additionally, we adapt the positive-unlabeled learning to this loss objective. In order to improve the generalizability of the model, we use dropout to augment positive samples and propose a positive-none-class mixup method. Extensive experiments show that P3M improves the F1 score by approximately 4-10 points in document-level RE with incomplete labeling, and achieves state-of-the-art results in fully labeled scenarios. Furthermore, P3M has also demonstrated robustness to prior estimation bias in incomplete labeled scenarios.

Jinhao Jiang, Junyi Li, Wayne Xin Zhao et al.

Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate knowledge memorization, followed by training to apply this knowledge following human instructions and preferences. However, this method may result in inefficient knowledge memorization due to a lack of awareness of knowledge utilization and imposes substantial demands on LLMs to simultaneously learn knowledge utilization and format alignment with limited training samples. To facilitate the domain adaptation of LLM, we revise this process and propose a new domain adaptation framework including domain knowledge learning and general format alignment, called Mix-CPT. Specifically, we first conduct a knowledge mixture continual pre-training that concurrently focuses on knowledge memorization and utilization, allowing for mutual reinforcement. To avoid catastrophic forgetting during the continual pre-training process, we further incorporate a logit swap self-distillation constraint. Subsequently, leveraging the knowledge and capabilities acquired during continual pre-training, we efficiently perform instruction tuning and alignment with a few general training samples to achieve format alignment. Extensive experiments demonstrate that our proposed Mix-CPT framework can simultaneously improve the task-solving capabilities of LLMs on the target and general domains compared to the traditional adaptation methods.

Haotian Xu, Shengjie Wang, Zhaolei Wang et al.

Reinforcement learning (RL) has achieved promising results on most robotic control tasks. Safety of learning-based controllers is an essential notion of ensuring the effectiveness of the controllers. Current methods adopt whole consistency constraints during the training, thus resulting in inefficient exploration in the early stage. In this paper, we propose an algorithm named Constrained Policy Optimization with Extra Safety Budget (ESB-CPO) to strike a balance between the exploration efficiency and the constraints satisfaction. In the early stage, our method loosens the practical constraints of unsafe transitions (adding extra safety budget) with the aid of a new metric we propose. With the training process, the constraints in our optimization problem become tighter. Meanwhile, theoretical analysis and practical experiments demonstrate that our method gradually meets the cost limit's demand in the final training stage. When evaluated on Safety-Gym and Bullet-Safety-Gym benchmarks, our method has shown its advantages over baseline algorithms in terms of safety and optimality. Remarkably, our method gains remarkable performance improvement under the same cost limit compared with baselines.

Shengjie Wang, Yuxue Cao, Xiang Zheng et al.

Recent years have seen the emergence of non-cooperative objects in space, like failed satellites and space junk. These objects are usually operated or collected by free-float dual-arm space manipulators. Thanks to eliminating the difficulties of modeling and manual parameter-tuning, reinforcement learning (RL) methods have shown a more promising sign in the trajectory planning of space manipulators. Although previous studies demonstrate their effectiveness, they cannot be applied in tracking dynamic targets with unknown rotation (non-cooperative objects). In this paper, we proposed a learning system for motion planning of free-float dual-arm space manipulator (FFDASM) towards non-cooperative objects. Specifically, our method consists of two modules. Module I realizes the multi-target trajectory planning for two end-effectors within a large target space. Next, Module II takes as input the point clouds of the non-cooperative object to estimate the motional property, and then can predict the position of target points on an non-cooperative object. We leveraged the combination of Module I and Module II to track target points on a spinning object with unknown regularity successfully. Furthermore, the experiments also demonstrate the scalability and generalization of our learning system.

Xue Xia, Randall Balestriero, Tao Zhang et al.

Historical maps are unique and valuable archives that document geographic features across different time periods. However, automated analysis of historical map images remains a significant challenge due to their wide stylistic variability and the scarcity of annotated training data. Constructing linked spatio-temporal datasets from historical map time series is even more time-consuming and labor-intensive, as it requires synthesizing information from multiple maps. Such datasets are essential for applications such as dating buildings, analyzing the development of road networks and settlements, studying environmental changes etc. We present MapSAM2, a unified framework for automatically segmenting both historical map images and time series. Built on a visual foundation model, MapSAM2 adapts to diverse segmentation tasks with few-shot fine-tuning. Our key innovation is to treat both historical map images and time series as videos. For images, we process a set of tiles as a video, enabling the memory attention mechanism to incorporate contextual cues from similar tiles, leading to improved geometric accuracy, particularly for areal features. For time series, we introduce the annotated Siegfried Building Time Series Dataset and, to reduce annotation costs, propose generating pseudo time series from single-year maps by simulating common temporal transformations. Experimental results show that MapSAM2 learns temporal associations effectively and can accurately segment and link buildings in time series under limited supervision or using pseudo videos. We will release both our dataset and code to support future research.

