ImageNet-Segmentation

Findings

• IC-447CLIP ViT-B/16 produces noisy saliency maps and contains only 42 concept detectors, indicating poor visual interpretability [eval]
• IC-450LLaVA with the original CLIP encoder produces noisy, non-sparse attention maps that poorly localize to the objects described in generated text [eval]
• IC-680CLIP ViT's image token contributions are spatially localized to match described content, enabling zero-shot segmentation that outperforms existing CLIP-based methods [eval]