Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection

TL;DR

Relief R-CNN introduces a fast region proposal method using convolutional feature discrepancies, significantly speeding up object detection while maintaining accuracy.

Contribution

The paper presents a novel, efficient region proposal generator that directly uses convolutional features, reducing detection time in R-CNN based methods.

Findings

Achieves the fastest detection speed among compared algorithms.

Maintains comparable accuracy with existing methods.

Reduces computational resource demands during testing.

Abstract

R-CNN style methods are sorts of the state-of-the-art object detection methods, which consist of region proposal generation and deep CNN classification. However, the proposal generation phase in this paradigm is usually time consuming, which would slow down the whole detection time in testing. This paper suggests that the value discrepancies among features in deep convolutional feature maps contain plenty of useful spatial information, and proposes a simple approach to extract the information for fast region proposal generation in testing. The proposed method, namely Relief R-CNN (R2-CNN), adopts a novel region proposal generator in a trained R-CNN style model. The new generator directly generates proposals from convolutional features by some simple rules, thus resulting in a much faster proposal generation speed and a lower demand of computation resources. Empirical studies show that R2-CNN could achieve the fastest detection speed with comparable accuracy among all the compared algorithms in testing.