Summary of Joint Attention-guided Feature Fusion Network For Saliency Detection Of Surface Defects, by Xiaoheng Jiang et al.
Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects
by Xiaoheng Jiang, Feng Yan, Yang Lu, Ke Wang, Shuai Guo, Tianzhu Zhang, Yanwei Pang, Jianwei Niu, Mingliang Xu
First submitted to arxiv on: 5 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 The proposed joint attention-guided feature fusion network (JAFFNet) is a novel approach for saliency detection of surface defects in industrial manufacturing processes. This encoder-decoder network incorporates a joint attention-guided feature fusion (JAFF) module to adaptively fuse low-level and high-level features, emphasizing defect features while suppressing background noise. Additionally, the network introduces a dense receptive field (DRF) module to capture rich context information, enabling detection of defects with different scales. The JAFF module utilizes learned joint channel-spatial attention maps to guide feature fusion, while the DRF module employs multi-receptive-field units to process input features. Experimental results on SD-saliency-900, Magnetic tile, and DAGM 2007 demonstrate promising performance compared to state-of-the-art methods, with a real-time defect detection speed of 66 FPS. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary JAFFNet is a new way to detect surface defects in factories. This system uses a special kind of neural network that looks at both small and big features to find the defects. It’s like using a flashlight to shine on just the right spot, instead of shining it everywhere. This helps the system find even tiny defects that are hard to see. The system also works fast, so it can be used in real-time. |
Keywords
* Artificial intelligence * Attention * Encoder decoder * Neural network
