Zobrazeno 1 - 10
of 150
pro vyhledávání: '"Yao, Hantao"'
Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously learned know
Externí odkaz:
http://arxiv.org/abs/2408.01076
Autor:
Gao, Haihan, Zhang, Rui, Yi, Qi, Yao, Hantao, Li, Haochen, Guo, Jiaming, Peng, Shaohui, Gao, Yunkai, Wang, QiCheng, Hu, Xing, Wen, Yuanbo, Zhang, Zihao, Du, Zidong, Li, Ling, Guo, Qi, Chen, Yunji
Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature extractor, hindering the agent from learning a unified cross-domain repr
Externí odkaz:
http://arxiv.org/abs/2406.03250
Diffusion-based re-ranking is a common method used for retrieving instances by performing similarity propagation in a nearest neighbor graph. However, existing techniques that construct the affinity graph based on pairwise instances can lead to the p
Externí odkaz:
http://arxiv.org/abs/2406.02343
Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as they are independent of the pre-
Externí odkaz:
http://arxiv.org/abs/2405.15549
Continual learning endeavors to equip the model with the capability to integrate current task knowledge while mitigating the forgetting of past task knowledge. Inspired by prompt tuning, prompt-based methods maintain a frozen backbone and train with
Externí odkaz:
http://arxiv.org/abs/2401.11544
Audio-visual video recognition (AVVR) aims to integrate audio and visual clues to categorize videos accurately. While existing methods train AVVR models using provided datasets and achieve satisfactory results, they struggle to retain historical clas
Externí odkaz:
http://arxiv.org/abs/2401.06287
Prompt tuning represents a valuable technique for adapting pre-trained visual-language models (VLM) to various downstream tasks. Recent advancements in CoOp-based methods propose a set of learnable domain-shared or image-conditional textual tokens to
Externí odkaz:
http://arxiv.org/abs/2311.18231
Autor:
Li, Haochen, Zhang, Rui, Yao, Hantao, Song, Xinkai, Hao, Yifan, Zhao, Yongwei, Li, Ling, Chen, Yunji
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a discrimina
Externí odkaz:
http://arxiv.org/abs/2306.05718
Object Re-identification (ReID) aims to retrieve the probe object from many gallery images with the ReID model inferred based on a stationary camera-free dataset by associating and collecting the identities across all camera views. When deploying the
Externí odkaz:
http://arxiv.org/abs/2305.15909
Prompt tuning is an effective way to adapt the pre-trained visual-language model (VLM) to the downstream task using task-related textual tokens. Representative CoOp-based work combines the learnable textual tokens with the class tokens to obtain spec
Externí odkaz:
http://arxiv.org/abs/2303.13283