Computer Vision and Machine Learning at MPI Informatics
cvml.mpi-inf.mpg.de
Computer Vision and Machine Department at the Max Planck Institute for Informatics | https://www.mpi-inf.mpg.de/departments/computer-vision-and-machine-learning/
👤 Joined on 12 March 2025
113
Followers
39
Following
51
Total Posts
📜 Kullanıcı Geçmişi
- 12 Mar 2025, 15:18
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@cvml.bsky.social - 13 Mar 2025, 10:05
✏️ Kullanıcı adı değişti:
@cvml.bsky.social→@cvml.mpi-inf.mpg.de
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
🚀New preprint: DAVE — Distribution-aware Attribution via ViT Gradient DEcomposition. 1/11 🔍 What’s new: We fix a persistent issue in ViT explainability: unstable, artifact-heavy pixel attributions. DAVE yields fine-grained pixel-level maps without patch-grid saliency.
Show Post
As poster sessions wrap up in Mexico City, we're grateful for the incredible research shared and connections made. Thank you to everyone who made our CDMX venue such a vibrant part of NeurIPS 2025! 🇲🇽 #NeurIPS2025 #NeurIPSCDMX
Show Post
ICCV 2025 kicks off tomorrow! We look forward to welcoming everyone to Hawaii 🌺
Show Post
Are you using DINOv2 for tasks that require semantic features? DIY-SC might be the alternative! It refines DINOv2 or SD+DINOv2 features and achieves a new SOTA on the semantic correspondence dataset SPair-71k when not relying on annotated keypoints! [1/6] genintel.github.io/DIY-SC
Show Post
Super excited to introduce ✨ AnyUp: Universal Feature Upsampling 🔎 Upsample any feature - really any feature - with the same upsampler, no need for cumbersome retraining. SOTA feature upsampling results while being feature-agnostic at inference time. 🌐 wimmerth.github.io/anyup/
Show Post