检索结果-内蒙古大学图书馆

Graph Contrastive Learning with Decoupled Augmentation

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Decoupled Augmentation

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Gao, Shihao Li, Caoshuo Mao, Cunli Zhang, Xulong Qu, Xiaoyang Jin, Taisong Wang, Jianzong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China Ping An Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9798350368741

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph's semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches. © 2025 IEEE.

关键词： Contrastive learning Graph representation Self-supervised learning

Memory-Reduced Meta-Learning with Guaranteed Convergence

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Honglin Ma, Ji Yu, Xiao Department of Automation Xiamen University 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

The optimization-based meta-learning approach is gaining increased traction because of its unique ability to quickly adapt to a new task using only small amounts of data. However, existing optimization-based meta-learning approaches, such as MAML, ANIL and their variants, generally employ backpropagation for upper-level gradient estimation, which requires using historical lower-level parameters/gradients and thus increases computational and memory overhead in each iteration. In this paper, we propose a meta-learning algorithm that can avoid using historical parameters/gradients and significantly reduce memory costs in each iteration compared to existing optimization-based meta-learning approaches. In addition to memory reduction, we prove that our proposed algorithm converges sublinearly with the iteration number of upper-level optimization, and the convergence error decays sublinearly with the batch size of sampled tasks. In the specific case in terms of deterministic meta-learning, we also prove that our proposed algorithm converges to an exact solution. Moreover, we quantify that the computational complexity of the algorithm is on the order of O(ϵ−1), which matches existing convergence results on meta-learning even without using any historical parameters/gradients. Experimental results on meta-learning benchmarks confirm the efficacy of our proposed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词：

efficient Dataset Distillation through Low-Rank Space Sampling

学校读者我要写书评

暂无评论

Efficient Dataset Distillation through Low-Rank Space Sampli...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hangyang Kong Wenbo Zhou Xuxiang He Xiaotong Tu Xinghao Ding Institute of Artificial Intelligence Xiamen University Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China School of Informatics Xiamen University Xiamen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Huge amount of data is the key of the success of deep learning, however, redundant information impairs the generalization ability of the model and increases the burden of calculation. Dataset Distillation (DD) compresses the original dataset into a smaller but representative subset for high-quality data and efficient training strategies. Existing works for DD generate synthetic images by treating each image as an independent entity, thereby overlooking the common features among data. This paper proposes a dataset distillation method based on Matching Training Trajectories with Low-rank Space Sampling(MTT-LSS), which uses low-rank approximations to capture multiple low-dimensional manifold subspaces of the original data. The synthetic data is represented by basis vectors and shared dimension mappers from these subspaces, reducing the cost of generating individual data points while effectively minimizing information redundancy. The proposed method is tested on CIFAR-10, CIFAR-100, and SVHN datasets, and outperforms the baseline methods by an average of 9.9%.

关键词： Training Manifolds Costs Redundancy Noise Signal processing algorithms Vectors Trajectory Speech processing Synthetic data

AnyTrans: Translate AnyText in the Image with Large Scale Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qian, Zhipeng Zhang, Pei Yang, Baosong Fan, Kai Ma, Yiwei Wong, Derek F. Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Alibaba Group Inc China NLP2CT Lab University of Macau China

This paper introduces AnyTrans, an all-encompassing framework for the task–Translate AnyText in the Image (TATI), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, the advanced inpainting and editing abilities of diffusion models make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Additionally, our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the TATI task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs. Copyright © 2024, The Authors. All rights reserved.

关键词： Diffusion

EOV-Seg: efficient Open-Vocabulary Panoptic Segmentation 39

学校读者我要写书评

暂无评论

EOV-Seg: Efficient Open-Vocabulary Panoptic Segmentation

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Niu, Hongwei Hu, Jie Lin, Jianghang Jiang, Guannan Zhang, Shengchuan Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Institute of Artificial Intelligence Xiamen University Fujian China National University of Singapore Singapore Fujian China

ISBN: (纸本)157735897X

Open-vocabulary panoptic segmentation aims to segment and classify everything in diverse scenes across an unbounded vocabulary. Existing methods typically employ two-stage or single-stage framework. The two-stage framework involves cropping the image multiple times using masks generated by a mask generator, followed by feature extraction, while the single-stage framework relies on a heavyweight mask decoder to make up for the lack of spatial position information through self-attention and cross-attention in multiple stacked Transformer blocks. Both methods incur substantial computational overhead, thereby hindering the efficiency of model inference. To fill the gap in efficiency, we propose EOV-Seg, a novel single-stage, shared, efficient, and spatial-aware framework designed for open-vocabulary panoptic segmentation. Specifically, EOV-Seg innovates in two aspects. First, a Vocabulary-Aware Selection (VAS) module is proposed to improve the semantic comprehension of visual aggregated features and alleviate the feature interaction burden on the mask decoder. Second, we introduce a Two-way Dynamic Embedding Experts (TDEE), which efficiently utilizes the spatial awareness capabilities of ViT-based CLIP backbone. To the best of our knowledge, EOV-Seg is the first open-vocabulary panoptic segmentation framework towards efficiency, which runs faster and achieves competitive performance compared with state-of-the-art methods. Specifically, with COCO training only, EOV-Seg achieves 24.5 PQ, 32.1 mIoU, and 11.6 FPS on the ADE20K dataset and the inference time of EOV-Seg is 4-19 times faster than state-of-the-art methods. Especially, equipped with ResNet50 backbone, EOV-Seg runs 23.8 FPS with only 71M parameters on a single RTX 3090 GPU. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