Fengbo Lan, Shengjie Wang, Yunzhe Zhang et al.

Achieving human-like dexterous manipulation remains a crucial area of research in robotics. Current research focuses on improving the success rate of pick-and-place tasks. Compared with pick-and-place, throwing-catching behavior has the potential to increase the speed of transporting objects to their destination. However, dynamic dexterous manipulation poses a major challenge for stable control due to a large number of dynamic contacts. In this paper, we propose a Learning-based framework for Throwing-Catching tasks using dexterous hands (LTC). Our method, LTC, achieves a 73\% success rate across 45 scenarios (diverse hand poses and objects), and the learned policies demonstrate strong zero-shot transfer performance on unseen objects. Additionally, in tasks where the object in hand faces sideways, an extremely unstable scenario due to the lack of support from the palm, all baselines fail, while our method still achieves a success rate of over 60\%.

Yikang Zhou, Tao Zhang, Shunping Ji et al.

Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient occlusion. However, they all underperform on newly emerging and disappearing objects that are common in the real world because they attempt to model object emergence and disappearance through feature transitions between background and foreground queries that have significant feature gaps. We introduce Dynamic Anchor Queries (DAQ) to shorten the transition gap between the anchor and target queries by dynamically generating anchor queries based on the features of potential candidates. Furthermore, we introduce a query-level object Emergence and Disappearance Simulation (EDS) strategy, which unleashes DAQ's potential without any additional cost. Finally, we combine our proposed DAQ and EDS with DVIS to obtain DVIS-DAQ. Extensive experiments demonstrate that DVIS-DAQ achieves a new state-of-the-art (SOTA) performance on five mainstream video segmentation benchmarks. Code and models are available at \url{https://github.com/SkyworkAI/DAQ-VS}.

Shengjie Wang, Fengbo Lan, Xiang Zheng et al.

In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization. However, these criteria only guarantee the infinite-time convergence of the system's state to an equilibrium point, which leads to sub-optimality of the policy. In this paper, we propose a policy optimization technique incorporating sampling-based Lyapunov stability. Our approach enables the system's state to reach an equilibrium point within an optimal time and maintain stability thereafter, referred to as "optimal-time stability". To achieve this, we integrate the optimization method into the Actor-Critic framework, resulting in the development of the Adaptive Lyapunov-based Actor-Critic (ALAC) algorithm. Through evaluations conducted on ten robotic tasks, our approach outperforms previous studies significantly, effectively guiding the system to generate stable patterns.

Peiyan Hu, Rui Wang, Xiang Zheng et al.

Simulating and controlling physical systems described by partial differential equations (PDEs) are crucial tasks across science and engineering. Recently, diffusion generative models have emerged as a competitive class of methods for these tasks due to their ability to capture long-term dependencies and model high-dimensional states. However, diffusion models typically struggle with handling system states with abrupt changes and generalizing to higher resolutions. In this work, we propose Wavelet Diffusion Neural Operator (WDNO), a novel PDE simulation and control framework that enhances the handling of these complexities. WDNO comprises two key innovations. Firstly, WDNO performs diffusion-based generative modeling in the wavelet domain for the entire trajectory to handle abrupt changes and long-term dependencies effectively. Secondly, to address the issue of poor generalization across different resolutions, which is one of the fundamental tasks in modeling physical systems, we introduce multi-resolution training. We validate WDNO on five physical systems, including 1D advection equation, three challenging physical systems with abrupt changes (1D Burgers' equation, 1D compressible Navier-Stokes equation and 2D incompressible fluid), and a real-world dataset ERA5, which demonstrates superior performance on both simulation and control tasks over state-of-the-art methods, with significant improvements in long-term and detail prediction accuracy. Remarkably, in the challenging context of the 2D high-dimensional and indirect control task aimed at reducing smoke leakage, WDNO reduces the leakage by 78% compared to the second-best baseline. The code can be found at https://github.com/AI4Science-WestlakeU/wdno.git.

Hesong Li, Ziqi Wu, Ruiwen Shao et al.

