AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

Mehdi Noroozi, Paolo Favaro

ECCV 2016 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 2,820 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 a random gap between tiles (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 47.7 -> 52.6Improved
add per-patch mean/std normalization (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 43.5 -> 52.6Improved
add color channel jittering (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 51.1 -> 52.6Improved
remove the gap shortcut guard: jigsaw task becomes easier (ablation)CFN Jigsaw · Jigsaw task accuracyaccuracy: 88 -> 98Mixed
raise average Hamming distance of permutation set from 3.99 to 8.00 (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 50.2 -> 53.2Improved
raise average Hamming distance of permutation set from 6.35 to 8.00 (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 51.3 -> 53.2Improved
use 1000 permutations instead of 10 (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 49.2 -> 53.2Improved
use 1000 permutations instead of 6 (easier, unambiguous task) (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 49.7 -> 53.2Improved
raise minimum Hamming distance from 2 to 5 with 71 permutations (ablation)CFN Jigsaw · PASCAL VOC 2007 detection (Jigsaw ablation)mAP: 52.6 -> 52.8No clear effect
use Jigsaw CFN pretraining instead of context prediction by Pathak et al.AlexNet · PASCAL VOC 2007 detectionmAP: 44.5 -> 53.2Improved
use Jigsaw CFN pretraining instead of Doersch et al.AlexNet · PASCAL VOC 2007 detectionmAP: 46.6 -> 53.2Improved
use Jigsaw CFN pretraining instead of Pathak et al.AlexNet · PASCAL VOC 2012 segmentationmIoU: 29.7 -> 37.6Improved

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