Research map / Learning theory and algorithms / Prediction and decision losses
Trusting SVM for Piecewise Linear CNNs
Leonard Berrada, Andrew Zisserman, M. Pawan Kumar
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 |
|---|---|---|---|
| Fine-tune Adadelta with LW-SVM | Adadelta (100) · MNIST test | testing accuracy: 98.96% -> 99.24% | Improved |
| Fine-tune Adadelta with LW-SVM | Adadelta (100) · CIFAR-10 test | testing accuracy: 84.42% -> 86.62% | Improved |
| Fine-tune Adadelta with LW-SVM | Adadelta (100) · CIFAR-100 test | testing accuracy: 58.71% -> 61.20% | Improved |
| Optimize dense layers and SVM layer with LW-SVM | VGG-16 (PT) · ImageNet validation | Top-1 accuracy: 73.30% -> 73.81% | Improved |
| Optimize dense layers and SVM layer with LW-SVM | VGG-16 (PT) · ImageNet validation | Top-5 accuracy: 91.33% -> 91.61% | Improved |
| Continue Adagrad training rather than fine-tune with LW-SVM | Adagrad on CIFAR-10 · CIFAR-10 test | testing accuracy: 83.84% vs 83.43% | Mixed |
Closest papers by meaning
- On the Upper Bounds of Number of Linear Regions and Generalization Error of Deep Convolutional Neural Networks (TPAMI 2025 · similarity 0.87)
- Structured Convolutions for Efficient Neural Network Design (NeurIPS 2020 · similarity 0.87)
- Nonlinear Pairwise Layer and Its Training for Kernel Learning (AAAI 2018 · similarity 0.87)
- On the Number of Linear Regions of Convolutional Neural Networks With Piecewise Linear Activations (TPAMI 2024 · similarity 0.86)
- Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales (NeurIPS 2022 · similarity 0.86)
- Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels (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.