Scanning Transmission Electron Microscopy (STEM) enables the observation of atomic arrangements at sub-angstrom resolution, allowing for atomically resolved analysis of the physical and chemical properties of materials. However, due to the effects of noise, electron beam damage, sample thickness, etc, obtaining satisfactory atomic-level images is often challenging. Enhancing STEM images can reveal clearer structural details of materials. Nonetheless, existing STEM image enhancement methods usually overlook unique features in the frequency domain, and existing datasets lack realism and generality. To resolve these issues, in this paper, we develop noise calibration, data synthesis, and enhancement methods for STEM images. We first present a STEM noise calibration method, which is used to synthesize more realistic STEM images. The parameters of background noise, scan noise, and pointwise noise are obtained by statistical analysis and fitting of real STEM images containing atoms. Then we use these parameters to develop a more general dataset that considers both regular and random atomic arrangements and includes both HAADF and BF mode images. Finally, we design a spatial-frequency interactive network for STEM image enhancement, which can explore the information in the frequency domain formed by the periodicity of atomic arrangement. Experimental results show that our data is closer to real STEM images and achieves better enhancement performances together with our network. Code will be available at https://github.com/HeasonLee/SFIN}{https://github.com/HeasonLee/SFIN.

Yuxue Cao, Wenbo Zhao, Shengjie Wang et al.

Symmetric bi-manual manipulation is an essential skill in on-orbit operations due to its potent load capacity. Previous works have applied compliant control to maintain the stability of manipulations. However, traditional methods have viewed motion planning and compliant control as two separate modules, which can lead to conflicts with the simultaneous change of the desired trajectory and impedance parameters in the presence of external forces and disturbances. Additionally, the joint usage of these two modules requires experts to manually adjust parameters. To achieve high efficiency while enhancing adaptability, we propose a novel Learning-based Adaptive Compliance algorithm (LAC) that improves the efficiency and robustness of symmetric bi-manual manipulation. Specifically, the algorithm framework integrates desired trajectory generation and impedance-parameter adjustment under a unified framework to mitigate contradictions and improve efficiency. Second, we introduce a centralized Actor-Critic framework with LSTM networks preprocessing the force states, enhancing the synchronization of bi-manual manipulation. When evaluated in dual-arm peg-in-hole assembly experiments, our method outperforms baseline algorithms in terms of optimality and robustness.

Yuanbo Fang, Haoze Sun, Jun Liu et al.

End-to-end speech large language models ((LLMs)) extend the capabilities of text-based models to directly process and generate audio tokens. However, this often leads to a decline in reasoning and generation performance compared to text input, a phenomenon referred to as intelligence degradation. To systematically evaluate this gap, we propose S2SBench, a benchmark designed to quantify performance degradation in Speech LLMs. It includes diagnostic datasets targeting sentence continuation and commonsense reasoning under audio input. We further introduce a pairwise evaluation protocol based on perplexity differences between plausible and implausible samples to measure degradation relative to text input. We apply S2SBench to analyze the training process of Baichuan-Audio, which further demonstrates the benchmark's effectiveness. All datasets and evaluation code are available at https://github.com/undobug/S2SBench.

Peiyan Hu, Xiaowei Qian, Wenhao Deng et al.

The application of deep learning for partial differential equation (PDE)-constrained control is gaining increasing attention. However, existing methods rarely consider safety requirements crucial in real-world applications. To address this limitation, we propose Safe Diffusion Models for PDE Control (SafeDiffCon), which introduce the uncertainty quantile as model uncertainty quantification to achieve optimal control under safety constraints through both post-training and inference phases. Firstly, our approach post-trains a pre-trained diffusion model to generate control sequences that better satisfy safety constraints while achieving improved control objectives via a reweighted diffusion loss, which incorporates the uncertainty quantile estimated using conformal prediction. Secondly, during inference, the diffusion model dynamically adjusts both its generation process and parameters through iterative guidance and fine-tuning, conditioned on control targets while simultaneously integrating the estimated uncertainty quantile. We evaluate SafeDiffCon on three control tasks: 1D Burgers' equation, 2D incompressible fluid, and controlled nuclear fusion problem. Results demonstrate that SafeDiffCon is the only method that satisfies all safety constraints, whereas other classical and deep learning baselines fail. Furthermore, while adhering to safety constraints, SafeDiffCon achieves the best control performance. The code can be found at https://github.com/AI4Science-WestlakeU/safediffcon.

