6 papers
VRP-SAM: SAM with Visual Reference Prompt
Yanpeng Sun, Jiahui Chen, Shan Zhang +7
In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmenta…
Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?
Zebin You, Xinyu Zhang, Hanzhong Guo +2
The ultimate goal of generative models is to perfectly capture the data distribution. For image generation, common metrics of visual quality (e.g., FID) and the perceived truthfuln…
Add-SD: Rational Generation without Manual Reference
Lingfeng Yang, Xinyu Zhang, Xiang Li +7
Diffusion models have exhibited remarkable prowess in visual generalization. Building on this success, we introduce an instruction-based object addition pipeline, named Add-SD, whi…
OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer
Yu Wang, Xiangbo Su, Qiang Chen +6
Open-vocabulary object detection focusing on detecting novel categories guided by natural language. In this report, we propose Open-Vocabulary Light-Weighted Detection Transformer…
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Mingxiang Liao, Hannan Lu, Xinyu Zhang +6
Comprehensive and constructive evaluation protocols play an important role in the development of sophisticated text-to-video (T2V) generation models. Existing evaluation protocols…
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
Qiang Chen, Xiangbo Su, Xinyu Zhang +12
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder…