AI Paper Atlas

Research map / Benchmarks / CIFAR-10-LT IF=100

CIFAR-10-LT IF=100 leaderboard

21 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-10-LT IF=100. Best accuracy: 92.33 (GLMC + SCoRe-FL, ICML 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

CIFAR-10-LT IF=100 · accuracy

21 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
192.33GLMC + SCoRe-FL
GLMC
SCoRe: Submodular Combinatorial Representation Learning
ICML 2024 · Table 1
Recognition and long-tail
290.08BCE3SBCE3S: Binary Cross-Entropy Based Tripartite Synergistic Learning for Long-Tailed Recognition
AAAI 2026 · Table 3
Recognition and long-tail
390VICAL
ResNet-32
VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
ECCV 2026 · Table 1
Recognition and long-tail
489.1GLMC+Loss+LR (Ours)Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
ICML 2026 · Table 2
Recognition and long-tail
588.9GLMC+SpAProj
ResNet-32
Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning
AAAI 2026 · Table 1
Recognition and long-tail
688.5GLMC + SAMN
ResNet32
Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition
CVPR 2026 · Table 1
Recognition and long-tail
787.8LGLA
ResNet-32
Local and Global Logit Adjustments for Long-Tailed Learning
ICCV 2023 · Table 1
Recognition and long-tail
887.75GLMC
ResNet-32
Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions
CVPR 2023 · Table: CIFAR-10-LT and CIFAR-1
Recognition and long-tail
986.93SURE + re-weighting
ResNet-32
SURE: SUrvey REcipes for building reliable and robust deep networks
CVPR 2024 · Table 2
Noisy labels
1086.8TCL
ResNet-32
Trust-calibrated Collaborative Learning for Long-Tailed Visual Recognition
CVPR 2026 · Table 2
Recognition and long-tail
11 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.