Tao Zhang

Different from most state-of-the-art~(SOTA) algorithms that use static and uniform sampling methods with a lot of hypothesis planes to get fine depth sampling. In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume. We present the SuperMVS network to implement Multi-View Stereo with Non-Uniform Cost Volume. SuperMVS is a coarse-to-fine framework with four cascade stages. It can output higher resolution and accurate depth map. Our SuperMVS achieves the SOTA results with low memory, low runtime, and fewer planes on the DTU datasets and Tanks \& Temples dataset.

Hao Fei, Yuan Zhou, Juncheng Li et al.

The Multimodal Large Language Model (MLLM) is currently experiencing rapid growth, driven by the advanced capabilities of LLMs. Unlike earlier specialists, existing MLLMs are evolving towards a Multimodal Generalist paradigm. Initially limited to understanding multiple modalities, these models have advanced to not only comprehend but also generate across modalities. Their capabilities have expanded from coarse-grained to fine-grained multimodal understanding and from supporting limited modalities to arbitrary ones. While many benchmarks exist to assess MLLMs, a critical question arises: Can we simply assume that higher performance across tasks indicates a stronger MLLM capability, bringing us closer to human-level AI? We argue that the answer is not as straightforward as it seems. This project introduces General-Level, an evaluation framework that defines 5-scale levels of MLLM performance and generality, offering a methodology to compare MLLMs and gauge the progress of existing systems towards more robust multimodal generalists and, ultimately, towards AGI. At the core of the framework is the concept of Synergy, which measures whether models maintain consistent capabilities across comprehension and generation, and across multiple modalities. To support this evaluation, we present General-Bench, which encompasses a broader spectrum of skills, modalities, formats, and capabilities, including over 700 tasks and 325,800 instances. The evaluation results that involve over 100 existing state-of-the-art MLLMs uncover the capability rankings of generalists, highlighting the challenges in reaching genuine AI. We expect this project to pave the way for future research on next-generation multimodal foundation models, providing a robust infrastructure to accelerate the realization of AGI. Project page: https://generalist.top/

Zhibo Xiao, Luwei Yang, Tao Zhang et al.

The recommendation has been playing a key role in many industries, e.g., e-commerce, streaming media, social media, etc. Recently, a new recommendation scenario, called Trigger-Induced Recommendation (TIR), where users are able to explicitly express their instant interests via trigger items, is emerging as an essential role in many e-commerce platforms, e.g., Alibaba.com and Amazon. Without explicitly modeling the user's instant interest, traditional recommendation methods usually obtain sub-optimal results in TIR. Even though there are a few methods considering the trigger and target items simultaneously to solve this problem, they still haven't taken into account temporal information of user behaviors, the dynamic change of user instant interest when the user scrolls down and the interactions between the trigger and target items. To tackle these problems, we propose a novel method -- Deep Evolutional Instant Interest Network (DEI2N), for click-through rate prediction in TIR scenarios. Specifically, we design a User Instant Interest Modeling Layer to predict the dynamic change of the intensity of instant interest when the user scrolls down. Temporal information is utilized in user behavior modeling. Moreover, an Interaction Layer is introduced to learn better interactions between the trigger and target items. We evaluate our method on several offline and real-world industrial datasets. Experimental results show that our proposed DEI2N outperforms state-of-the-art baselines. In addition, online A/B testing demonstrates the superiority over the existing baseline in real-world production environments.

Bowen Deng, Tong Wang, Lele Fu et al.

Graph node clustering is a fundamental unsupervised task. Existing methods typically train an encoder through selfsupervised learning and then apply K-means to the encoder output. Some methods use this clustering result directly as the final assignment, while others initialize centroids based on this initial clustering and then finetune both the encoder and these learnable centroids. However, due to their reliance on K-means, these methods inherit its drawbacks when the cluster separability of encoder output is low, facing challenges from the Uniform Effect and Cluster Assimilation. We summarize three reasons for the low cluster separability in existing methods: (1) lack of contextual information prevents discrimination between similar nodes from different clusters; (2) training tasks are not sufficiently aligned with the downstream clustering task; (3) the cluster information in the graph structure is not appropriately exploited. To address these issues, we propose conTrastive grapH clustEring by SwApping fUsed gRomov-wasserstein coUplingS (THESAURUS). Our method introduces semantic prototypes to provide contextual information, and employs a cross-view assignment prediction pretext task that aligns well with the downstream clustering task. Additionally, it utilizes Gromov-Wasserstein Optimal Transport (GW-OT) along with the proposed prototype graph to thoroughly exploit cluster information in the graph structure. To adapt to diverse real-world data, THESAURUS updates the prototype graph and the prototype marginal distribution in OT by using momentum. Extensive experiments demonstrate that THESAURUS achieves higher cluster separability than the prior art, effectively mitigating the Uniform Effect and Cluster Assimilation issues

Jie Han, Yixiong Zou, Haozhao Wang et al.

