AI Paper Atlas

Research map / Benchmarks / 10-Split CIFAR-100

10-Split CIFAR-100 leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on 10-Split CIFAR-100. Best accuracy: 81.66 (Adam-NSCL + BECAME, ICML 2025).

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.

10-Split CIFAR-100 · accuracy

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

#accuracy ↑MethodPaperTopic
181.66Adam-NSCL + BECAME
Adam-NSCL
BECAME: Bayesian Continual Learning with Adaptive Model Merging
ICML 2025 · NSCL-based performance compari
Online and replay-based
279.79Linear Connector (Ours)
ResNet-18
Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector
CVPR 2022 · Table: Results on 10-split-CIF
Online and replay-based
379.54MSCN
SNN
Multi-Synaptic Cooperation: A Bio-Inspired Framework for Robust and Scalable Continual Learning
ICLR 2026 · Table 1
Online and replay-based
478.58HLOPHebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
ICLR 2024 · Table 3
Online and replay-based
577.21AdNS (Ours)
ResNet-18
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning
ECCV 2022 · Table 1
Online and replay-based
675.97Adam-NSCL+SD
Adam-NSCL
Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling
CVPR 2023 · Table 1
Online and replay-based
773.77Adam-NSCL
ResNet-18
Training Networks in Null Space of Feature Covariance for Continual Learning
CVPR 2021 · Table 1
Online and replay-based
872.48GPM
AlexNet-like
Gradient Projection Memory for Continual Learning
ICLR 2021 · Table 1(b)
Online and replay-based
970.78QGPMQuantized Gradient Projection for Memory-Efficient Continual Learning
ICLR 2026 · Table 1
Online and replay-based
1058.8BrainWash cautious, ϵ = 0.1
ResNet-18, EWC
BrainWash: A Poisoning Attack to Forget in Continual Learning
CVPR 2024 · Table 1
Online and replay-based

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