Towards Better Object Detection in Scale Variation with Adaptive Feature Selection
arXiv:2012.03265
Abstract
It is a common practice to exploit pyramidal feature representation to tackle the problem of scale variation in object instances. However, most of them still predict the objects in a certain range of scales based solely or mainly on a single-level representation, yielding inferior detection performance. To this end, we propose a novel adaptive feature selection module (AFSM), to automatically learn the way to fuse multi-level representations in the channel dimension, in a data-driven manner. It significantly improves the performance of the detectors that have a feature pyramid structure, while introducing nearly free inference overhead. Moreover, a class-aware sampling mechanism (CASM) is proposed to tackle the class imbalance problem, by re-weighting the sampling ratio to each of the training images, based on the statistical characteristics of each class. This is crucial to improve the performance of the minor classes. Experimental results demonstrate the effectiveness of the proposed method, with 83.04% mAP at 15.96 FPS on the VOC dataset, and 39.48% AP on the VisDrone-DET validation subset, respectively, outperforming other state-of-the-art detectors considerably. The code is available at https://github.com/ZeHuiGong/AFSM.git.
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- DSSD : Deconvolutional Single Shot Detector
- Learning Spatial Fusion for Single-Shot Object Detection
- Bag of Freebies for Training Object Detection Neural Networks
- HRDNet: High-resolution Detection Network for Small Objects
- PENet: Object Detection using Points Estimation in Aerial Images
- Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection