activity
20172026
most citedRethinking Client Drift in Federated Learning: A Logit Perspective

6 citations · 54 across the 65 of their papers we have counts for

collaborators
Showing 2023 · cs.CVShow all

14 papers · 2 filters

cs.CV2023

Improving Image Restoration through Removing Degradations in Textual Representations

Jingbo Lin, Zhilu Zhang, Yuxiang Wei +3

In this paper, we introduce a new perspective for improving image restoration by removing degradation in the textual representations of a given degraded image. Intuitively, restora…

cs.CV2023

Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation

Zixian Guo, Yuxiang Wei, Ming Liu +4

Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very…

cs.CV2023★ 2 cited

VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering

Chun-Mei Feng, Yang Bai, Tao Luo +6

Albeit progress has been made in Composed Image Retrieval (CIR), we empirically find that a certain percentage of failure retrieval results are not consistent with their relative c…

cs.CV2023

Decoupled Textual Embeddings for Customized Image Generation

Yufei Cai, Yuxiang Wei, Zhilong Ji +3

Customized text-to-image generation, which aims to learn user-specified concepts with a few images, has drawn significant attention recently. However, existing methods usually suff…

cs.CV2023★ 1 cited

FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models

Wan Xu, Tianyu Huang, Tianyu Qu +3

Few-shot class-incremental learning (FSCIL) aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. However, many of these works l…

cs.CV2023★ 1 cited

DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

Tianyu Huang, Yihan Zeng, Zhilu Zhang +5

3D generation has raised great attention in recent years. With the success of text-to-image diffusion models, the 2D-lifting technique becomes a promising route to controllable 3D…