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.

Xue Xia, Randall Balestriero, Tao Zhang et al.

Tracking geographic entities from historical maps, such as buildings, offers valuable insights into cultural heritage, urbanization patterns, environmental changes, and various historical research endeavors. However, linking these entities across diverse maps remains a persistent challenge for researchers. Traditionally, this has been addressed through a two-step process: detecting entities within individual maps and then associating them via a heuristic-based post-processing step. In this paper, we propose a novel approach that combines segmentation and association of geographic entities in historical maps using video instance segmentation (VIS). This method significantly streamlines geographic entity alignment and enhances automation. However, acquiring high-quality, video-format training data for VIS models is prohibitively expensive, especially for historical maps that often contain hundreds or thousands of geographic entities. To mitigate this challenge, we explore self-supervised learning (SSL) techniques to enhance VIS performance on historical maps. We evaluate the performance of VIS models under different pretraining configurations and introduce a novel method for generating synthetic videos from unlabeled historical map images for pretraining. Our proposed self-supervised VIS method substantially reduces the need for manual annotation. Experimental results demonstrate the superiority of the proposed self-supervised VIS approach, achieving a 24.9\% improvement in AP and a 0.23 increase in F1 score compared to the model trained from scratch.

Tao Zhang, Wu Huang

Prototype is widely used to represent internal structure of category for few-shot learning, which was proposed as a simple inductive bias to address the issue of overfitting. However, since prototype representation is normally averaged from individual samples, it can appropriately to represent some classes but with underfitting to represent some others that can be batter represented by exemplars. To address this problem, in this work, we propose Shrinkage Exemplar Networks (SENet) for few-shot classification. In SENet, categories are represented by the embedding of samples that shrink towards their mean via spectral filtering. Furthermore, a shrinkage exemplar loss is proposed to replace the widely used cross entropy loss for capturing the information of individual shrinkage samples. Several experiments were conducted on miniImageNet, tiered-ImageNet and CIFAR-FS datasets. The experimental results demonstrate the effectiveness of our proposed method.

Zongbo Hao, Tao Zhang, Mingwang Chen et al.

Convolutional Neural Networks (CNNs) perform very well in image classification and object detection in recent years, but even the most advanced models have limited rotation invariance. Known solutions include the enhancement of training data and the increase of rotation invariance by globally merging the rotation equivariant features. These methods either increase the workload of training or increase the number of model parameters. To address this problem, this paper proposes a module that can be inserted into the existing networks, and directly incorporates the rotation invariance into the feature extraction layers of the CNNs. This module does not have learnable parameters and will not increase the complexity of the model. At the same time, only by training the upright data, it can perform well on the rotated testing set. These advantages will be suitable for fields such as biomedicine and astronomy where it is difficult to obtain upright samples or the target has no directionality. Evaluate our module with LeNet-5, ResNet-18 and tiny-yolov3, we get impressive results.

Mengting Xu, Tao Zhang, Zhongnian Li et al.

Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks. However, the effect of the standard PGD attack can be easily weakened by rescaling the logits, while the original decision of every input will not be changed. To mitigate this issue, in this paper, we propose Scale-Invariant Adversarial Attack (SI-PGD), which utilizes the angle between the features in the penultimate layer and the weights in the softmax layer to guide the generation of adversaries. The cosine angle matrix is used to learn angularly discriminative representation and will not be changed with the rescaling of logits, thus making SI-PGD attack to be stable and effective. We evaluate our attack against multiple defenses and show improved performance when compared with existing attacks. Further, we propose Scale-Invariant (SI) adversarial defense mechanism based on the cosine angle matrix, which can be embedded into the popular adversarial defenses. The experimental results show the defense method with our SI mechanism achieves state-of-the-art performance among multi-step and single-step defenses.

