AI Paper Atlas

Research map / Benchmarks / 11-dataset average, 16-shot

11-dataset average, 16-shot leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on 11-dataset average, 16-shot. Best accuracy: 87.6 (ImagineFSLLoRA, CVPR 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.

11-dataset average, 16-shot · accuracy

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

#accuracy ↑MethodPaperTopic
187.6ImagineFSLLoRA
CLIP ViT-B/16
ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning
CVPR 2025 · Table 2
Self-supervised and contrastive
286.85MPS-Tuning
CLIP ViT-B/16
Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning
ICLR 2026 · Table 7
CLIP and zero-shot
385.3DeMul
CLIP ViT-B/16
Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation
ICLR 2025 · Appendix, Main results detail
CLIP and zero-shot
484.4GalLoP
CLIP ViT-B/16
GalLop: Learning global and local prompts for vision-language models
ECCV 2024 · Table 1
OOD and anomaly detection
582.3TOGA
CLIP ViT-B/16
Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
CVPR 2026 · Table 1
CLIP and zero-shot
681.25VRGAdapter
CLIP RN50
Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter
CVPR 2026 · Table 2
Graph self-supervised learning
781.13LAMM
ViT-B/16 CLIP
LAMM: Label Alignment for Multi-Modal Prompt Learning
AAAI 2024 · Hierarchical loss ablation tab
CLIP and zero-shot
880.61BOIF (Ours)
CLIP ResNet-50
Bayes-inspired Integration of Pretrained Priors and Few-Shot Evidence for Few-Shot Classification
ICML 2026 · Table 1
Zero-/few-shot and meta-learning
980.28PiNI
CLIP ViT-B/16
Enhance Vision-Language Alignment with Noise
AAAI 2025 · Table: The performance average
CLIP and zero-shot
1079.78LDC
ResNet-50
Logits DeConfusion with CLIP for Few-Shot Learning
CVPR 2025 · Table 2
Zero-/few-shot and meta-learning
3 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.