检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at https://***/Darkbblue/generic-diffusion-feature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation

Imagine Before Go: Self-Supervised Generative Map for Object...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinyao Yu Xinhang Song Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The Object Goal navigation (ObjectNav) task requires the agent to navigate to a specified target in an unseen environment. Since the environment layout is unknown, the agent needs to infer the unknown contextual objects from partially observations, thereby deducing the likely location of the target. Previous end-to-end RL methods capture contextual relationships through implicit representations while they lack notion of geometry. Alternatively, modular methods construct local maps for recording the observed geometric structure of unseen environment, however, lacking the reasoning of contextual relation limits the exploration efficiency. In this work, we propose the self-supervised generative map (SGM), a modular method that learns the explicit context relation via self-supervised learning. The SGM is trained to leverage both episodic observations and general knowledge to reconstruct the masked pixels of a cropped global map. During navigation, the agent maintains an incomplete local semantic map, meanwhile, the unknown regions of the local map are generated by the pretrained SGM. Based on the generated map, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson, MP3D and HM3D show the effectiveness of our method. The code is available at https://***/sx-zhang/SGM.

关键词： Training Geometry Navigation Large language models Semantics Layout Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Semantic Head for Cascade Instance Segmentation

Enhanced Semantic Head for Cascade Instance Segmentation

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Huang, Xuerong Su, Li Li, Guorong Zhang, Xinfeng Qing, Laiyun Huang, Qingming University of Chinese Academy of Sciences Beijing China Cas Key Lab of Big Data Mining and Knowledge Management Beijing China Institute of Computing Technology Cas Key Lab of Intelligent Information Processing Beijing China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Recently, cascade instance segmentation inspired by cascade object detection has achieved notable performance. Due to the lack of global information, many methods suffer from incomplete segmentation such as missing edge regions and discontinuities within instances. To solve this problem, we proposed an effective and flexible semantic head to extract enhanced spatial context information. A vision transformer is utilized to generate global context features, and a convolution network is adopted to generate spatial context features. After combining the two modules, we obtain enhanced semantic segmentation features for segmentation. Extensive experiments show that the enhanced semantic head achieves 40.6% and 42.3% mask AP for cascade predictor HTC and DSC, which surpass about 0.9 and 1.4 percentage points respectively. The enhanced semantic head is universal and effective to improve the performance of different cascade predictors. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Domain-aware Node Representation Learning for Graph Out-of-Distribution Generalization

Domain-aware Node Representation Learning for Graph Out-of-D...

引用

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

作者： Yi Qiao Yang Liu Qing He Xiang Ao Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciencs Beijing China Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph Neural Networks (GNNs) have demonstrated impressive success across diverse fields when data satisfies in-distribution (ID) assumption. Nevertheless, GNN performance significantly declines in cases of distribution shifts between training and testing graph data. This degradation primarily stems from spurious correlations between irrelevant domain information and target labels in out-of-distribution (OOD) scenarios. Thus, maximizing the utilization of domain information becomes imperative. In light of this, we propose a novel approach named Domain-aware Node Representation Learning (DNRL), comprehensively incorporates domain information to bolster generalization capability. Specifically, DNRL selectively interpolates nodes with the same label but different domains, extending training data into unseen domains and alleviating the effects caused by domain-related spurious correlations. Futhermore, by introducing a domain-aware contrastive learning strategy, our method implicitly decouples domain information from node information to learn domain-independent node representations. Extensive experiments on graph out-of-distribution benchmarks demonstrate that DNRL can achieve effective OOD generalization performance across diverse domains.

关键词： Representation learning Training Degradation Interpolation Correlation Training data Signal processing Graph neural networks Data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutual information 48

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutua...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Jicun Li, Xingjian Wang, Tianyang Wang, Shi Cao, Yanan Xu, Chengzhong Dou, Dejing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Big Data Lab Baidu Research China University of Alabama Birmingham United States Institute of Information Engineering Chinese Academy of Sciences China State Key Lab of Iotsc University of Macau China

ISBN: (纸本)9781728163277

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method. © 2023 IEEE.

关键词： Fine-tuning Stability Mutual information Pre-trained Language Model

来源：评论

学校读者我要写书评

暂无评论

Learning to Localize Cross-Anatomy Landmarks in X-Ray Images with a Universal Model

引用

Biomedical Engineering Frontiers 2022年第1期3卷 298-308页

作者： Heqin Zhu Qingsong Yao Li Xiao S.Kevin Zhou Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China Center for Medical Imaging RoboticsAnalytic Computing&Learning(MIRACLE)School of Biomedical Engineering&Suzhou Institute for Advanced ResearchUniversity of Science and Technology of ChinaSuzhou 215123China

Objective and Impact *** this work,we develop a universal anatomical landmark detection model which learns once from multiple datasets corresponding to different anatomical *** with the conventional model trained on a single dataset,this universal model not only is more light weighted and easier to train but also improves the accuracy of the anatomical landmark *** accurate and automatic localization of anatomical landmarks plays an essential role in medical image ***,recent deep learning-based methods only utilize limited data from a single *** is promising and desirable to build a model learned from different regions which harnesses the power of big *** model consists of a local network and a global network,which capture local features and global features,*** local network is a fully convolutional network built up with depth-wise separable convolutions,and the global network uses dilated convolution to enlarge the receptive field to model global *** evaluate our model on four 2D X-ray image datasets totaling 1710 images and 72 landmarks in four anatomical *** experimental results show that our model improves the detection accuracy compared to the state-of-the-art *** model makes the first attempt to train a single network on multiple datasets for landmark *** results qualitatively and quantitatively show that our proposed model performs better than other models trained on multiple datasets and even better than models trained on a single dataset separately.

