DeepAI AI Chat
Log In Sign Up

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

by   Miao Hu, et al.

Learning pyramidal feature representations is crucial for recognizing object instances at different scales. Feature Pyramid Network (FPN) is the classic architecture to build a feature pyramid with high-level semantics throughout. However, intrinsic defects in feature extraction and fusion inhibit FPN from further aggregating more discriminative features. In this work, we propose Attention Aggregation based Feature Pyramid Network (A^2-FPN), to improve multi-scale feature learning through attention-guided feature aggregation. In feature extraction, it extracts discriminative features by collecting-distributing multi-level global context features, and mitigates the semantic information loss due to drastically reduced channels. In feature fusion, it aggregates complementary information from adjacent features to generate location-wise reassembly kernels for content-aware sampling, and employs channel-wise reweighting to enhance the semantic consistency before element-wise addition. A^2-FPN shows consistent gains on different instance segmentation frameworks. By replacing FPN with A^2-FPN in Mask R-CNN, our model boosts the performance by 2.1 ResNet-101 as backbone, respectively. Moreover, A^2-FPN achieves an improvement of 2.0 Cascade Mask R-CNN and Hybrid Task Cascade.


page 3

page 5

page 6

page 8


SPFNet:Subspace Pyramid Fusion Network for Semantic Segmentation

The encoder-decoder structure has significantly improved performance in ...

AugFPN: Improving Multi-scale Feature Learning for Object Detection

Current state-of-the-art detectors typically exploit feature pyramid to ...

Pyramid Fusion Transformer for Semantic Segmentation

The recently proposed MaskFormer <cit.> gives a refreshed perspective on...

CATNet: Context AggregaTion Network for Instance Segmentation in Remote Sensing Images

The task of instance segmentation in remote sensing images, aiming at pe...

Hybrid Task Cascade for Instance Segmentation

Cascade is a classic yet powerful architecture that has boosted performa...

A Mask Attention Interaction and Scale Enhancement Network for SAR Ship Instance Segmentation

Most of existing synthetic aperture radar (SAR) ship in-stance segmentat...

AGPCNet: Attention-Guided Pyramid Context Networks for Infrared Small Target Detection

Infrared small target detection is an important problem in many fields s...