Research map / Label-efficient and robust learning / Recognition and long-tail
Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
Chaojian Yu, Xinyi Zhao, Qi Zheng, Peng Zhang, Xinge You
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 |
|---|---|---|---|
| add cross-layer interaction relu5_2 (FBP to CBP-1) (ablation) | factorized bilinear pooling · CUB-200-2011 | accuracy (%): 85.70 -> 86.75 | Improved |
| add relu5_1 as second cross-layer pair (CBP-1 to HBP-1) (ablation) | CBP · CUB-200-2011 | accuracy (%): 86.75 -> 86.78 | No clear effect |
| use relu5_2*relu5_1 pair instead of relu5_3*relu4_3 (HBP-2 to HBP-3) (ablation) | HBP · CUB-200-2011 | accuracy (%): 86.91 -> 87.15 | Improved |
| add intermediate layers via HBP-3 over FBP-1 (ablation) | FBP · CUB-200-2011 | accuracy (%): 85.70 -> 87.15 | Improved |
| replace relu5_3*relu5_2 with relu5_3*relu4_3 pair (ablation) | CBP · CUB-200-2011 | accuracy (%): 86.75 -> 86.67 | No clear effect |
| replace hypercolumn concatenation with cross-layer bilinear pooling | HyperBP · CUB-200-2011 | accuracy (%): 86.60 -> 86.75 | Improved |
| replace hypercolumn concatenation with cross-layer bilinear pooling | HyperBP · CUB-200-2011 | model size: 18.4M -> 10.0M | Improved |
| use HBP instead of CBP | CBP · CUB-200-2011 | model size: 10.0M -> 17.5M | Hurt |
| increase projection dimension d from 512 to 8192 (ablation) | HBP · CUB-200-2011 | accuracy | Improved |
| add HBP over FBP baseline | FBP · Stanford Cars | accuracy (%): 92.8 -> 93.7 | Improved |
| use HBP over MA-CNN | MA-CNN · FGVC-Aircraft | accuracy (%): 89.9 -> 90.3 | Improved |
| use HBP over MA-CNN | MA-CNN · CUB-200-2011 | accuracy (%): 86.5 -> 87.1 | Improved |
Closest papers by meaning
- Compact Bilinear Pooling (CVPR 2016 · similarity 0.92)
- Low-Rank Bilinear Pooling for Fine-Grained Classification (CVPR 2017 · similarity 0.90)
- Kernel Pooling for Convolutional Neural Networks (CVPR 2017 · similarity 0.89)
- Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification (ECCV 2018 · similarity 0.89)
- Learning Compact Discriminant Representation via Low-Rank Bilinear Pooling (TPAMI 2025 · similarity 0.89)
- Efficient Compact Bilinear Pooling via Kronecker Product (AAAI 2022 · similarity 0.88)
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.
