papers

Publications (36)

cs.CV2024

Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners

Mushui Liu, Bozheng Li, Yunlong Yu

Prompt tuning, which involves training a small set of parameters, effectively enhances the pre-trained Vision-Language Models (VLMs) to downstream tasks. However, they often come a…

cs.CV2024

RestorerID: Towards Tuning-Free Face Restoration with ID Preservation

Jiacheng Ying, Mushui Liu, Zhe Wu +7

Blind face restoration has made great progress in producing high-quality and lifelike images. Yet it remains challenging to preserve the ID information especially when the degradat…

cs.CV2024

Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning

Mushui Liu, Fangtai Wu, Bozheng Li +3

Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited vi…

cs.CV2024

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition

Bozheng Li, Mushui Liu, Gaoang Wang +1

In this paper, we propose a novel Temporal Sequence-Aware Model (TSAM) for few-shot action recognition (FSAR), which incorporates a sequential perceiver adapter into the pre-traini…

cs.CV2018

Zero-Shot Learning via Latent Space Encoding

Yunlong Yu, Zhong Ji, Jichang Guo +2

Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common…

cs.CV2024

LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation

Mushui Liu, Yuhang Ma, Yang Zhen +6

Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving mult…