Mengting Xu, Tao Zhang, Daoqiang Zhang

Deep neural networks are discovered to be non-robust when attacked by imperceptible adversarial examples, which is dangerous for it applied into medical diagnostic system that requires high reliability. However, the defense methods that have good effect in natural images may not be suitable for medical diagnostic tasks. The preprocessing methods (e.g., random resizing, compression) may lead to the loss of the small lesions feature in the medical image. Retraining the network on the augmented data set is also not practical for medical models that have already been deployed online. Accordingly, it is necessary to design an easy-to-deploy and effective defense framework for medical diagnostic tasks. In this paper, we propose a Robust and Retrain-Less Diagnostic Framework for Medical pretrained models against adversarial attack (i.e., MedRDF). It acts on the inference time of the pertained medical model. Specifically, for each test image, MedRDF firstly creates a large number of noisy copies of it, and obtains the output labels of these copies from the pretrained medical diagnostic model. Then, based on the labels of these copies, MedRDF outputs the final robust diagnostic result by majority voting. In addition to the diagnostic result, MedRDF produces the Robust Metric (RM) as the confidence of the result. Therefore, it is convenient and reliable to utilize MedRDF to convert pre-trained non-robust diagnostic models into robust ones. The experimental results on COVID-19 and DermaMNIST datasets verify the effectiveness of our MedRDF in improving the robustness of medical diagnostic models.

Li Wang, Tao Zhang, Lin Ye et al.

This paper presents an efficient servomotor-aided calibration method for the triaxial gyroscope. The entire calibration process only requires approximately one minute, and does not require high-precision equipment. This method is based on the idea that the measurement of the gyroscope should be equal to the rotation speed of the servomotor. A six-observation experimental design is proposed to minimize the maximum variance of the estimated scale factors and biases. In addition, a fast converging recursive linear least square estimation method is presented to reduce computational complexity. The simulation results reflect the robustness of the calibration method under normal and extreme conditions. We experimentally demonstrate the feasibility of the proposed method on a robot arm, and implement the method on a microcontroller. We verify the calibration results of the proposed method by comparing with a traditional turntable approach, and the experiment indicates that the results of these two methods are comparable. By comparing the calibrated low-cost gyroscope reading with the reading from a high-precision gyroscope, we can conclude that our method significantly increases the gyroscope's accuracy.

Shuqing Bian, Xu Chen, Wayne Xin Zhao et al.

With the ever-increasing growth of online recruitment data, job-resume matching has become an important task to automatically match jobs with suitable resumes. This task is typically casted as a supervised text matching problem. Supervised learning is powerful when the labeled data is sufficient. However, on online recruitment platforms, job-resume interaction data is sparse and noisy, which affects the performance of job-resume match algorithms. To alleviate these problems, in this paper, we propose a novel multi-view co-teaching network from sparse interaction data for job-resume matching. Our network consists of two major components, namely text-based matching model and relation-based matching model. The two parts capture semantic compatibility in two different views, and complement each other. In order to address the challenges from sparse and noisy data, we design two specific strategies to combine the two components. First, two components share the learned parameters or representations, so that the original representations of each component can be enhanced. More importantly, we adopt a co-teaching mechanism to reduce the influence of noise in training data. The core idea is to let the two components help each other by selecting more reliable training instances. The two strategies focus on representation enhancement and data enhancement, respectively. Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data. Experiment results have demonstrated that our model is able to outperform state-of-the-art methods for job-resume matching.

Haoyin Zhou, Tao Zhang, Jagadeesan Jayender

The ability to handle outliers is essential for performing the perspective-n-point (PnP) approach in practical applications, but conventional RANSAC+P3P or P4P methods have high time complexities. We propose a fast PnP solution named R1PPnP to handle outliers by utilizing a soft re-weighting mechanism and the 1-point RANSAC scheme. We first present a PnP algorithm, which serves as the core of R1PPnP, for solving the PnP problem in outlier-free situations. The core algorithm is an optimal process minimizing an objective function conducted with a random control point. Then, to reduce the impact of outliers, we propose a reprojection error-based re-weighting method and integrate it into the core algorithm. Finally, we employ the 1-point RANSAC scheme to try different control points. Experiments with synthetic and real-world data demonstrate that R1PPnP is faster than RANSAC+P3P or P4P methods especially when the percentage of outliers is large, and is accurate. Besides, comparisons with outlier-free synthetic data show that R1PPnP is among the most accurate and fast PnP solutions, which usually serve as the final refinement step of RANSAC+P3P or P4P. Compared with REPPnP, which is the state-of-the-art PnP algorithm with an explicit outliers-handling mechanism, R1PPnP is slower but does not suffer from the percentage of outliers limitation as REPPnP.

