AI Paper Atlas

Research map / Benchmarks / STL-10

STL-10 leaderboard

129 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on STL-10. Best accuracy: 99.8 (SURM (Circulant), NeurIPS 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.

STL-10 · accuracy

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

#accuracy ↑MethodPaperTopic
199.8SURM (Circulant)
ViT-B/16
Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
NeurIPS 2024 · ViT-experiments table
Pruning and efficient tuning
299.6Imagen
Imagen
Text-to-Image Diffusion Models are Zero Shot Classifiers
NeurIPS 2023 · Image classification results t
CLIP and zero-shot
399.3SEIC
CLIP ViT-B/16
Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency
AAAI 2026 · Table 1
Cross-modal learning
499.02IICMVNCD (Ours)Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery
ICCV 2025 · Table 2
Clustering
599SATC
CLIP ViT-B/32
Spatial Structure and Selective Text Jointly Facilitate Image Clustering
ICLR 2026 · Table 1
Human and embodied modeling
698.7CLUDI (ViT-B/16)
DINO ViT-B/16
Clustering via Self-Supervised Diffusion
ICML 2025 · Table 1
Self-supervised and contrastive
798.7MoE Jetpack (ConvNeXt-F)
ConvNeXt-T, ImageNet-21k
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
NeurIPS 2024 · Table: Performance comparison
Mixture of experts
898.6LP-FT + VRF
CLIP ViT-B/16
Robust Fine-tuning of Zero-shot Models via Variance Reduction
NeurIPS 2024 · Table: Accuracy of various met
Zero-/few-shot and meta-learning
998.4MAGIC*
CLIP ViT-B/32
MAGIC: Multi-Granularity Language-Informed Image Clustering
ICML 2026 · Table 2
Cross-modal learning
1098.3Ours (NTK spectral clustering)
CLIP ViT-B/32
Delving into Spectral Clustering with Vision-Language Representations
ICLR 2026 · Table 1
Cross-modal learning
91 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

STL-10 · FID

23 papers, each with its best reported number for its own method; lower is better.

13 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

STL-10 · IS

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

1 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

STL-10 · NMI

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

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