AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Roadblocks for Temporarily Disabling Shortcuts and Learning New Knowledge

Hongjing Niu, Hanting Li, Feng Zhao, Bin Li

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Roadblocks instead of LDDdebiasing model · CMNIST 0.5% minorityaccuracy: 65.22 -> 66.64Improved
use Roadblocks instead of LDDdebiasing model · CMNIST 1.0% minorityaccuracy: 81.73 -> 82.04Improved
use Roadblocks instead of LDDdebiasing model · CMNIST 2.0% minorityaccuracy: 84.79 -> 84.93No clear effect
use Roadblocks instead of LDDdebiasing model · CMNIST 5.0% minorityaccuracy: 89.66 -> 88.65Hurt
use Roadblocks instead of prior-based ReBiasdebiasing model · CMNIST (0.5% to 5.0% minority)accuracy: 70.47 -> 66.64 at 0.5%; 96.96 -> 88.65 at 5.0%Hurt
use Roadblocks instead of Vanilla trainingCNN · CMNIST 0.5% minorityaccuracy: 35.19 -> 66.64Improved
use Roadblocks instead of Vanilla trainingCNN · CMNIST 5.0% minorityaccuracy: 82.17 -> 88.65Improved
use Roadblocks instead of LDDdebiasing model · CelebA unbiased testaccuracy: 64.82 -> 79.73Improved
use Roadblocks instead of LDDdebiasing model · CelebA bias-conflicting testaccuracy: 47.63 -> 64.06Improved
use Roadblocks instead of LDDdebiasing model · BAR bias-conflicting testaccuracy: 63.50 -> 69.51Improved
use Roadblocks instead of EnDdebiasing model · CelebA unbiased testaccuracy: 75.93 -> 79.73Improved
use Roadblocks instead of Vanilla trainingCNN · CelebA bias-conflicting testaccuracy: 33.75 -> 64.06Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy