检索结果-内蒙古大学图书馆

Category-aware Allocation Transformer for Weakly Supervised Object Localization

学校读者我要写书评

暂无评论

Category-aware Allocation Transformer for Weakly Supervised ...

International Conference on Computer Vision (ICCV)

作者： Zhiwei Chen Jinren Ding Liujuan Cao Yunhang Shen Shengchuan Zhang Guannan Jiang Rongrong Ji Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Tencent Youtu Lab China CATL China

Weakly supervised object localization (WSOL) aims to localize objects based on only image-level labels as supervision. Recently, transformers have been introduced into WSOL, yielding impressive results. The self-attention mechanism and multilayer perceptron structure in transformers preserve long-range feature dependency, facilitating complete localization of the full object extent. However, current transformer-based methods predict bounding boxes using category-agnostic attention maps, which may lead to confused and noisy object localization. To address this issue, we propose a novel Category-aware Allocation TRansformer (CATR) that learns category-aware representations for specific objects and produces corresponding category-aware attention maps for object localization. First, we introduce a Category-aware Stimulation Module (CSM) to induce learnable category biases for self-attention maps, providing auxiliary supervision to guide the learning of more effective transformer representations. Second, we design an Object Constraint Module (OCM) to refine the object regions for the category-aware attention maps in a self-supervised manner. Extensive experiments on the CUB-200-2011 and ILSVRC datasets demonstrate that the proposed CATR achieves significant and consistent performance improvements over competing approaches.

关键词：

L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shi, Ziwei Zhang, Xiaoran Xia, Yan Zang, Yu Shen, Siqi Wang, Cheng Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Technical University of Munich Germany Munich Center for Machine Learning Germany

We tackle the challenge of LiDAR-based place recognition, which traditionally depends on costly and time-consuming prior 3D maps. To overcome this, we first construct XAL&RSI dataset, which encompasses approximately 110, 000 remote sensing submaps and 13, 000 LiDAR point cloud submaps captured in urban scenes, and propose a novel method, L2RSI, for cross-view LiDAR place recognition using high-resolution Remote Sensing Imagery. This approach enables large-scale localization capabilities at a reduced cost by leveraging readily available overhead images as map proxies. L2RSI addresses the dual challenges of cross-view and cross-modal place recognition by learning feature alignment between point cloud submaps and remote sensing submaps in the semantic domain. Additionally, we introduce a novel probability propagation method based on a dynamic Gaussian mixture model to refine position predictions, effectively leveraging temporal and spatial information. This approach enables large-scale retrieval and cross-scene generalization without fine-tuning. Extensive experiments on XA-L&RSI demonstrate that, within a 100km2 retrieval range, L2RSI accurately localizes 95.08% of point cloud submaps within a 30m radius for top-1 retrieved location. We provide a video to more vividly display the place recognition results of L2RSI at https://***/L2RSI/. Copyright © 2025, The Authors. All rights reserved.

关键词： Hydrogeology

Multi-Agent Reinforcement Learning for Wireless Networks Against Adversarial Communications

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning for Wireless Networks Aga...

IEEE Conference on Global Communications (GLOBECOM)

作者： Zefang Lv Yifan Chen Liang Xiao Helin Yang Xiangyang Ji Department of Information and Communication Engineering Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen University Department of Automation Tsinghua University

Based on the efficient and reliable exchange of learning messages containing both the policy selection experiences such as the learning parameters and observations among the learning agents, multi -agent reinforcement learning (RL) has to address adversarial communications that send fake learning messages to learning agents with the goal of decreasing the RL rewards or even failing the learning tasks. In this paper, we propose a multi-agent RL (MARL) communication framework for wireless networks against adversarial communications, in which each learning agent chooses the cooperative agents to share learning messages based on the agent reputation that indicates the probability to send fake learning messages. By comparing with the learning history, each learning agent authenticates the received learning messages before integrating them in the RL task state formulation and the learning parameter update for robust task learning. The learning factor that increases with the correlation between the local and the shared observation is calculated to update the task Q-values and neural network weights based on the shared learning parameters. As a case study, the multi-agent deep Q-network within our proposed MARL communication framework is implemented in the UAV swarm video transmission system and the performance gain over the benchmark is provided in the simulation results based on 5-UAV swarm against an attacker that sends fake observations and neural network weights.

