AI Paper Atlas

Research map / Video / Video segmentation and tracking

Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation

Gensheng Pei, Fumin Shen, Yazhou Yao, Guo-Sen Xie, Zhenmin Tang, Jinhui Tang

ECCV 2022 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 72 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 optical flow to the image frame input (baseline fusion vs image only) (ablation)baseline additive fusion · DAVIS-16 val (MiT-b1)J Mean: 79.1 -> 83.0Improved
add the image frame to optical flow input (baseline fusion vs flow only) (ablation)baseline additive fusion · DAVIS-16 val (MiT-b1)J Mean: 77.9 -> 83.0Improved
add the feature alignment module (FAM) (ablation)baseline · DAVIS-16 val (MiT-b1)J Mean: 83.0 -> 85.2Improved
add the feature adaptation module (FAT) (ablation)baseline · DAVIS-16 val (MiT-b1)J Mean: 83.0 -> 85.0Improved
add both FAM and FAT (ablation)baseline · DAVIS-16 val (MiT-b1)J Mean: 83.0 -> 86.2Improved
add FAM, FAT and both modules costs speed (ablation)baseline · DAVIS-16 val (MiT-b1)FPS: 22.0 -> 20.8Hurt
enlarge backbone from MiT-b0 to MiT-b1 (ablation)HFAN · DAVIS-16 val (MiT-b1) single-scaleJ Mean: 81.5 -> 86.2Improved
enlarge backbone from MiT-b1 to MiT-b3 (ablation)HFAN · DAVIS-16 val single-scaleFPS: 20.8 -> 10.6Hurt
use multi-scale test instead of single-scale test (ablation)HFAN MiT-b1 · DAVIS-16 valJ Mean: 86.2 -> 87.1Improved
raise input size from 384x384 to 512x512 (RAFT flow) (ablation)HFAN MiT-b1 · DAVIS-16 val multi-scaleJ Mean: 86.2 -> 87.1Improved
use RAFT instead of PWCNet optical flow (ablation)HFAN MiT-b1 · DAVIS-16 val multi-scale 512x512J Mean: 85.7 -> 87.1Improved
use HFAN instead of MATNet+CRF with the same MiT-b1 backboneMiT-b1 · DAVIS-16 valJ Mean: 83.8 -> 87.1Improved

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