ML Research Wiki / Benchmarks / Few-Shot Image Classification / Bongard-HOI

Bongard-HOI

Few-Shot Image Classification Benchmark

Performance Over Time

📊 Showing 9 results | 📏 Metric: Avg. Accuracy

Top Performing Models

Rank Model Paper Avg. Accuracy Date Code
1 Human (Amateur) Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions 91.42 2022-05-27 📦 nvlabs/bongard-hoi
2 GPT-4o + CA A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs 77.30 2025-01-23 -
3 SVM-Mimic + PMF (fine-tuned CLIP RN-50) 📚 Support-Set Context Matters for Bongard Problems 76.41 2023-09-07 📦 nraghuraman/bongard-context
4 Gemini 2.0 + CA A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs 74.50 2025-01-23 -
5 SVM-Mimic (frozen CLIP RN-50) 📚 Support-Set Context Matters for Bongard Problems 72.45 2023-09-07 📦 nraghuraman/bongard-context
6 Meta-Baseline (ImagNet_R50) Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions 55.82 2022-05-27 📦 nvlabs/bongard-hoi
7 Meta-Baseline (MoCov2_R50) Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions 54.30 2022-05-27 📦 nvlabs/bongard-hoi
8 Meta-Baseline (Scratch_R50) Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions 54.23 2022-05-27 📦 nvlabs/bongard-hoi
9 ANIL (ImageNet_R50) Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions 49.74 2022-05-27 📦 nvlabs/bongard-hoi

All Papers (9)

nvlabs/bongard-hoi

Support-Set Context Matters for Bongard Problems

2023
SVM-Mimic + PMF (fine-tuned CLIP RN-50)
nraghuraman/bongard-context

Support-Set Context Matters for Bongard Problems

2023
SVM-Mimic (frozen CLIP RN-50)
nraghuraman/bongard-context
nvlabs/bongard-hoi
nvlabs/bongard-hoi
nvlabs/bongard-hoi
nvlabs/bongard-hoi