Support-Set Context Matters for Bongard Problems
Open paper
Benchmark
Model
Rank
Results
few-shot-image-classification-on-bongard-hoi
SVM-Mimic + PMF (fine-tuned CLIP RN-50)
#2
Avg. Accuracy: 76.41
few-shot-image-classification-on-bongard-hoi
SVM-Mimic (frozen CLIP RN-50)
#3
Avg. Accuracy: 72.45
Rank counts only results with a code link.