Scale-Aware Trident Networks for Object Detection

TL;DR

This paper introduces TridentNet, a scale-aware multi-branch architecture for object detection that improves performance by generating scale-specific features and training with scale-aware sampling, achieving state-of-the-art results.

Contribution

The paper proposes a novel TridentNet architecture with scale-specific branches and a scale-aware training scheme, enhancing object detection across varying object sizes.

Findings

Achieves 48.4 mAP on COCO with ResNet-101 backbone.

Scale-aware training improves detection of objects at different scales.

Fast approximation version maintains performance without extra computational cost.

Abstract

Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to specialize each branch by sampling object instances of proper scales for training. As a bonus, a fast approximation version of TridentNet could achieve significant improvements without any additional parameters and computational cost compared with the vanilla detector. On the COCO dataset, our TridentNet with ResNet-101 backbone achieves state-of-the-art single-model results of 48.4 mAP. Codes are available at https://git.io/fj5vR.