Haiwen Huang
@haiwen-huang.bsky.social
PhD student in AI at University of Tuebingen.
Dreaming for a better world.
https://andrehuang.github.io/
Dreaming for a better world.
https://andrehuang.github.io/
Sharing another video showing how LoftUp significantly improves DINOv2 features! Works like a charm!
Try it out:
Code: github.com/andrehuang/l...
Paper: arxiv.org/abs/2504.14032
Try it out:
Code: github.com/andrehuang/l...
Paper: arxiv.org/abs/2504.14032
April 26, 2025 at 7:52 AM
Sharing another video showing how LoftUp significantly improves DINOv2 features! Works like a charm!
Try it out:
Code: github.com/andrehuang/l...
Paper: arxiv.org/abs/2504.14032
Try it out:
Code: github.com/andrehuang/l...
Paper: arxiv.org/abs/2504.14032
Excited to introduce LoftUp!
A strong (than ever) and lightweight feature upsampler for vision encoders that can boost performance on dense prediction tasks by 20%–100%!
Easy to plug into models like DINOv2, CLIP, SigLIP — simple design, big gains. Try it out!
github.com/andrehuang/l...
A strong (than ever) and lightweight feature upsampler for vision encoders that can boost performance on dense prediction tasks by 20%–100%!
Easy to plug into models like DINOv2, CLIP, SigLIP — simple design, big gains. Try it out!
github.com/andrehuang/l...
April 22, 2025 at 7:55 AM
Excited to introduce LoftUp!
A strong (than ever) and lightweight feature upsampler for vision encoders that can boost performance on dense prediction tasks by 20%–100%!
Easy to plug into models like DINOv2, CLIP, SigLIP — simple design, big gains. Try it out!
github.com/andrehuang/l...
A strong (than ever) and lightweight feature upsampler for vision encoders that can boost performance on dense prediction tasks by 20%–100%!
Easy to plug into models like DINOv2, CLIP, SigLIP — simple design, big gains. Try it out!
github.com/andrehuang/l...