Rethinking the backbone architecture for tiny object detection

Abstract

Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios. However, existing tiny object detection methods use standard deep neural networks as their backbone architecture. We argue that such backbones are inappropriate for detecting tiny objects as they are designed for the classification of larger objects, and do not have the spatial resolution to identify small targets. Specifically, such backbones use max-pooling or a large stride at early stages in the architecture. This produces lower resolution feature-maps that can be efficiently processed by subsequent layers. However, such low-resolution feature-maps do not contain information that can reliably discriminate tiny objects. To solve this problem we design 'bottom-heavy' versions of backbones that allocate more resources to processing higher-resolution features without introducing any additional computational burden overall. We also investigate if pre-training these backbones on images of appropriate size, using CIFAR100 and ImageNet32, can further improve performance on tiny object detection. Results on TinyPerson and WiderFace show that detectors with our proposed backbones achieve better results than the current state-of-the-art methods.

References in corpus (8)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Striving for Simplicity: The All Convolutional Net
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images
• TinaFace: Strong but Simple Baseline for Face Detection
• SFA: Small Faces Attention Face Detector
• Robust Face Detection via Learning Small Faces on Hard Images