149 citations · 181 across the 11 of their papers we have counts for
11 papers
TouchStone: Evaluating Vision-Language Models by Language Models
Shuai Bai, Shusheng Yang, Jinze Bai +6
Large vision-language models (LVLMs) have recently witnessed rapid advancements, exhibiting a remarkable capacity for perceiving, understanding, and processing visual information b…
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Jinze Bai, Shuai Bai, Shusheng Yang +6
In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images. Starting from the Qwen…
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
Jingfeng Yao, Xinggang Wang, Shusheng Yang +1
Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining.…
MobileInst: Video Instance Segmentation on the Mobile
Renhong Zhang, Tianheng Cheng, Shusheng Yang +8
Video instance segmentation on mobile devices is an important yet very challenging edge AI problem. It mainly suffers from (1) heavy computation and memory costs for frame-by-frame…
RILS: Masked Visual Reconstruction in Language Semantic Space
Shusheng Yang, Yixiao Ge, Kun Yi +4
Both masked image modeling (MIM) and natural language supervision have facilitated the progress of transferable visual pre-training. In this work, we seek the synergy between two p…
Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection
Yuxin Fang, Shusheng Yang, Shijie Wang +3
We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our t…
Masked Image Modeling with Denoising Contrast
Kun Yi, Yixiao Ge, Xiaotong Li +5
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, tha…
Temporally Efficient Vision Transformer for Video Instance Segmentation
Shusheng Yang, Xinggang Wang, Yu Li +5
Recently vision transformer has achieved tremendous success on image-level visual recognition tasks. To effectively and efficiently model the crucial temporal information within a…
Relational Surrogate Loss Learning
Tao Huang, Zekang Li, Hua Lu +6
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. Thi…
Tracking Instances as Queries
Shusheng Yang, Yuxin Fang, Xinggang Wang +4
Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object…
Crossover Learning for Fast Online Video Instance Segmentation
Shusheng Yang, Yuxin Fang, Xinggang Wang +5
Modeling temporal visual context across frames is critical for video instance segmentation (VIS) and other video understanding tasks. In this paper, we propose a fast online VIS mo…