关键词：

AdaFlow: efficient Long Video Editing via Adaptive Attention Slimming And keyframe Selection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Shuheng Liu, Yuqi Zhou, Hongbo Peng, Jun Zhou, Yiyi Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Institute of Artificial Intelligence Xiamen University 361005 China Peng Cheng Laboratory Shenzhen518000 China

Despite great progress, text-driven long video editing is still notoriously challenging mainly due to excessive memory overhead. Although recent efforts have simplified this task into a two-step process of keyframe translation and interpolation generation, the token-wise keyframe translation still plagues the upper limit of video length. In this paper, we propose a novel and training-free approach towards efficient and effective long video editing, termed AdaFlow. We first reveal that not all tokens of video frames hold equal importance for keyframe translation, based on which we propose an Adaptive Attention Slimming scheme for AdaFlow to squeeze the KV sequence, thus increasing the number of keyframes for translations by an order of magnitude. In addition, an Adaptive keyframe Selection scheme is also equipped to select the representative frames for joint editing, further improving generation quality. With these innovative designs, AdaFlow achieves high-quality long video editing of minutes in one inference, i.e., more than 1k frames on one A800 GPU, which is about ten times longer than the compared methods, e.g., TokenFlow. To validate AdaFlow, we also build a new benchmark for long video editing with high-quality annotations, termed LongV-EVAL. Our code is released at: https://***/jidantang55/AdaFlow. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

Optimal Synthesis for Stochastic Systems with Information Security Preservation Under Temporal Logic Constraints

学校读者我要写书评

暂无评论

Optimal Synthesis for Stochastic Systems with Information Se...

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Yiwei Zheng Weiyao Lan Xiao Yu Department of Automation Xiamen Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen China Institute of Artificial Intelligence Xiamen University Xiamen China

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

In this paper, we present a method for synthesizing optimal policies for stochastic systems under high-level mission specifications while maintaining information security. The stochastic systems are modeled as probabilistic labeling Markov decision processes (PLMDPs), and the high-level mission specifications are represented by linear temporal logic (LTL) formulas, which must be satisfied repeatedly, infinitely often. Meanwhile, an intruder is modeled as an observer who knows the exact structure of the system and passively monitors its behavior, aiming to infer the high-level mission specifications. Our objective is to synthesize an optimal policy that minimizes the mean payoff cost while preventing the intruder from definitively determining the given mission specifications. We begin by extending the PLMDP model by incorporating an observation function and the corresponding probability function, and we introduce the concept of LTL opacity for stochastic systems. Next, by proposing a new structure called the synchronous accepting maximally end component, we identify the subset of the accepting end components that satisfy the LTL opacity requirement. Finally, we develop a modified linear program with information security constraints to synthesize an optimal policy that ensures both formal correctness and LTL opacity.

关键词： Costs Stochastic systems Markov decision processes Information security Observers Probabilistic logic Labeling Robots Optimization Monitoring

Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiong, Kezheng Xiang, Haoen Xu, Qingshan Wen, Chenglu Shen, Siqi Li, Jonathan Wang, Cheng Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Nanyang Technological University Singapore University of Waterloo Waterloo Canada

Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the need for costly pose annotations. However, they fail to establish reliable optimization objectives for unsupervised training, either relying on overly strong geometric assumptions, or suffering from poor-quality pseudo-labels due to inadequate integration of low-level geometric and high-level contextual information. We have observed that in the feature space, latent new inlier correspondences tend to cluster around respective positive anchors that summarize features of existing inliers. Motivated by this observation, we propose a novel unsupervised registration method termed INTEGER to incorporate high-level contextual information for reliable pseudo-label mining. Specifically, we propose the Feature-Geometry Coherence Mining module to dynamically adapt the teacher for each mini-batch of data during training and discover reliable pseudo-labels by considering both high-level feature representations and low-level geometric cues. Furthermore, we propose Anchor-Based Contrastive Learning to facilitate contrastive learning with anchors for a robust feature space. Lastly, we introduce a Mixed-Density Student to learn density-invariant features, addressing challenges related to density variation and low overlap in the outdoor scenario. Extensive experiments on KITTI and nuScenes datasets demonstrate that our INTEGER achieves competitive performance in terms of accuracy and generalizability. [Code Release] © 2024, CC BY-NC-ND.

