Michael Fuest,Pingchuan Ma,Ming Gui et al.
Michael Fuest et al.
Diffusion Models are popular generative modeling methods in various vision tasks, attracting significant attention. They can be considered a unique instance of self-supervised learning methods due to their independence from label annotation...
A CUR Decomposition-Based Mix-Order Framework for Large-Scale Hypergraph Matching [0.03%]
基于CUR分解的大型超图匹配混合阶框架
Qixuan Zheng,Ming Zhang,Hong Yan
Qixuan Zheng
Compatibilities between the hyperedges of two hy-pergraphs can be represented as a sparse tensor to avoid expo-nentially increasing computational costs in hypergraph matching. Kd-tree-based approximate nearest neighbor (ANN) methods have be...
Alessandro Conti,Enrico Fini,Massimiliano Mancini et al.
Alessandro Conti et al.
Large vision-language models revolutionized image classification and semantic segmentation paradigms. However, they typically assume a pre-defined set of categories, or vocabulary, at test time for composing textual prompts. This assumption...
All-in-One Transformer for Image Restoration Under Adverse Weather Degradations [0.03%]
面向恶劣天气退化的一站式图像恢复Transformer模型
Jiawei Mao,Yu Yang,Xuesong Yin et al.
Jiawei Mao et al.
Severe weather restoration models often face the simultaneous interaction of multiple degradations in real-world scenarios. Existing approaches typically handle single or composite degradations based on scene descriptors derived from text o...
ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild [0.03%]
面向野外遥感目标识别的大规模数据集和基准线(ATRNet-STAR)
Yongxiang Liu,Weijie Li,Li Liu et al.
Yongxiang Liu et al.
The absence of publicly available, large-scale, high-quality datasets for Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has significantly hindered the application of rapidly advancing deep learning techniques, which hold h...
Dynamical Causality under Latent Confounders for Biological Network Reconstruction [0.03%]
存在潜在混淆变量情况下的生物网络重构的动态因果性
Jinling Yan,Shao-Wu Zhang,Chihao Zhang et al.
Jinling Yan et al.
Causal interaction inference is prone to spurious causal interactions, due to the substantial confounders in a biological system. While many existing methods attempt to address misidentification challenges, there remains a notable lack of e...
Exploring Security Vulnerabilities in Multilingual Speech Translation Systems Via Deceptive Inputs [0.03%]
欺骗输入下跨语言语音翻译系统的安全漏洞探索研究
Chang Liu,Haolin Wu,Xi Yang et al.
Chang Liu et al.
As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited work has explored this issue in depth. This paper explores met...
DFormer++: Improving RGBD Representation Learning for Semantic Segmentation [0.03%]
DFormer++：改进RGBD表示学习以增强语义分割性能
Bo-Wen Yin,Jiao-Long Cao,Dan Xu et al.
Bo-Wen Yin et al.
We explore the potential of pretrain-and-finetune manner on the RGB-D semantic segmentation to solve the common mismatch problem in this field. Specifically, we present DFormer++, a novel RGB-D pretrain-and-finetune framework to learn trans...
Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms [0.03%]
具有一般函数逼近的对抗性 imitation learning：理论分析和实用算法
Tian Xu,Zhilong Zhang,Zexuan Chen et al.
Tian Xu et al.
Adversarial imitation learning (AIL), a prominent approach in imitation learning, has achieved significant practical success powered by neural network approximation. However, existing theoretical analyses of AIL are primarily confined to si...
Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment [0.03%]
预训练语言模型的参数高效微调方法批判性综述与评估
Lingling Xu,Haoran Xie,S Joe Qin et al.
Lingling Xu et al.
With the continuous growth in the number of parameters of the Transformer-based pretrained language models (PLMs), particularly the emergence of large language models (LLMs) with billions of parameters, many natural language processing (NLP...