AI Paper Atlas

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

Mitigating Negative Flips via Margin Preserving Training

Simone Ricci, Niccolò Biondi, Federico Pernici, Alberto Del Bimbo

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 2 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 margin-calibrating logit bias (with KL distillation) (ablation)MPT-KL · ImageNet-1k (ResNet-18 to ResNet-18)NFR (%): 8.09 -> 6.09Improved
add double-source focal distillation (with bias) (ablation)MPT · ImageNet-1k (ResNet-18 to ResNet-18)NFR (%): 7.71 -> 6.09Improved
add logit bias alone (no distillation) (ablation)cross-entropy training · ImageNet-1k (ResNet-18 to ResNet-18)ER on Yall (%): 32.88 -> 34.13Hurt
add logit bias alone (no distillation) (ablation)cross-entropy training · ImageNet-1k (ResNet-18 to ResNet-18)ER on Yold (%): 28.40 -> 26.23Improved
increase margin k on new classes (ablation)MPT · CIFAR100NFRImproved
use MPT-KL instead of ELODI ensemble of eight new modelsmodel update · ImageNet-1k (ResNet-18 to ResNet-18)NFR (%): 7.61 -> 6.09Improved
use MPT-LM instead of ELODImodel update · CIFAR100 (ResNet-18 to ResNet-50)NFR (%): 9.10 -> 9.42Hurt
apply MPT to pretrained ViT-B/32 classifier fine-tuningViT-B/32 · CIFAR100 (pretrained ViT-B/32, classifier fine-tuned)NFR (%): 7.08 -> 3.26Improved

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