关键词： Contrastive Learning

Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Yiwei Sun, Xiaoshuai Ji, Jiayi Jiang, Guannan Zhuang, Weilin Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Fujian Xiamen China Contemporary Amperex Technology Co. Limited Fujian Ningde China

Text-based person retrieval (TPR) is a challenging task that involves retrieving a specific individual based on a textual description. Despite considerable efforts to bridge the gap between vision and language, the significant differences between these modalities continue to pose a challenge. Previous methods have attempted to align text and image samples in a modal-shared space, but they face uncertainties in optimization directions due to the movable features of both modalities and the failure to account for one-to-many relationships of image-text pairs in TPR datasets. To address this issue, we propose an effective bi-directional one-to-many embedding paradigm that offers a clear optimization direction for each sample, thus mitigating the optimization problem. Additionally, this embedding scheme generates multiple features for each sample without introducing trainable parameters, making it easier to align with several positive samples. Based on this paradigm, we propose a novel Bi-directional one-to-many Embedding Alignment (Beat) model to address the TPR task. Our experimental results demonstrate that the proposed Beat model achieves state-of-the-art performance on three popular TPR datasets, including CUHK-PEDES (65.61 R@1), ICFG-PEDES (58.25 R@1), and RSTPReID (48.10 R@1). Furthermore, additional experiments on MS-COCO, CUB, and Flowers datasets further demonstrate the potential of Beat to be applied to other image-text retrieval tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

DYNAMIC LOW-RANK SPARSE ADAPTATION FOR LARGE LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Weizhong Zhang, Yuxin Zheng, Xiawu Liu, Yang Lin, Jing Yao, Yiwu Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Huawei Technologies China Institute of Artificial Intelligence Xiamen University China Peng Cheng Laboratory Shenzhen China

Despite the efficacy of network sparsity in alleviating the deployment strain of Large Language Models (LLMs), it endures significant performance degradation. Applying Low-Rank Adaptation (LoRA) to fine-tune the sparse LLMs offers an intuitive approach to counter this predicament, while it holds shortcomings include: 1) The inability to integrate LoRA weights into sparse LLMs post-training, and 2) Insufficient performance recovery at high sparsity ratios. In this paper, we introduce dynamic Low-rank Sparse Adaptation (LoSA), a novel method that seamlessly integrates low-rank adaptation into LLM sparsity within a unified framework, thereby enhancing the performance of sparse LLMs without increasing the inference latency. In particular, LoSA dynamically sparsifies the LoRA outcomes based on the corresponding sparse weights during fine-tuning, thus guaranteeing that the LoRA module can be integrated into the sparse LLMs post-training. Besides, LoSA leverages Representation Mutual Information (RMI) as an indicator to determine the importance of layers, thereby efficiently determining the layer-wise sparsity rates during fine-tuning. Predicated on this, LoSA adjusts the rank of the LoRA module based on the variability in layer-wise reconstruction errors, allocating an appropriate fine-tuning for each layer to reduce the output discrepancies between dense and sparse LLMs. Extensive experiments tell that LoSA can efficiently boost the efficacy of sparse LLMs within a few hours, without introducing any additional inferential burden. For example, LoSA reduced the perplexity of sparse LLaMA-2-7B by 68.73↓ and increased zero-shot accuracy by 16.32%↑, achieving a 2.60× speedup on CPU and 2.23× speedup on GPU, requiring only 45 minutes of fine-tuning on a single NVIDIA A100 80GB GPU. Code is available at https://***/wzhuang-xmu/LoSA. Copyright © 2025, The Authors. All rights reserved.

关键词： Graphics processing unit

Pseudo-label Alignment for Semi-supervised Instance Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Jie Chen, Chen Cao, Liujuan Zhang, Shengchuan Shu, Annan Jiang, Guannan Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Contemporary Amperex Technology Co. Limited China

Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that contain valuable information may be directly filtered out due to mismatches in class and mask quality. To address this issue, we propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper. In PAIS, we devise a dynamic aligning loss (DALoss) that adjusts the weights of semi-supervised loss terms with varying class and mask score pairs. Through extensive experiments conducted on the COCO and Cityscapes datasets, we demonstrate that PAIS is a promising framework for semi-supervised instance segmentation, particularly in cases where labeled data is severely limited. Notably, with just 1% labeled data, PAIS achieves 21.2 mAP (based on Mask-RCNN) and 19.9 mAP (based on K-Net) on the COCO dataset, outperforming the current state-of-the-art model, i.e., NoisyBoundary with 7.7 mAP, by a margin of over 12 points. Code is available at: https://***/hujiecpp/PAIS. Copyright © 2023, The Authors. All rights reserved.

关键词： Information filtering