Research map / Architectures and efficiency / CNN design
Compositional Model Based Fisher Vector Coding for Image Classification
Lingqiao Liu, Peng Wang, Chunhua Shen, Lei Wang, Anton van den Hengel, Chao Wang, Heng Tao Shen
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 |
|---|---|---|---|
| replace GMM Fisher coding with sparse compositional FVC (SCFVC) | GMMFVC · Birds-200 | accuracy: 70.1% -> 77.3% | Improved |
| replace GMM Fisher coding with SCFVC | GMMFVC · MIT-67 | accuracy: 72.6% -> 77.6% | Improved |
| replace GMM Fisher coding with SCFVC | GMMFVC · Pascal VOC 2007 | mAP: 84.6% -> 86.6% | Improved |
| add discriminative/residual decomposition guided by supervised coding (HSCFVC over SCFVC) (ablation) | SCFVC · Birds-200 | accuracy: 77.3% -> 80.8% | Improved |
| add discriminative/residual decomposition (HSCFVC over SCFVC) (ablation) | SCFVC · MIT-67 | accuracy: 77.6% -> 79.5% | Improved |
| add discriminative/residual decomposition (HSCFVC over SCFVC) (ablation) | SCFVC · Pascal VOC 2007 | mAP: 86.6% -> 88.1% | Improved |
| add Fisher vector coding on top of the guiding supervised coding (HSCFVC over SupC) (ablation) | SupC · Birds-200 | accuracy: 69.5% -> 80.8% | Improved |
| add residual part Fisher vector to the discriminative part (ablation) | HSCFVC · Birds-200, MIT-67, Pascal-07 | accuracy / mAP | Improved |
| enable guidance term (lambda > 0) in HSCFVC (ablation) | HSCFVC · Birds-200, Pascal-07, MIT-67 | accuracy / mAP | Improved |
| use region-crop scheme with aspect ratio kept and 3 scales | HSCFVC · Pascal VOC 2007 | mAP: 88.1% -> 89.8% | Improved |
| increase number of GMM Gaussians to 500 while reducing dimension to 400 (ablation) | GMMFVC · MIT-67 | accuracy: 72.6% -> 73.7% | Improved |
| increase Gaussians to 1000 while reducing dimension to 200 (ablation) | GMMFVC · MIT-67 | accuracy: 72.6% -> 71.1% | Hurt |
Closest papers by meaning
- Locally-Transferred Fisher Vectors for Texture Classification (ICCV 2017 · similarity 0.88)
- Approximate Fisher Kernels of Non-iid Image Models for Image Categorization (TPAMI 2016 · similarity 0.85)
- Modality and Component Aware Feature Fusion For RGB-D Scene Classification (CVPR 2016 · similarity 0.85)
- Deep Quantization: Encoding Convolutional Activations With Deep Generative Model (CVPR 2017 · similarity 0.84)
- Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes (TPAMI 2019 · similarity 0.84)
- Discriminating image representations with principal distortions (ICLR 2025 · similarity 0.83)
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.
