AI Paper Atlas

Research map / Benchmarks / FC100 5-way 5-shot

FC100 5-way 5-shot leaderboard

39 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on FC100 5-way 5-shot. Best accuracy: 88.81 (EfficientFSL, AAAI 2026).

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.

FC100 5-way 5-shot · accuracy

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

#accuracy ↑MethodPaperTopic
188.81EfficientFSL
ViT-B/16 (ImageNet-21K)
EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning In Vision Transformers
AAAI 2026 · Table 1
Pruning and efficient tuning
277.17F2SST
ViT-S/16
F2SST: Frequency-to-Spatial Semantic Transfer for Few-Shot Image Classification
AAAI 2026 · Table 2
Zero-/few-shot and meta-learning
368.68FeLMi
ResNet-12
FeLMi : Few shot Learning with hard Mixup
NeurIPS 2022 · Table 2
Zero-/few-shot and meta-learning
468.5SMKD (Classifier)
ViT-S
Supervised Masked Knowledge Distillation for Few-Shot Transformers
CVPR 2023 · Table: Results on CIFAR-FS and
Self-supervised and contrastive
568Label-Halluc (IER-distill pretrained)
ResNet-12
Label Hallucination for Few-Shot Classification
AAAI 2022 · Table 2
Zero-/few-shot and meta-learning
666.42Ours-Classifier
ViT-S/8
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-Shot Learning
CVPR 2022 · Table: FC100
Attention and transformers
765.3Ours-Distill
ResNet-12
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
CVPR 2021 · Table 2
Zero-/few-shot and meta-learning
865.02SemFew-Trans
Swin-T
Simple Semantic-Aided Few-Shot Learning
CVPR 2024 · Table 2
CLIP and zero-shot
965.02CPEA
ViT-S/16
Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification
ICCV 2023 · Table 2
Zero-/few-shot and meta-learning
1064.25TransVLAD
ViT-B (MAE)
TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning
ECCV 2022 · Table 2
Zero-/few-shot and meta-learning
29 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.