SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.05930 · AAAI · 2021

AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing

Rui Huang, Qi Song, Kangfu Mei

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

Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity, which is problematic in real-time scenarios. In this paper, we propose a new model, called Attention-Augmented Network (AttaNet), to capture both global context and multilevel semantics while keeping the efficiency high. AttaNet consists of two primary modules: Strip Attention Module (SAM) and Attention Fusion Module (AFM). Viewing that in challenging images with low segmentation accuracy, there are a significantly larger amount of vertical strip areas than horizontal ones, SAM utilizes a striping operation to reduce the complexity of encoding global context in the vertical direction drastically while keeping most of contextual information, compared to the non-local approaches. Moreover, AFM follows a cross-level aggregation strategy to limit the computation, and adopts an attention strategy to weight the importance of different levels of features at each pixel when fusing them, obtaining an efficient multi-level representation. We have conducted extensive experiments on two semantic segmentation benchmarks, and our network achieves different levels of speed/accuracy trade-offs on Cityscapes, e.g., 71 FPS/79.9% mIoU, 130 FPS/78.5% mIoU, and 180 FPS/70.1% mIoU, and leading performance on ADE20K as well.

For agents

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

get_harvested_code_for_paper("2103.05930")
get_code_for_paper("2103.05930")
have("2103.05930")

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

curl https://syntology.ai/api/ran/2103.05930.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.05930.svg)](https://syntology.ai/paper/2103.05930)

Connect an agent — have() is free.