AI Paper Atlas

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

Multi-Task Self-Supervised Visual Learning

Carl Doersch, Andrew Zisserman

ICCV 2017 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 639 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
add colorization to relative positionRP · ImageNet frozen (top-5 recall)recall@5: 59.21 -> 66.64Improved
add exemplar to relative positionRP · ImageNet frozen (top-5 recall)recall@5: 59.21 -> 65.24Improved
add motion segmentation to relative positionRP · ImageNet frozen (top-5 recall)recall@5: 59.21 -> 63.73Improved
add colorization, exemplar and motion segmentation to relative positionRP · PASCAL VOC 2007 detectionmAP: 66.75 -> 70.53Improved
add exemplar to relative positionRP · NYU v2 depth% pixels below 1.25: 80.54 -> 78.70Hurt
add input harmonization (grayscale for relative position) (ablation)RP+Col · ImageNet frozen (top-5 recall)recall@5: 66.64 -> 68.08Improved
add input harmonization (grayscale for relative position) (ablation)RP+Col · PASCAL VOC 2007 detectionmAP: 68.75 -> 68.26No clear effect
add input harmonization (grayscale for relative position) (ablation)RP · ImageNet frozen (top-5 recall)recall@5: 59.21 -> 62.33Improved
add lasso at evaluation only (ablation)RP+Col+Ex+MS · ImageNet frozen (top-5 recall)recall@5: 69.30 -> 70.18Improved
add lasso at evaluation only (ablation)RP+Col+Ex+MS · PASCAL VOC 2007 detectionmAP: 70.53 -> 68.86Hurt
add lasso at pre-training only (ablation)RP+Col+Ex+MS · ImageNet frozen (top-5 recall)recall@5: 69.30 -> 68.09Hurt
add lasso at pre-training and evaluation (ablation)RP+Col+Ex+MS · ImageNet frozen (top-5 recall)recall@5: 69.30 -> 69.44No clear effect

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