Extended Feature Pyramid Network for Small Object Detection

By Chunfang Deng, Mengmeng Wang, Liang Liu, Yong Liu. IEEE transactions on multimedia, 2020

382 citations recorded by the source corpus.

Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the performance of small objects. In this paper, we propose an extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. Moreover, we introduce a cross resolution distillation mechanism to transfer the ability of perceiving details across the scales of the network, where a foreground-background-balanced loss function is designed to alleviate area imbalance of foreground and background. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results on small traffic-sign dataset Tsinghua-Tencent 100 K and small category of general object detection dataset MS COCO.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1bdb64c0c30b56e54da34b4e13820aafc36f6bf9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Gong Cheng
2. Junwei Han
3. Xiwen Yao
4. Ke Yan
5. Xiang Yuan
6. Qinghua Zeng
7. Lei Li
8. Zhenjun Han

Citations in the corpus

• Attention-Guided Pyramid Context Networks for Detecting Infrared Small Target Under Complex Background (2023, background): “Infrared Small Target Detection Networks: In visible image data, small target detection is gradually receiving more attention [30], [31], [32], [33], [34].”
• Effective Fusion Factor in FPN for Tiny Object Detection (2020, methodology): “EFPN [5] constructs a feature layer with more geometric details, which is designed for small objects via SR. Noh et al. [22] propose a feature level super-resolution approach using high-resolution object features as supervision signals and matching the relevant receptive fields of input and object…”
• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “With the help of deconvolution and sub-pixel convolution [112], Zhou et al. [83] and Deng et al. [113] obtained high-resolution features specialized for small object detection.”