SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.07868 · CVPR · 2023

DynaMask: Dynamic Mask Selection for Instance Segmentation

Lei Zhang, Shuai Li, Yabin Zhang, Chenhang He, Ruihuang Li

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

The representative instance segmentation methods mostly segment different object instances with a mask of the fixed resolution, e.g., 28 × 28 grid. However, a lowresolution mask loses rich details, while a high-resolution mask incurs quadratic computation overhead. It is a challenging task to predict the optimal binary mask for each instance. In this paper, we propose to dynamically select suitable masks for different object proposals. First, a dual-level Feature Pyramid Network (FPN) with adaptive feature aggregation is developed to gradually increase the mask grid resolution, ensuring high-quality segmentation of objects. Specifically, an efficient region-level top-down path (r-FPN) is introduced to incorporate complementary contextual and detailed information from different stages of image-level FPN (i-FPN). Then, to alleviate the increase of computation and memory costs caused by using large masks, we develop a Mask Switch Module (MSM) with negligible computational cost to select the most suitable mask resolution for each instance, achieving high efficiency while maintaining high segmentation accuracy. Without bells and whistles, the proposed method, namely DynaMask, brings consistent and noticeable performance improvements over other state-ofthe-arts at a moderate computation overhead. The source code: https://github.com/lslrh/DynaMask. * denotes the equal contribution, †denotes the corresponding author.

For agents

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

get_harvested_code_for_paper("2303.07868")
get_code_for_paper("2303.07868")
have("2303.07868")

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

curl https://syntology.ai/api/ran/2303.07868.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.07868.svg)](https://syntology.ai/paper/2303.07868)

Connect an agent — have() is free.