← authors · overview

• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
  2018 · 664 citations
• Generalisation in humans and deep neural networks
  2018 · 289 citations
• Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
  2019 · 137 citations
• Scaling Vision Transformers to 22 Billion Parameters
  2023 · 118 citations
• Comparing deep neural networks against humans: object recognition when the signal gets weaker
  2017 · 102 citations
• Partial success in closing the gap between human and machine vision
  2021 · 63 citations
• On the surprising similarities between supervised and self-supervised models
  2020 · 19 citations
• Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
  2023 · 16 citations
• The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks
  2022 · 1 citations
• Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?
  2023 · 1 citations
• LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
  2025
• Towards flexible perception with visual memory
  2024