Jiahua Dong, Yang Cong, Gan Sun et al.

Online metric learning has been widely exploited for large-scale data classification due to the low computational cost. However, amongst online practical scenarios where the features are evolving (e.g., some features are vanished and some new features are augmented), most metric learning models cannot be successfully applied to these scenarios, although they can tackle the evolving instances efficiently. To address the challenge, we develop a new online Evolving Metric Learning (EML) model for incremental and decremental features, which can handle the instance and feature evolutions simultaneously by incorporating with a smoothed Wasserstein metric distance. Specifically, our model contains two essential stages: a Transforming stage (T-stage) and a Inheriting stage (I-stage). For the T-stage, we propose to extract important information from vanished features while neglecting non-informative knowledge, and forward it into survived features by transforming them into a low-rank discriminative metric space. It further explores the intrinsic low-rank structure of heterogeneous samples to reduce the computation and memory burden especially for highly-dimensional large-scale data. For the I-stage, we inherit the metric performance of survived features from the T-stage and then expand to include the new augmented features. Moreover, a smoothed Wasserstein distance is utilized to characterize the similarity relationships among the heterogeneous and complex samples, since the evolving features are not strictly aligned in the different stages. In addition to tackling the challenges in one-shot case, we also extend our model into multishot scenario. After deriving an efficient optimization strategy for both T-stage and I-stage, extensive experiments on several datasets verify the superior performance of our EML model.

Tao Zhang, Wei Li

Recent work has shown that optimizing the Learning Rate (LR) schedule can be a very accurate and efficient way to train deep neural networks. We observe that the rate of change (ROC) of LR has correlation with the training process, but how to use this relationship to control the training to achieve the purpose of improving accuracy? We propose a new method, k-decay, just add an extra item to the commonly used and easy LR schedule(exp, cosine and polynomial), is effectively improves the performance of these schedule, also better than the state-of-the-art algorithms of LR shcedule such as SGDR, CLR and AutoLRS. In the k-decay, by adjusting the hyper-parameter \(k\), to generate different LR schedule, when k increases, the performance is improved. We evaluate the k-decay method on CIFAR And ImageNet datasets with different neural networks (ResNet, Wide ResNet). Our experiments show that this method can improve on most of them. The accuracy has been improved by 1.08\% on the CIFAR-10 dataset and by 2.07 \% on the CIFAR-100 dataset. On the ImageNet, accuracy is improved by 1.25\%. Our method is not only a general method to be applied other LR Shcedule, but also has no additional computational cost.

Ao Ren, Tao Zhang, Yuhao Wang et al.

The rapidly growing parameter volume of deep neural networks (DNNs) hinders the artificial intelligence applications on resource constrained devices, such as mobile and wearable devices. Neural network pruning, as one of the mainstream model compression techniques, is under extensive study to reduce the number of parameters and computations. In contrast to irregular pruning that incurs high index storage and decoding overhead, structured pruning techniques have been proposed as the promising solutions. However, prior studies on structured pruning tackle the problem mainly from the perspective of facilitating hardware implementation, without analyzing the characteristics of sparse neural networks. The neglect on the study of sparse neural networks causes inefficient trade-off between regularity and pruning ratio. Consequently, the potential of structurally pruning neural networks is not sufficiently mined. In this work, we examine the structural characteristics of the irregularly pruned weight matrices, such as the diverse redundancy of different rows, the sensitivity of different rows to pruning, and the positional characteristics of retained weights. By leveraging the gained insights as a guidance, we first propose the novel block-max weight masking (BMWM) method, which can effectively retain the salient weights while imposing high regularity to the weight matrix. As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency. Our experimental results show that DARB can achieve 13$\times$ to 25$\times$ pruning ratio, which are 2.8$\times$ to 4.3$\times$ improvements than the state-of-the-art counterparts on multiple neural network models and tasks. Moreover, DARB can achieve 14.3$\times$ decoding efficiency than block pruning with higher pruning ratio.

Tao Zhang, Kun Zhu, Ekram Hossain

For enabling automatic deployment and management of cellular networks, the concept of self-organizing network (SON) was introduced. SON capabilities can enhance network performance, improve service quality, and reduce operational and capital expenditure (OPEX/CAPEX). As an important component in SON, self-healing is defined as a network paradigm where the faults of target networks are mitigated or recovered by automatically triggering a series of actions such as detection, diagnosis and compensation. Data-driven machine learning has been recognized as a powerful tool to bring intelligence into network and to realize self-healing. However, there are major challenges for practical applications of machine learning techniques for self-healing. In this article, we first classify these challenges into five categories: 1) data imbalance, 2) data insufficiency, 3) cost insensitivity, 4) non-real-time response, and 5) multi-source data fusion. Then we provide potential technical solutions to address these challenges. Furthermore, a case study of cost-sensitive fault detection with imbalanced data is provided to illustrate the feasibility and effectiveness of the suggested solutions.

