pith. sign in

In: ICCV (2023)

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Metonymy in vision models undermines attention-based interpretability

cs.CV · 2026-05-07 · unverdicted · novelty 6.0

Pretrained vision transformers exhibit strong intra-object leakage where each part representation encodes information from the entire object, undermining the faithfulness of attention-based part-centric interpretability methods.

Dual-Foundation Models for Unsupervised Domain Adaptation

cs.CV · 2026-05-05 · unverdicted · novelty 5.0

Dual use of SAM for broader target pixel learning and DINOv3 for domain-invariant prototypes yields +1.3% and +1.4% mIoU gains over baselines on GTA-to-Cityscapes and SYNTHIA-to-Cityscapes.

citing papers explorer

Showing 2 of 2 citing papers.

  • Metonymy in vision models undermines attention-based interpretability cs.CV · 2026-05-07 · unverdicted · none · ref 26

    Pretrained vision transformers exhibit strong intra-object leakage where each part representation encodes information from the entire object, undermining the faithfulness of attention-based part-centric interpretability methods.

  • Dual-Foundation Models for Unsupervised Domain Adaptation cs.CV · 2026-05-05 · unverdicted · none · ref 23

    Dual use of SAM for broader target pixel learning and DINOv3 for domain-invariant prototypes yields +1.3% and +1.4% mIoU gains over baselines on GTA-to-Cityscapes and SYNTHIA-to-Cityscapes.