Research map / Architectures and efficiency / CNN design
Neuron Abandoning Attention Flow: Visual Explanation of Dynamics Inside CNN Models
Yi Liao, Yongsheng Gao, Weichuan Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use neuron abandoning back-propagation instead of using all neurons in each internal layer (Grad-CAM) | ResNet18/ResNet50 internal-layer attention maps · ImageNet2012 example images | qualitative attention map quality | Improved |
| insert CBAM into ResNet50 | ResNet50 · ImageNet2012 val | accuracy: 75.44% to 77.34% | Improved |
| insert BAM into ResNet50 | ResNet50 · ImageNet2012 val | accuracy: 75.44% to 75.98% | Improved |
| use Conv4Net instead of Conv64F | few-shot CNN · CUB200 5-way 1-shot | accuracy: 62.42% -> 65.88% | Improved |
| use ResNet50-NPID instead of ResNet18-NPID | contrastive learning classifier · ImageNet2012 val | accuracy: 41.0% -> 46.8% | Improved |
Closest papers by meaning
- Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection (AAAI 2018 · similarity 0.84)
- NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions (ICLR 2025 · similarity 0.83)
- Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks (NeurIPS 2025 · similarity 0.83)
- Self-Attention-Based Contextual Modulation Improves Neural System Identification (ICLR 2025 · similarity 0.82)
- In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval (ICML 2025 · similarity 0.82)
- Knowledge-Aware Neuron Interpretation for Scene Classification (AAAI 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
