Zobrazeno 1 - 10
of 237
pro vyhledávání: '"Chen, Chaoqi"'
Foundation models have made incredible strides in achieving zero-shot or few-shot generalization, leveraging prompt engineering to mimic the problem-solving approach of human intelligence. However, when it comes to some foundation models like Segment
Externí odkaz:
http://arxiv.org/abs/2408.16310
Despite the considerable advancements achieved by deep neural networks, their performance tends to degenerate when the test environment diverges from the training ones. Domain generalization (DG) solves this issue by learning representations independ
Externí odkaz:
http://arxiv.org/abs/2408.03608
Recent Transformer-based diffusion models have shown remarkable performance, largely attributed to the ability of the self-attention mechanism to accurately capture both global and local contexts by computing all-pair interactions among input tokens.
Externí odkaz:
http://arxiv.org/abs/2408.02615
The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor. Compared to conventional Data Augmentation (DA) techniques (e.g. cropping and rotation), exploiting prevailing diffusion models for data generation
Externí odkaz:
http://arxiv.org/abs/2403.12803
Autor:
Zhao, Gangming, Chen, Chaoqi, He, Wenhao, Pan, Chengwei, Fang, Chaowei, Li, Jinpeng, Chen, Xilin, Yu, Yizhou
Conventional domain adaptation typically transfers knowledge from a source domain to a stationary target domain. However, in many real-world cases, target data usually emerge sequentially and have continuously evolving distributions. Restoring and ad
Externí odkaz:
http://arxiv.org/abs/2402.04573
Autor:
Chen, Chaoqi, Tang, Luyao, Tao, Leitian, Zhou, Hong-Yu, Huang, Yue, Han, Xiaoguang, Yu, Yizhou
Albeit the notable performance on in-domain test points, it is non-trivial for deep neural networks to attain satisfactory accuracy when deploying in the open world, where novel domains and object classes often occur. In this paper, we study a practi
Externí odkaz:
http://arxiv.org/abs/2310.04724
Autor:
Wang, Jiexiang, Chen, Chaoqi
Unsupervised Domain Adaptation~(UDA) has attracted a surge of interest over the past decade but is difficult to be used in real-world applications. Considering the privacy-preservation issues and security concerns, in this work, we study a practical
Externí odkaz:
http://arxiv.org/abs/2308.06665
Autor:
Huang, Yi, Huang, Jiancheng, Liu, Jianzhuang, Yan, Mingfu, Dong, Yu, Lv, Jiaxi, Chen, Chaoqi, Chen, Shifeng
Latest diffusion-based methods for many image restoration tasks outperform traditional models, but they encounter the long-time inference problem. To tackle it, this paper proposes a Wavelet-Based Diffusion Model (WaveDM). WaveDM learns the distribut
Externí odkaz:
http://arxiv.org/abs/2305.13819
Recent advances in self-supervised learning (SSL) in computer vision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image views. However, the preserved high-l
Externí odkaz:
http://arxiv.org/abs/2301.00772
Domain generalization (DG) enables generalizing a learning machine from multiple seen source domains to an unseen target one. The general objective of DG methods is to learn semantic representations that are independent of domain labels, which is the
Externí odkaz:
http://arxiv.org/abs/2210.07571