AI Paper Atlas

Research map / Benchmarks / ImageNet-Sketch

ImageNet-Sketch leaderboard

61 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet-Sketch. Best accuracy: 68 (JFT memory, 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.

ImageNet-Sketch · accuracy

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

#accuracy ↑MethodPaperTopic
168JFT memory
DinoV2 ViT-L14
Towards flexible perception with visual memory
ICML 2025 · Table: OOD evaluation
Human and embodied modeling
261.4ViT-L MVT +FT
CLIP ViT-L
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
ICML 2024 · Table 1
Multimodal LLMs
359.97Transductive Priming
OpenCLIP ViT-B-16, LAION-2B
Neural Priming for Sample-Efficient Adaptation
NeurIPS 2023 · Transductive results table
Test-time adaptation
457.9SATA-B*
ViT-Base/16
SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
CVPR 2025 · Table 1
Attention and transformers
553.4Ours (single-fill)
CLIP ViT-B/16
Masked Images Are Counterfactual Samples for Robust Fine-Tuning
CVPR 2023 · Comparison with Existing Appro
OOD and anomaly detection
653.3MGTTA
ViT-Base
Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers
AAAI 2025 · Table: Comparisons with state-
Test-time adaptation
753.2DMN-ZS
CLIP ViT-B/16
Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
CVPR 2024 · Table 4
CLIP and zero-shot
853DeYO + CONGA
ViT-Base
CONGA:Confidence-and-Gradient-Aware Learning Rate Schedule for Test Time Adaptation
ICML 2026 · Table 4
Test-time adaptation
951.65SCAP
CLIP ViT-B/16
SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
CVPR 2025 · Table 1
CLIP and zero-shot
1051.15SONO
CLIP ViT-B/16
Cross-Modal Few-Shot Learning with Second-Order Neural Ordinary Differential Equations
AAAI 2025 · Table: domain generalization
CLIP and zero-shot
51 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.