π Exciting News! Our research, "EXACT: How to train your accuracy", will be published in Pattern Recognition Letters (Q1)! π
A huge thanks to my co-authors, @stdereka and @Scitator!
Check out the [arXiv version](https://t.co/fLIHO9Efi5), or dive into the [journal version](https://t.co/RcLu3Kt39p) which includes new experiments with label noise and additional proofs.
In this paper, we introduce innovative techniques for training with highly non-convex loss functions, significantly boosting model accuracy in both tabular datasets and computer vision.
1/7 Deep ensembles deliver exceptional results in uncertainty estimation (@balajiln) and OOD detection (@SharonYixuanLi). But how can we push their performance even further? Our latest paper, accepted at @ieeeICIP#ICIP2024, uses saliency maps to enhance ensemble diversity. π§΅π
In our new paper π we optimize accuracy via gradient descent! The work, called "EXACT: How to Train Your Accuracy", will be presented at the TAG-ML workshop during #ICML2022 π
Paper: https://t.co/a3krceFB3r
Poster: https://t.co/ZrqdJtmrTY
Enjoy!)