AI Paper Atlas

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

AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors

Vito Paolo Pastore, Massimiliano Ciranni, Enzo Tartaglione, Vittorio Murino

ECCV 2026 · 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
add the surprisal weight w_surprisal to the monitor-loss weight (ablation)AracNet · Waterbirds (ResNet50)worst-group accuracy: 88.78 -> 91.27Improved
add the monitor-loss weight w_l* to the surprisal weight (ablation)AracNet · Waterbirds (ResNet50)worst-group accuracy: 84.94 -> 91.27Improved
set surprisal exponent lambda to 2 rather than 1, 3, 4 or 5 (ablation)AracNet · Waterbirds (ResNet50)worst-group accuracy: 84.47 (lambda 5) -> 91.27 (lambda 2)Improved
pretrain biased backbone for 200 epochs instead of 50 (ablation)AracNet · Waterbirds (ResNet50)worst-group accuracy: 91.27 -> 90.85No clear effect
use monitor from a ResNet18 backbone to debias ResNet50 or ViT-S/16 (ablation)AracNet · Waterbirdsworst-group accuracy: 91.27 -> 91.06 (ResNet50); 90.68 (ViT-S/16)No clear effect
apply AracNet to ViT-S/16 with a monitor per blockViT-S/16 · Waterbirdsworst-group accuracy: 67.69 -> 90.66Improved
AracNet versus DeNetDM on Corrupted CIFAR-10 at highest biasCorrupted CIFAR-10 (rho=0.995) · Corrupted CIFAR-10 (rho=0.995)accuracy: 38.93 (DeNetDM) vs 33.23Hurt
AracNet versus best baselines at low bias on Corrupted CIFAR-10Corrupted CIFAR-10 (rho=0.950) · Corrupted CIFAR-10 (rho=0.950)accuracy: 56.30 -> 56.80Improved
AracNet versus DDB on UrbanCarsUrbanCars · UrbanCarsI.D. accuracy: I.D. 86.39 (DDB) vs 85.95; BG-CoObj gap 0.12 vs 0.35Mixed
AracNet versus LoYS on BAR (rho=0.990)BAR · BAR (rho=0.990)accuracy: 75.92 -> 76.22Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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