DeepAI AI Chat
Log In Sign Up

AugFPN: Improving Multi-scale Feature Learning for Object Detection

by   Chaoxu Guo, et al.

Current state-of-the-art detectors typically exploit feature pyramid to detect objects at different scales. Among them, FPN is one of the representative works that build a feature pyramid by multi-scale features summation. However, the design defects behind prevent the multi-scale features from being fully exploited. In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems. Specifically, AugFPN consists of three components: Consistent Supervision, Residual Feature Augmentation, and Soft RoI Selection. AugFPN narrows the semantic gaps between features of different scales before feature fusion through Consistent Supervision. In feature fusion, ratio-invariant context information is extracted by Residual Feature Augmentation to reduce the information loss of feature map at the highest pyramid level. Finally, Soft RoI Selection is employed to learn a better RoI feature adaptively after feature fusion. By replacing FPN with AugFPN in Faster R-CNN, our models achieve 2.3 and 1.6 points higher Average Precision (AP) when using ResNet50 and MobileNet-v2 as backbone respectively. Furthermore, AugFPN improves RetinaNet by 1.6 points AP and FCOS by 0.9 points AP when using ResNet50 as backbone. Codes will be made available.


M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

Feature pyramids are widely exploited by both the state-of-the-art one-s...

Seismic Shot Gather Noise Localization Using a Multi-Scale Feature-Fusion-Based Neural Network

Deep learning-based models, such as convolutional neural networks, have ...

Isotropic and Steerable Wavelets in N Dimensions. A multiresolution analysis framework for ITK

This document describes the implementation of the external module ITKIso...

Deep Feature Pyramid Reconfiguration for Object Detection

State-of-the-art object detectors usually learn multi-scale representati...

Trident Pyramid Networks: The importance of processing at the feature pyramid level for better object detection

Feature pyramids have become ubiquitous in multi-scale computer vision t...

A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation

Learning pyramidal feature representations is crucial for recognizing ob...

RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection

Feature pyramid networks (FPN) are widely exploited for multi-scale feat...