Dynamic Proposals for Efficient Object Detection

TL;DR

This paper introduces a dynamic proposal generation method for object detection that adapts to varying computational resources, significantly speeding up detection while maintaining or improving accuracy.

Contribution

It presents a novel adaptive proposal mechanism that adjusts to computational constraints and input complexity, enhancing efficiency in object detection models.

Findings

Achieves significant speed-up across multiple detection models

Maintains or improves detection accuracy

Reduces computational costs effectively

Abstract

Object detection is a basic computer vision task to loccalize and categorize objects in a given image. Most state-of-the-art detection methods utilize a fixed number of proposals as an intermediate representation of object candidates, which is unable to adapt to different computational constraints during inference. In this paper, we propose a simple yet effective method which is adaptive to different computational resources by generating dynamic proposals for object detection. We first design a module to make a single query-based model to be able to inference with different numbers of proposals. Further, we extend it to a dynamic model to choose the number of proposals according to the input image, greatly reducing computational costs. Our method achieves significant speed-up across a wide range of detection models including two-stage and query-based models while obtaining similar or even better accuracy.