arXiv preprint arXiv:2112.10740 , year=

representative citing papers

citing papers explorer

Showing 5 of 5 citing papers.

• Towards Understanding Self-Pretraining for Sequence Classification cs.LG · 2026-05-20 · unverdicted · none · ref 145

  Self-pretraining improves Transformer sequence classification by enabling learning of proximity-biased attention from positional encodings that label supervision alone cannot easily acquire from random starts.

• Revisiting Feature Prediction for Learning Visual Representations from Video cs.CV · 2024-02-15 · conditional · none · ref 77

  V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.

• Vision Transformers Need Registers cs.CV · 2023-09-28 · unverdicted · none · ref 51

  Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.

• Self-Supervised Learning for Real-World Object Detection: a Survey cs.CV · 2024-10-09 · unverdicted · none · ref 64

  Survey benchmarks SSL instance discrimination and masked image modeling for object detection, finding instance discrimination suits CNN encoders while MIM suits ViT encoders and custom pre-training, especially for small objects.

• DINOv2: Learning Robust Visual Features without Supervision cs.CV · 2023-04-14 · unverdicted · none · ref 9

  Pith review generated a malformed one-line summary.