AI Paper Atlas

Research map / Benchmarks / Caltech-256

Caltech-256 leaderboard

19 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Caltech-256. Best accuracy: 95.9 (TAFT-1, ICLR 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.

Caltech-256 · accuracy

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

#accuracy ↑MethodPaperTopic
195.9TAFT-1
ViT-L/16
Tangent Transformers for Composition,Privacy and Removal
ICLR 2024 · Table 1
Pruning and efficient tuning
293.9Deep Novelty
VGG16
Deep Transfer Learning for Multiple Class Novelty Detection
CVPR 2019 · Classification Accuracy
CNN features
393Asymmetric Duos
Swin-V2-S
Asymmetric Duos: Sidekicks Improve Uncertainty
NeurIPS 2025 · Table: Base-model-controlled c
Pruning and efficient tuning
487.92Robust ImageNet model, full-network
ImageNet classifier
Do Adversarially Robust ImageNet Models Transfer Better?
NeurIPS 2020 · Table: transfer performance
Recognition and long-tail
587OTTER
CLIP ViT-B/16
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
NeurIPS 2024 · Table 1
Zero-/few-shot and meta-learning
685.3VGG19+DPRC
VGG19
Discriminant Projection Representation-Based Classification for Vision Recognition
AAAI 2018 · Table: Caltech 256 object data
Recognition and long-tail
785.06InterActive (Last, p=2)
VGGNet
InterActive: Inter-Layer Activeness Propagation
CVPR 2016 · Table 2
CNN design
884.9REGSL
ResNet-101
Improved Regularization and Robustness for Fine-tuning in Neural Networks
NeurIPS 2021 · Table 2
Noisy labels
982.7Knockoff, adaptive (D²)
ResNet-34
Knockoff Nets: Stealing Functionality of Black-Box Models
CVPR 2019 · Table: Accuracy on test sets
Recognition and long-tail
1080.9MuCaLe-Net
VGG-16
MuCaLe-Net: Multi Categorical-Level Networks to Generate More Discriminating Features
CVPR 2017 · Table 4
Recognition and long-tail
9 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.