# Learning Region Features for Object Detection

Source: [Learning Region Features for Object Detection](<https://www.sota2.com/research/paper/68fa64251e209131cea02dce>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:53:50.473Z

Authors: Jiayuan Gu, Han Hu, Liwei Wang, Yichen Wei, Jifeng Dai

Published: 2018-03-19T17:58:50.000Z

## Abstract

While most steps in the modern object detection methods are learnable, the region feature extraction step remains largely hand-crafted, featured by RoI pooling methods. This work proposes a general viewpoint that unifies existing region feature extraction methods and a novel method that is end-to-end learnable. The proposed method removes most heuristic choices and outperforms its RoI pooling counterparts. It moves further towards fully learnable object detection.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1803.07066>)

[PDF](<https://arxiv.org/pdf/1803.07066.pdf>)