关键词： convolution utilize separable

来源：评论

学校读者我要写书评

暂无评论

Adaptively feature matching via joint transformational-spatial clustering

Adaptively feature matching via joint transformational-spati...

引用

作者： Wang, Linbo Tan, Li Fang, Xianyong Guo, Yanwen Wan, Shaohua MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei China National Key Lab for Novel Software Technology Nanjing University Nanjing China School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan China

The transformational and spatial proximities are important cues for identifying inliers from an appearance based match set because correct matches generally stay close in input images and share similar local transformations. However, most existing approaches only check one type of them or both types consecutively with manually set thresholds, and thus their matching accuracy and flexibility in handling large-scale images are limited. In this paper, we present an efficient clustering based approach to identify match inliers with both proximities simultaneously. It first projects the putative matches into a joint transformational-spatial space, where mismatches tend to scatter all around while correct matches gather together. A mode-seeking process based on joint kernel density estimation is then proposed to obtain significant clusters in the joint space, where each cluster contains matches mapping the same object across images with high accuracy. Moreover, kernel bandwidths for measuring match proximities are adaptively set during density estimation, which enhances its applicability for matching different images. Experiments on three standard datasets show that the proposed approach delivers superior performance on a variety of feature matching tasks, including multi-object matching, duplicate object matching and object retrieval. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Clustering Density estimation Feature matching Mode-seeking

来源：评论

学校读者我要写书评

暂无评论

The chordata olfactory receptor database

引用

Protein & Cell 2025年第4期16卷 283-292页

作者： Wei Han Siyu Bao Jintao Liu Yiran Wu Liting Zeng Tao Zhang Ningmeng Chen Kai Yao Shunguo Fan Aiping Huang Yuanyuan Feng Guiquan Zhang Ruiyi Zhang Hongjin Zhu Tian Hua Zhijie Liu Lina Cao Xingxu Huang Suwen Zhao Human Institute ShanghaiTech UniversityShanghai 201210China Research Center for Life Sciences Computing Zhejiang LabHangzhou 311121China Department of Intelligent Edge Cloud China Telecom Cloud Technology Co.Ltd.Shanghai 200120China School of Life Science and Technology ShanghaiTech UniversityShanghai 201210China School of Information Science and Technology Shanghai Tech UniversityShanghai 201210China Shanghai Key Laboratory of High-Resolution Electron Microscopy Shanghai Tech UniversityShanghai 201210China Zhejiang Provincial Key Laboratory of Pancreatic Disease The First Affiliated Hospitaland Institute of Translational MedicineZhejiang University School of MedicineHangzhou 310029China Shanghai Clinical Research and Trial Center Shanghai 201210China

Introduction of database Olfaction is one of the oldest chemosensory systems in chordates,playing crucial roles in their foraging,predator evasion,social communication,mating and parental care(Guo et al.,2023;Li and Liberles,2015;Liberles,2014).The initial step of olfaction is the binding and activation of olfactory receptors(ORs)by odorants in a combinatorial way(Malnic et al.,1999).

关键词： chordates chemosensory systems introduction database olfaction foraging olfaction binding activation olfactory olfactory receptors odorants

来源：评论

学校读者我要写书评

暂无评论

A Category Agnostic Model for Visual Rearrangment

A Category Agnostic Model for Visual Rearrangment

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuyi Liu Xinhang Song Weijie Li Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

This paper presents a novel category agnostic model for visual rearrangement task, which can help an embodied agent to physically recover the shuffled scene configuration without any category concepts to the goal configuration. Previous methods usually follow a similar architecture, completing the rearrangement task by aligning the scene changes of the goal and shuffled configuration, according to the semantic scene graphs. However, constructing scene graphs requires the inference of category labels, which not only causes the accuracy drop of the entire task but also limits the application in real world scenario. In this paper, we delve deep into the essence of visual re-arrangement task and focus on the two most essential issues, scene change detection and scene change matching. We utilize the movement and the protrusion of point cloud to accurately identify the scene changes and match these changes depending on the similarity of category agnostic appearance feature. Moreover, to assist the agent to explore the environment more efficiently and comprehensively, we propose a closer-aligned-retrace exploration policy, aiming to observe more details of the scene at a closer distance. We conduct extensive experiments onAI2THOR Rearrangement Challenge based on RoomR dataset and a new multi-room multi-instance dataset MrMiR collected by us. The experimental results demonstrate the effectiveness of our proposed method.

关键词： Point cloud compression Visualization Computer vision Accuracy Semantics Feature extraction Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Downstream Task-agnostic Transferable Attacks on Language-Image Pre-training Models

Downstream Task-agnostic Transferable Attacks on Language-Im...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yiqiang Lv Jingjing Chen Zhipeng Wei Kai Chen Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing

Vision-language pre-trained models (e.g., CLIP) trained on large-scale datasets via self-supervised learning, are drawing increasing research attention since they can achieve superior performances on multi-modal downstream tasks. Nevertheless, we find that the adversarial perturbations crafted on vision-language pre-trained models can be used to attack different corresponding downstream task models. Specifically, to investigate such adversarial transferability, we introduce a task-agnostic method named Global and Local Augmentation (GLA) attack to generate highly transferable adversarial examples on CLIP, to attack black-box downstream task models. GLA adopts random crop and resize at both global and local patch levels, to create more diversity and make adversarial noises robust. Then GLA generates the adversarial perturbations by minimizing the cosine similarity between intermediate features from augmented adversarial and benign examples. Extensive experiments on three CLIP image encoders with different backbones and three different downstream tasks demonstrate the superiority of our method compared with other strong baselines. The code is available at https://***/yqlvcoding/GLAattack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：