Domain Generalization via Text-Anchored Information Bottleneck
Open paper
Benchmark
Model
Rank
Results
domain-generalization-on-office-home
Text-Anchored Information Bottleneck (Ours)
–
Average Accuracy: 93.2
domain-generalization-on-pacs
Text-Anchored Information Bottleneck (Ours)
–
Average Accuracy: 98.5
Rank counts only results with a code link.