AI Paper Atlas

Research map / Video / Video segmentation and tracking

Domain Adaptive Video Segmentation via Temporal Pseudo Supervision

Yun Xing, Dayan Guan, Jiaxing Huang, Shijian Lu

ECCV 2022 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 17 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
use cross-frame augmentation and pseudo labelling (TPS) instead of spatial augmentation (PixMatch)PixMatch · SYNTHIA-Seq to Cityscapes-SeqmIoU: 51.0 -> 53.8Improved
use cross-frame augmentation and pseudo labelling (TPS) instead of spatial augmentation (PixMatch)PixMatch · VIPER to Cityscapes-SeqmIoU: 46.7 -> 48.9Improved
use consistency training (TPS) instead of adversarial learning (DA-VSN)DA-VSN · SYNTHIA-Seq to Cityscapes-SeqmIoU: 49.5 -> 53.8Improved
use propagation interval 1 instead of 3 (ablation)TPS · SYNTHIA-Seq to Cityscapes-SeqmIoU: 51.7 -> 53.8Improved
use propagation interval 1 instead of 2 (ablation)TPS · SYNTHIA-Seq to Cityscapes-SeqmIoU: 52.3 -> 53.8Improved
use confidence threshold 0 instead of 0.50 (ablation)TPS · SYNTHIA-Seq to Cityscapes-SeqmIoU: 53.1 -> 53.8Improved
use confidence threshold 0 instead of 0.25 (ablation)TPS · SYNTHIA-Seq to Cityscapes-SeqmIoU: 53.5 -> 53.8Improved
raise target loss weight lambda_T from 0.1 to 1.0 (ablation)TPS · SYNTHIA-Seq to Cityscapes-SeqmIoU: 50.0 -> 53.8Improved
raise target loss weight lambda_T from 1.0 to 2.0 (ablation)TPS · SYNTHIA-Seq to Cityscapes-SeqmIoU: 53.8 -> 53.3Hurt
add TPS consistency training to DA-VSN (ablation)DA-VSN · SYNTHIA-Seq to Cityscapes-SeqmIoU: 49.5 -> 55.1Improved
add TPS consistency training to DA-VSN (ablation)DA-VSN · VIPER to Cityscapes-SeqmIoU: 47.8 -> 50.2Improved

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