7 papers · 1 filter
Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
Kaixin Ding, Yang Zhou, Xi Chen +5
Recent advances in Text-to-Image (T2I) generative models, such as Imagen, Stable Diffusion, and FLUX, have led to remarkable improvements in visual quality. However, their performa…
Seg-VAR: Image Segmentation with Visual Autoregressive Modeling
Rongkun Zheng, Lu Qi, Xi Chen +3
While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires pre…
FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
Xi Chen, Hengshuang Zhao
Interactive segmentation enables users to extract binary masks of target objects through simple interactions such as clicks, scribbles, and boxes. However, existing methods often s…
DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data
Yuanpeng Tu, Xi Chen, Ser-Nam Lim +1
Open-vocabulary panoptic segmentation has received significant attention due to its applicability in the real world. Despite claims of robust generalization, we find that the advan…
ViLLa: Video Reasoning Segmentation with Large Language Model
Rongkun Zheng, Lu Qi, Xi Chen +4
Recent efforts in video reasoning segmentation (VRS) integrate large language models (LLMs) with perception models to localize and track objects via textual instructions, achieving…
Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation
Mingkang Zhu, Xi Chen, Zhongdao Wang +3
Recent diffusion model customization has shown impressive results in incorporating subject or style concepts with a handful of images. However, the modular composition of multiple…