Duo Wang, Yu Cheng, Mo Yu et al.

Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category, both of which have achieved successes in the simplified "$k$-shot $N$-way" image classification settings. Specifically, the optimization-based approaches train a meta-learner to predict the parameters of the task-specific classifiers. The task-specific classifiers are required to be homogeneous-structured to ease the parameter prediction, so the meta-learning approaches could only handle few-shot learning problems where the tasks share a uniform number of classes. The metric-based approaches learn one task-invariant metric for all the tasks. Even though the metric-learning approaches allow different numbers of classes, they require the tasks all coming from a similar domain such that there exists a uniform metric that could work across tasks. In this work, we propose a hybrid meta-learning model called Meta-Metric-Learner which combines the merits of both optimization- and metric-based approaches. Our meta-metric-learning approach consists of two components, a task-specific metric-based learner as a base model, and a meta-learner that learns and specifies the base model. Thus our model is able to handle flexible numbers of classes as well as generate more generalized metrics for classification across tasks. We test our approach in the standard "$k$-shot $N$-way" few-shot learning setting following previous works and a new realistic few-shot setting with flexible class numbers in both single-source form and multi-source forms. Experiments show that our approach can obtain superior performance in all settings.

Zhao Xiaole, Huali Zhang, Hangfei Liu et al.

Spatial resolution is a critical imaging parameter in magnetic resonance imaging (MRI). Acquiring high resolution MRI data usually takes long scanning time and would subject to motion artifacts due to hardware, physical, and physiological limitations. Single image super-resolution (SISR), especially that based on deep learning techniques, is an effective and promising alternative technique to improve the current spatial resolution of magnetic resonance (MR) images. However, the deeper network is more difficult to be effectively trained because the information is gradually weakened as the network deepens. This problem becomes more serious for medical images due to the degradation of training examples. In this paper, we present a novel channel splitting and serial fusion network (CSSFN) for single MR image super-resolution. Specifically, the proposed CSSFN network splits the hierarchical features into a series of subfeatures, which are then integrated together in a serial manner. Thus, the network becomes deeper and can deal with the subfeatures on different channels discriminatively. Besides, a dense global feature fusion (DGFF) is adopted to integrate the intermediate features, which further promotes the information flow in the network. Extensive experiments on several typical MR images show the superiority of our CSSFN model over other advanced SISR methods.

Yu Cheng, Duo Wang, Pan Zhou et al.

Deep neural networks (DNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past five years, tremendous progress has been made in this area. In this paper, we review the recent techniques for compacting and accelerating DNN models. In general, these techniques are divided into four categories: parameter pruning and quantization, low-rank factorization, transferred/compact convolutional filters, and knowledge distillation. Methods of parameter pruning and quantization are described first, after that the other techniques are introduced. For each category, we also provide insightful analysis about the performance, related applications, advantages, and drawbacks. Then we go through some very recent successful methods, for example, dynamic capacity networks and stochastic depths networks. After that, we survey the evaluation matrices, the main datasets used for evaluating the model performance, and recent benchmark efforts. Finally, we conclude this paper, discuss remaining the challenges and possible directions for future work.

Jingjia Huang, Nannan Li, Tao Zhang et al.

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure. We argue that the process of detecting actions should be naturally one of observation and refinement: observe the current window and refine the span of attended window to cover true action regions. In this paper, we propose an active action proposal model that learns to find actions through continuously adjusting the temporal bounds in a self-adaptive way. The whole process can be deemed as an agent, which is firstly placed at a position in the video at random, adopts a sequence of transformations on the current attended region to discover actions according to a learned policy. We utilize reinforcement learning, especially the Deep Q-learning algorithm to learn the agent's decision policy. In addition, we use temporal pooling operation to extract more effective feature representation for the long temporal window, and design a regression network to adjust the position offsets between predicted results and the ground truth. Experiment results on THUMOS 2014 validate the effectiveness of the proposed approach, which can achieve competitive performance with current action detection algorithms via much fewer proposals.