SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.08485 · ECCV · 2022

Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Optical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS). Most of the previous methods directly extract and fuse the motion and appearance features for segmenting target objects in the UVOS setting. However, optical flow is intrinsically an instantaneous velocity of all pixels among consecutive frames, thus making the motion features not aligned well with the primary objects among the corresponding frames. To solve the above challenge, we propose a concise, practical, and efficient architecture for appearance and motion feature alignment, dubbed hierarchical feature alignment network (HFAN). Specifically, the key merits in HFAN are the sequential Feature AlignMent (FAM) module and the Feature AdaptaTion (FAT) module, which are leveraged for processing the appearance and motion features hierarchically. FAM is capable of aligning both appearance and motion features with the primary object semantic representations, respectively. Further, FAT is explicitly designed for the adaptive fusion of appearance and motion features to achieve a desirable trade-off between cross-modal features. Extensive experiments demonstrate the effectiveness of the proposed HFAN, which reaches a new state-of-the-art performance on DAVIS-16, achieving 88.7 J &F Mean, i.e., a relative improvement of 3.5% over the best published result.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.08485")
get_code_for_paper("2207.08485")
have("2207.08485")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.08485.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.08485.svg)](https://syntology.ai/paper/2207.08485)

Connect an agent — have() is free.