Research map / Detection and segmentation / CNN features
Object based Scene Representations using Fisher Scores of Local Subspace Projections
Mandar D Dixit, Nuno Vasconcelos
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 MFA covariance scores (Lambda) instead of GMM variance scores (sigma) (ablation) | MFA-FS · MIT Indoor | accuracy (%): 53.86 -> 71.11 | Improved |
| use MFA covariance scores (Lambda) instead of GMM variance scores (sigma) (ablation) | MFA-FS · SUN | accuracy (%): 37.71 -> 53.38 | Improved |
| use GMM variance statistics instead of means (ablation) | GMM-FV · MIT Indoor | accuracy (%): 66.08 -> 53.86 | Hurt |
| MFA mean scores instead of GMM mean statistics (ablation) | MFA-FS(mu) · MIT Indoor | accuracy (%): 66.08 -> 67.68 | Improved |
| replace GMM variance FV with MFA subspace-variance FV (ablation) | FV · MIT Indoor | accuracy (%): 53.86 -> 60.7 | Improved |
| combine MFA-FS(mu) with MFA-FS(Lambda) (ablation) | MFA-FS · MIT Indoor | accuracy (%): ~1% | Mixed |
| concatenate three patch scales instead of best single scale (AlexNet) (ablation) | MFA-FS · MIT Indoor | accuracy (%): 71.11 -> 73.58 | Improved |
| concatenate three patch scales instead of best single scale (VGG-16) (ablation) | MFA-FS · SUN | accuracy (%): 61.71 -> 63.31 | Improved |
| concatenate three patch scales (VGG-19) instead of 128x128 (ablation) | MFA-FS · MIT Indoor | accuracy (%): 79.39 -> 81.43 | Improved |
| add Places CNN features to MFA-FS (VGG) | MFA-FS · MIT Indoor | accuracy (%): 81.43 -> 87.23 | Improved |
| add Places CNN features to MFA-FS (VGG) | MFA-FS · SUN | accuracy (%): 63.31 -> 71.06 | Improved |
| task transfer MFA-FS instead of Places CNN dataset transfer (AlexNet) | MFA-FS · MIT Indoor | accuracy (%): 68.24 -> 73.58 | Improved |
Closest papers by meaning
- Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes (TPAMI 2019 · similarity 0.89)
- Deep Scene Image Classification With the MFAFVNet (ICCV 2017 · similarity 0.88)
- Locally-Transferred Fisher Vectors for Texture Classification (ICCV 2017 · similarity 0.83)
- Modality and Component Aware Feature Fusion For RGB-D Scene Classification (CVPR 2016 · similarity 0.83)
- Discriminating image representations with principal distortions (ICLR 2025 · similarity 0.82)
- Compositional Model Based Fisher Vector Coding for Image Classification (TPAMI 2017 · 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.
