Research map / Architectures and efficiency / CNN design
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add the tree architecture to the VGG-16 classifier (ablation) | ACNet · CUB-200-2011 | Top-1 accuracy: 3.025% improvements | Helped |
| set tree height to 2 rather than 3 (ablation) | ACNet · CUB-200-2011 | Top-1 Acc. (%): 87.8 -> 86.0 | Hurt |
| set tree height to 4 rather than 3 (ablation) | ACNet · CUB-200-2011 | Top-1 accuracy: 2.3% drop | Hurt |
| use an asymmetric rather than symmetric tree (ablation) | ACNet · CUB-200-2011 | Top-1 accuracy: improved 1.6% | Helped |
| use global average pooling rather than global max-pooling in routing (ablation) | ACNet · CUB-200-2011 | Top-1 accuracy: 0.6% top-1 accuracy drop | Helped |
| add the attention block to the tree transformer (ablation) | ACNet · CUB-200-2011 | Top-1 accuracy: improving 0.4% top-1 accuracy in average | Helped |
| use ASPP instead of one convolution layer in the transformer (ablation) | ACNet · CUB-200-2011 | Top-1 accuracy: improves 0.5% top-1 accuracy in average | Helped |
| remove the global context block from branch routing (ablation) | ACNet · CUB-200-2011 | Top-1 accuracy: drops 0.275% in average | Hurt |
| use tree height 3 rather than height 1 (ablation) | ACNet · CUB-200-2011 | Top-1 Acc. (%): 82.2 -> 87.8 | Helped |
Closest papers by meaning
- TransFG: A Transformer Architecture for Fine-Grained Recognition (AAAI 2022 · similarity 0.89)
- ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization (AAAI 2024 · similarity 0.89)
- Filtration and Distillation: Enhancing Region Attention for Fine-Grained Visual Categorization (AAAI 2020 · similarity 0.88)
- Novel Class Discovery for Ultra-Fine-Grained Visual Categorization (CVPR 2024 · similarity 0.87)
- Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation (NeurIPS 2024 · similarity 0.86)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.85)
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.