5 papers
Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
Xiaoxiao Ma, Feng Zhao, Pengyang Ling +6
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower informat…
CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation
Ziyang Gong, Zhixiang Wei, Di Wang +13
The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across…
Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models
Zhixiang Wei, Xiaoxiao Ma, Ruishen Yan +5
Vision Foundation Models(VFMs) have achieved remarkable success in various computer vision tasks. However, their application to semantic segmentation is hindered by two significant…
HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models
Zhixiang Wei, Guangting Wang, Xiaoxiao Ma +4
Large-scale but noisy image-text pair data have paved the way for the success of Contrastive Language-Image Pretraining (CLIP). As the foundation vision encoder, CLIP in turn serve…
Masked Pre-training Enables Universal Zero-shot Denoiser
Xiaoxiao Ma, Zhixiang Wei, Yi Jin +5
In this work, we observe that model trained on vast general images via masking strategy, has been naturally embedded with their distribution knowledge, thus spontaneously attains t…