SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.12255 · 2019

Improving Object Detection with Inverted Attention

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

Improving object detectors against occlusion, blur and noise is a critical step to deploy detectors in real applications. Since it is not possible to exhaust all image defects through data collection, many researchers seek to generate hard samples in training. The generated hard samples are either images or feature maps with coarse patches dropped out in the spatial dimensions. Significant overheads are required in training the extra hard samples and/or estimating drop-out patches using extra network branches. In this paper, we improve object detectors using a highly efficient and fine-grain mechanism called Inverted Attention (IA). Different from the original detector network that only focuses on the dominant part of objects, the detector network with IA iteratively inverts attention on feature maps and puts more attention on complementary object parts, feature channels and even context. Our approach (1) operates along both the spatial and channels dimensions of the feature maps; (2) requires no extra training on hard samples, no extra network parameters for attention estimation, and no testing overheads. Experiments show that our approach consistently improved both two-stage and single-stage detectors on benchmark databases.

For agents

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

get_harvested_code_for_paper("1903.12255")
get_code_for_paper("1903.12255")
have("1903.12255")

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

curl https://syntology.ai/api/ran/1903.12255.json

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

[![Syntology run record](https://syntology.ai/api/ran/1903.12255.svg)](https://syntology.ai/paper/1903.12255)

Connect an agent — have() is free.