87 citations · 305 across the 28 of their papers we have counts for
36 papers · 1 filter
Revisiting the Integration of Convolution and Attention for Vision Backbone
Lei Zhu, Xinjiang Wang, Wayne Zhang +1
Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate…
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
Mengcheng Lan, Chaofeng Chen, Yiping Ke +3
Open-vocabulary semantic segmentation requires models to effectively integrate visual representations with open-vocabulary semantic labels. While Contrastive Language-Image Pre-tra…
ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
Mengcheng Lan, Chaofeng Chen, Yiping Ke +3
Despite the success of large-scale pretrained Vision-Language Models (VLMs) especially CLIP in various open-vocabulary tasks, their application to semantic segmentation remains cha…
Panoptic Video Scene Graph Generation
Jingkang Yang, Wenxuan Peng, Xiangtai Li +8
Towards building comprehensive real-world visual perception systems, we propose and study a new problem called panoptic scene graph generation (PVSG). PVSG relates to the existing…
SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
Mengcheng Lan, Xinjiang Wang, Yiping Ke +3
Unsupervised semantic segmentation is a challenging task that segments images into semantic groups without manual annotation. Prior works have primarily focused on leveraging prior…
Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Yijiang Li, Xinjiang Wang, Lihe Yang +3
Deep co-training has been introduced to semi-supervised segmentation and achieves impressive results, yet few studies have explored the working mechanism behind it. In this work, w…