The first project: *SLACK: Stable Learning of Augmentations with Cold-start and KL regularization* presented at #CVPR2023 lead to a new automatic data augmentation method arxiv.org/abs/2306.09998
11/
- both @SpyrosGidaris & I had very short time between #eccv2022 & #cvpr2023 deadline
- we had main results ready & made a strong push for the submission and
…
we’re in the 2020s: non-polished works w/o bold numbers across the board have little chance to pass through 😅
Fake it till you make it 🦄 - training visual representations from a synthetic clone of ImageNet - #CVPR2023
Paper: arxiv.org/abs/2212.08420
Project page: europe.naverlabs.com/imagenet-sd/
🌟 Previewing the UniAD 2.0
🚀 A milestone upgrade on the codebase of the #CVPR2023 best paper UniAD.
👉 Check out this branch github.com/OpenDriveLab..., and we will get you more details soon
Reposting some of my prior works here on this site :) "Semidefinite Relaxations for Robust Multiview Triangulation" at #CVPR2023!
paper: arxiv.org/abs/2301.11431
code: github.com/Linusnie/rob...
Does continual learning change when there is repetition in the data stream?
The report of the #CVPR2023 CLVision challenge on **Continual learning in the presence of repetition** is out in Neural Networks. #OpenAccess
www.sciencedirect.com/science/arti...
We had so much fun at #CVPR2023 constructing ✂️ and presenting that poster 😄
Full credit of the idea to @skamalas.bsky.social
It will be recorded only for internal use by the students I think.
There is some overlap with the MDEC talk but that one focussed very much on #MapFreeReloc and mentions scene coordinate regression (SCR) only on the side.
My last tutorial at #CVPR2023 had more on SCR:
youtu.be/7iRBMWPd7Bc?...