AI Paper Atlas

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

A Stationary (and Therefore Compatible) Representation is All You Need

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

TPAMI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 1 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 higher-order contrastive term to the d-Simplex cross-entropy (HOC vs FD)d-Simplex fixed classifier · CIFAR100/10 (CL2R, 31 tasks)ACA: 15.37 -> 23.44Improved
use d-Simplex-HOC instead of d-Simplex-FDd-Simplex · CUB180/20 (CL2R, 31 tasks)ACA: 21.97 -> 25.46Improved
use d-Simplex-HOC instead of d-Simplex-FDd-Simplex · TinyImageNet200/20 (CL2R, 31 tasks)ACA: 0.44 -> 25.14Improved
use d-Simplex-HOC instead of CVSfine-tuning with replay · CIFAR100/10 (CL2R, 31 tasks)ACA: 2.928 -> 23.44Improved
use d-Simplex-HOC instead of d-Simplex-FD under two model replacementsd-Simplex · CIFAR100R/10 (IAM-CL2R, 7 tasks, two model replacements)AA: 56.581 -> 68.13Improved
use d-Simplex-HOC instead of d-Simplex-FD under two model replacementsd-Simplex · CIFAR100R/10 (IAM-CL2R, 31 tasks, two model replacements)AA: 56.267 -> 67.40Improved
use d-Simplex-HOC instead of d-Simplex-FD with changing architecturesd-Simplex · CIFAR100R/10 (IAM-CL2R, 31 tasks, architecture change, AA at task 21)AA: 56.88 -> 67.28Improved
set lambda to 0.1 rather than 0 (contrastive only) (ablation)d-Simplex-HOC · CIFAR100/10 (CL2R, 16 tasks)ACA: 40.706 -> 43.20Improved
set lambda to 0.1 rather than 1 (cross-entropy only) (ablation)d-Simplex-HOC · CIFAR100/10 (CL2R, 16 tasks)ACA: 0 -> 43.20Improved
raise rho from 0.1 to 5 (ablation)d-Simplex-HOC · CIFAR100/10 (CL2R, 16 tasks)ACA: 8.367 -> 43.20Improved
raise rho from 5 to 25 (ablation)d-Simplex-HOC · CIFAR100/10 (CL2R, 16 tasks)ACA: 43.20 -> 26.195Hurt
vary number of pre-allocated classes K from 100 to 10,000 (ablation)d-Simplex-HOC · CIFAR100/10 (CL2R, 16 tasks)ACA: 43.199 -> 45.46No clear effect

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