Summary of Noah: Learning Pairwise Object Category Attentions For Image Classification, by Chao Li et al.
NOAH: Learning Pairwise Object Category Attentions for Image Classification
by Chao Li, Aojun Zhou, Anbang Yao
First submitted to arxiv on: 4 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 paper proposes a novel deep neural network (DNN) architecture for image classification tasks, dubbed Non-glObal Attentive Head (NOAH). NOAH replaces traditional head structures in DNNs with pairwise object category attention (POCA), which efficiently captures spatially dense category-specific attentions to improve classification performance. The proposed architecture is a drop-in design that can be easily integrated into various types of DNNs, including convolutional neural networks, vision transformers, and multi-layer perceptrons. The authors validate the effectiveness of NOAH on ImageNet classification benchmark with 25 different architectures, showing significant performance improvements for lightweight models like MobileNetV2, Deit-Tiny, and gMLP-Tiny. The paper also demonstrates that NOAH generalizes well to medium-size and large-size DNNs and performs well across various training regimes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new type of deep neural network (DNN) called Non-glObal Attentive Head (NOAH). This new architecture helps computers better understand pictures by looking at specific parts of the image. It’s like when you’re trying to find someone in a crowd, and you focus on their face or hair. NOAH does this for images, which makes it really good at recognizing things. |
Keywords
* Artificial intelligence * Attention * Classification * Image classification * Neural network
