AI Paper Atlas

Research map / Video / Video segmentation and tracking

Exploring the Semi-Supervised Video Object Segmentation Problem from a Cyclic Perspective

Yuxi Li, Ning Xu, Wenjie Yang, John See, Weiyao Lin

IJCV 2022 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 5 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
add cycle-consistency training loss (ablation)STM ResNet50 · DAVIS17 validationJ&F: 69.7 -> 71.7Improved
add cycle-consistency training loss (ablation)STM ResNet50 · DAVIS16 validationJ&F: 82.3 -> 83.9Improved
add gradient correction at inference on top of cyclic model (ablation)STM-ResNet50-cycle · DAVIS17 validationJ&F: 71.7 -> 72.9Improved
add gradient correction at inference on top of cyclic model (ablation)STM-ResNet50-cycle · DAVIS16 validationJ&F: 83.9 -> 84.0No clear effect
add cyclic training when reference is only the last predicted frame (ablation)STM · DAVIS17 validationJ&F: 56.8 -> 61.2Improved
add cyclic training when reference is only the first frame (ablation)STM · DAVIS16 validationJ&F: 81.2 -> 81.2No clear effect
add cyclic training with memory (MEM) reference (ablation)STM · DAVIS17 validationJ&F: 69.7 -> 71.7Improved
add cyclic training to KMN (ablation)KMN · DAVIS17 validationJ&F: 69.9 -> 70.7Improved
add gradient correction to cyclic KMN (ablation)KMN-cycle · DAVIS17 validationJ&F: 70.7 -> 72.2Improved
add gradient correction to cyclic GCM (ablation)GCM-cycle · DAVIS17 validationJ&F: 70.4 -> 70.7No clear effect
add cyclic training to AOT-T (ablation)AOT-T · DAVIS17 validationJ&F: 79.2 -> 80.2Improved
add gradient correction on box-template noisy reference masks (ablation)STM-cycle with MEM · DAVIS17 validationJ&F: 64.5 -> 71.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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