Summary of Amanet: Advancing Sar Ship Detection with Adaptive Multi-hierarchical Attention Network, by Xiaolin Ma et al.
AMANet: Advancing SAR Ship Detection with Adaptive Multi-Hierarchical Attention Network
by Xiaolin Ma, Junkai Cheng, Aihua Li, Yuhua Zhang, Zhilong Lin
First submitted to arxiv on: 24 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel adaptive multi-hierarchical attention module (AMAM) and network (AMANet) for improving ship detection in synthetic aperture radar (SAR) images, particularly for small and coastal ships. The AMAM learns multi-scale features by fusing information from adjacent feature layers and adaptively aggregating salient features from various layers. This is achieved through a three-step process: enhancing smaller targets using multi-scale feature enhancement, filtering out complex backgrounds by dissecting and amalgamating features, and embedding the AMAM between a backbone network and a feature pyramid network (FPN). The proposed AMANet method outperforms state-of-the-art methods in extensive experiments on two large-scale SAR ship detection datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better detect ships in images taken from space using radar. Currently, it’s hard to find small boats and ships near the coast because there’s not much information in those areas. To fix this problem, scientists created a new way to look at features in these images that makes them more useful for finding smaller targets. This new method can be used with different computer programs to make object detection even better. It works by taking information from different layers of the image and combining it to highlight important details. The results show that this new method is better than other methods currently available. |
Keywords
* Artificial intelligence * Attention * Embedding * Feature pyramid * Object detection
