CVDec 9, 2016

Feature Pyramid Networks for Object Detection

arXiv:1612.03144v226848 citations
Originality Highly original
AI Analysis

This provides a practical and accurate solution for multi-scale object detection in computer vision, addressing a known bottleneck in deep learning detectors.

The paper tackled the problem of multi-scale object detection by introducing Feature Pyramid Networks (FPN), which construct feature pyramids efficiently from deep convolutional networks, achieving state-of-the-art results on the COCO benchmark with a single model and running at 5 FPS on a GPU.

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using FPN in a basic Faster R-CNN system, our method achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.

Code Implementations85 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes