Waterbirds

anchor

Findings

• IC-1016ImageNet-pretrained ResNet-50 backbone exhibits shortcut bias toward background features when adapted to bird classification via a new readout layer [eval]
• IC-1099AdamW-pretrained vision models (ViTs, ConvNeXt) have disproportionately large embedding-layer gradients at initialization, causing SGD fine-tuning to degrade OOD accuracy by up to 15% relative to AdamW [eval]
• IC-1520OpenCLIP's per-sample zero-shot accuracy on ImageNet-based OOD benchmarks is strongly correlated with the perceptual similarity between that sample and its nearest neighbor in LAION-400M [eval]
• IC-644CLIP relies on spurious features (background) as a shortcut in zero-shot classification, and conditioning on the correct background reduces this reliance [eval]
• IC-679CLIP relies on background/location as a spurious cue for bird classification, and ablating geolocation heads improves worst-group accuracy by 25.2% [eval]
• IC-742ResNet-50-BN on Waterbirds relies on background as a spurious feature for classification, and this shortcut is invisible to entropy-based confidence metrics [eval]
• IC-835CLIP zero-shot predictions exhibit large worst-group accuracy gaps due to spurious correlations on Waterbirds and CelebA [eval]
• IC-837CLIP ViT-L/14 embeds more target-attribute information and less sensitive-attribute information than CLIP ResNet-50 on Waterbirds [eval]