SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.05699 · ICCV · 2021

Oriented R-CNN for Object Detection

Xiwen Yao, Junwei Han, Gong Cheng, Jiabao Wang, Xingxing Xie

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

Figure 1: Comparisons of different schemes for generating oriented proposals. (a) Rotated RPN densely places rotated anchors with different scales, ratios, and angles. (b) RoI Transformer + learns oriented proposal from horizontal RoI. It involvs RPN, RoI Alignment, and regression. (c) Our proposed oriented RPN generates high-quality proposals in a nearly cost-free manner. The number of parameters of oriented RPN is about 1/3000 of RoI Transformer + and 1/15 of rotated RPN.

For agents

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

get_harvested_code_for_paper("2108.05699")
get_code_for_paper("2108.05699")
have("2108.05699")

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

curl https://syntology.ai/api/ran/2108.05699.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.05699.svg)](https://syntology.ai/paper/2108.05699)

Connect an agent — have() is free.