Skip to yearly menu bar Skip to main content


Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Zeyi Sun · Ye Fang · Tong Wu · Pan Zhang · Yuhang Zang · Shu Kong · Yuanjun Xiong · Dahua Lin · Jiaqi Wang

Arch 4A-E Poster #327
[ ] [ Project Page ]
Thu 20 Jun 10:30 a.m. PDT — noon PDT


Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the details, even those irrelevant to specific tasks. However, for a finer understanding and controlled editing of images, it becomes crucial to focus on specific regions of interest, which can be indicated as points, masks, or boxes by humans or perception models. To fulfill the requirements, we introduce Alpha-CLIP, an enhanced version of CLIP with an auxiliary alpha channel to suggest attentive regions and fine-tuned with constructed millions of RGBA region-text pairs. Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents. It demonstrates effectiveness in various tasks, including but not limited to open-world recognition, multimodal large language models, and conditional 2D / 3D generation. It has a strong potential to serve as a versatile tool for image-related tasks. All the code, models, and training data will be publicly available.

Live content is unavailable. Log in and register to view live content