AI Paper Atlas

Research map / Video / Video segmentation and tracking

MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation

Roy Miles, Mehmet Kerim Yucel, Bruno Manganelli, Albert Saà-Garriga

CVPR 2023 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 37 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 logit distillation to cross-entropy (ablation)MobileVOS student · YouTube-VOS validationJ&F: 80.75 -> 81.38Improved
Add representation distillation alongside logit distillation (ablation)MobileVOS student · YouTube-VOS validationJ&F: 81.38 -> 82.28Improved
Use representation distillation rather than the ω=0 supervised-contrastive endpoint (ablation)MobileVOS ResNet18 · DAVIS 2017 validationJ&F: 83.1 -> 84.2Improved
Use supervised contrastive learning rather than the ω=1 distillation endpoint (ablation)MobileVOS ResNet18 · YouTube-VOS validationJ&F: 81.1 -> 82.3Improved
Add distillation (ablation)MobileVOS MobileNetV2 without ASPP · DAVIS 2016 validationJ&F: 89.2 -> 90.1Improved
Add distillation (ablation)MobileVOS MobileNetV2 without ASPP · DAVIS 2017 validationJ&F: 80.5 -> 81.8Improved
Remove ASPP (ablation)MobileVOS MobileNetV2 · DAVIS 2016 validationJ&F: 90.5 -> 90.1Hurt
Remove ASPP (ablation)MobileVOS MobileNetV2 · DAVIS 2017 validationJ&F: 82.2 -> 81.8Hurt
Remove ASPP (ablation)MobileVOS MobileNetV2 · YouTube-VOS 2019 validationOverall: 80.3 -> 80.1Mixed
Add poly loss (ablation)MobileNetV2 without ASPP, trained without distillation · DAVIS 2016 validationJ&F: 89.8 -> 89.8No clear effect
Add poly loss (ablation)MobileNetV2 without ASPP, trained without distillation · DAVIS 2017 validationJ&F: 79.9 -> 80.1No clear effect
Use boundary sampling instead of random pixel sampling (ablation)MobileVOS representation distillation · DAVIS 2016 validationJ&FImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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