Long-Tailed Federated Learning Via Aggregated Meta Mapping

学校读者我要写书评

暂无评论

Long-Tailed Federated Learning Via Aggregated Meta Mapping

IEEE International Conference on Image Processing

作者： Pinxin Qian Yang Lu Hanzi Wang Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China The Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China

One major problem concerned in federated learning is data non-IIDness. Existing federated learning methods to deal with non-IID data generally assume that the data is globally balanced. However, real-world multi-class data tends to exhibit long-tail distribution. Therefore, we propose a new federated learning method called Federated Aggregated Meta Mapping (FedAMM) to address the joint problem of non-IID and global long-tailed data in a federated learning scenario. FedAMM assigns different weights to the local training samples by trainable loss-weight mapping in a meta-learning manner. To deal with data non-IIDness and global long-tail, the meta loss-weight mappings are aggregated on the server to acquire global long-tail distribution knowledge implicitly. We further propose an asynchronous meta updating mechanism to reduce the communication cost for meta-learning training. Experiments show that FedAMM outperforms the state-of-the-art federated learning methods.

关键词：

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection 39

学校读者我要写书评

暂无评论

L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Dete...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Xun Xu, Ziyu Wu, Hai Wang, Jinlong Xia, Qiming Xia, Yan Li, Jonathan Gao, Kyle Wen, Chenglu 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 Zhongguancun Academy China Technische Universität München Germany University of Waterloo Canada

ISBN: (纸本)157735897X

LiDAR-based 3D object detection is crucial for autonomous driving. However, due to the quality deterioration of LiDAR point clouds, it suffers from performance degradation in adverse weather conditions. Fusing LiDAR with the weather-robust 4D radar sensor is expected to solve this problem;however, it faces challenges of significant differences in terms of data quality and the degree of degradation in adverse weather. To address these issues, we introduce L4DR, a weather-robust 3D object detection method that effectively achieves LiDAR and 4D Radar fusion. Our L4DR proposes Multi-Modal Encoding (MME) and Foreground-Aware Denoising (FAD) modules to reconcile sensor gaps, which is the first exploration of the complementarity of early fusion between LiDAR and 4D radar. Additionally, we design an Inter-Modal and Intra-Modal ({IM}2) parallel feature extraction backbone coupled with a Multi-Scale Gated Fusion (MSGF) module to counteract the varying degrees of sensor degradation under adverse weather conditions. Experimental evaluation on a VoD dataset with simulated fog proves that L4DR is more adaptable to changing weather conditions. It delivers a significant performance increase under different fog levels, improving the 3D mAP by up to 20.0% over the traditional LiDAR-only approach. Moreover, the results on the K-Radar dataset validate the consistent performance improvement of L4DR in real-world adverse weather conditions. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Zhihang Lin, Mingbao Xie, Yuan Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Shanghai Innovation Institute China Skywork AI Singapore East China Normal University Shanghai China

This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models based on Group Relative Policy Optimization (GRPO). GRPO, while effective, incurs high training costs due to the need for sampling multiple completions for each question. Our experiment and theoretical analysis reveals that the number of completions impacts model accuracy yet increases training time multiplicatively, and not all completions contribute equally to policy training—their contribution depends on their relative advantage. To address these issues, we propose CPPO, which prunes completions with low absolute advantages, significantly reducing the number needed for gradient calculation and updates. Additionally, we introduce a dynamic completion allocation strategy to maximize GPU utilization by incorporating additional questions, further enhancing training efficiency. Experimental results demonstrate that CPPO achieves up to 8.32× speedup on GSM8K and 3.51× on Math while preserving or even enhancing the accuracy compared to the original GRPO. We release our code at https://***/lzhxmu/CPPO. Copyright © 2025, The Authors. All rights reserved.

关键词：

Frequency Domain Nuances Mining for Visible-Infrared Person Re-identification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yukang Lu, Yang Yan, Yan Wang, Hanzi Li, Xuelong Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University 361005 China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Northwestern Polytechnical University Shaanxi Xi’an China

The key of visible-infrared person re-identification (VIReID) lies in how to minimize the modality discrepancy between visible and infrared images. Existing methods mainly exploit the spatial information while ignoring the discriminative frequency information. To address this issue, this paper aims to reduce the modality discrepancy from the frequency domain perspective. Specifically, we propose a novel Frequency Domain Nuances Mining (FDNM) method to explore the cross-modality frequency domain information, which mainly includes an amplitude guided phase (AGP) module and an amplitude nuances mining (ANM) module. These two modules are mutually beneficial to jointly explore frequency domain visible-infrared nuances, thereby effectively reducing the modality discrepancy in the frequency domain. Besides, we propose a center-guided nuances mining loss to encourage the ANM module to preserve discriminative identity information while discovering diverse cross-modality nuances. Extensive experiments show that the proposed FDNM has significant advantages in improving the performance of VIReID. Specifically, our method outperforms the second-best method by 5.2% in Rank-1 accuracy and 5.8% in mAP on the SYSUMM01 dataset under the indoor search mode, respectively. Besides, we also validate the effectiveness and generalization of our method on the challenging visible-infrared face recognition task. The code will be available. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis