AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-Supervised AutoFlow

Hsin-Ping Huang, Charles Herrmann, Junhwa Hur, Erika Lu, Kyle Sargent, Austin Stone, Ming-Hsuan Yang, Deqing Sun

CVPR 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 7 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use self-supervised losses to search rendering parameters without target-domain flow labelsAutoFlow dataset generation · Sintel and KITTIAEPE: 7.63 -> 4.22Improved
Use self-supervised loss-guided rendering instead of supervised AutoFlowRAFT pre-training · Sintel CleanAEPE: 1.74 -> 1.83Hurt
Use self-supervised loss-guided rendering instead of supervised AutoFlowRAFT pre-training · Sintel FinalAEPE: 2.41 -> 2.59Hurt
Use self-supervised loss-guided rendering instead of supervised AutoFlowRAFT pre-training · KITTIAEPE: 4.18 -> 4.22Mixed
Add self-supervised fine-tuning after S-AF pre-trainingRAFT on Sintel · Sintel FinalAEPE: 2.57 -> 2.40Improved
Add self-supervised fine-tuning after S-AF pre-trainingRAFT on KITTI · KITTI 2015Fl-all (%): 13.60 -> 6.56Improved
Add photometric, smoothness, and distillation terms together to the search metric (ablation)Self-supervised AutoFlow · Sintel CleanAEPE: 2.30 -> 1.83Improved
Add photometric, smoothness, and distillation terms together to the search metric (ablation)Self-supervised AutoFlow · Sintel FinalAEPE: 2.98 -> 2.59Improved
Use a single self-supervised loss term instead of combining all three (ablation)Self-supervised AutoFlow · Sintel FinalAEPE: 2.59 vs 3.24, 2.84, and 3.04Hurt
Mix the top-3 searched datasets rather than selecting a single candidate (ablation)Self-supervised AutoFlow · KITTI 2015AEPE: 5.40 -> 4.58Mixed
Use intermediate RAFT predictions in the search metric instead of only the final prediction (ablation)Self-supervised AutoFlow search · Sintel FinalAEPEHurt
Use S-AF+SS initialization instead of SMURF for DAVIS segmentation trackingOptical-flow-based segmentation propagation · DAVISIoU: 0.876 -> 0.888Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy