xiaoachen98 / semantic-segment-anything

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Hi there 👋

• 🌱 I'm Lin Chen, a Ph.D. student in BIVLab, USTC.
• 🔭 I’m working as a research intern at Shanghai AI Laboratory.
• 💬 I'm currently looking for collaborations, feel free to contact me.

Research Projects

• 🔥 Large-scale high-quality video-text data and superior large video-language model: ShareGPT4Video.
• 🔥 An elite vision-indispensable multi-modal benchmark: MMStar.
• 🔥 Large-scale high-quality image-text data and superior large multi-modal model: ShareGPT4V.
• More Stable "Drag" Editing: FreeDrag
• Robust & Transferable Semantic Segmentation: DDB, DTP, Rein
• Discriminator-free Adversarial Domain Adaption: DALN