2 citations · 3 across the 5 of their papers we have counts for
5 papers
Attention Head Purification: A New Perspective to Harness CLIP for Domain Generalization
Yingfan Wang, Guoliang Kang
Domain Generalization (DG) aims to learn a model from multiple source domains to achieve satisfactory performance on unseen target domains. Recent works introduce CLIP to DG tasks…
SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training
Gengwei Zhang, Liyuan Wang, Guoliang Kang +2
In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trai…
VISA: Reasoning Video Object Segmentation via Large Language Models
Cilin Yan, Haochen Wang, Shilin Yan +5
Existing Video Object Segmentation (VOS) relies on explicit user instructions, such as categories, masks, or short phrases, restricting their ability to perform complex video segme…
Mining Open Semantics from CLIP: A Relation Transition Perspective for Few-Shot Learning
Cilin Yan, Haochen Wang, Xiaolong Jiang +4
Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in…
LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation
Yuxiang Bao, Di Qiu, Guoliang Kang +4
Leveraging the generative ability of image diffusion models offers great potential for zero-shot video-to-video translation. The key lies in how to maintain temporal consistency ac…