Research map / Architectures and efficiency / CNN design
Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays
Laurie Bose, Piotr Dudek, Jianing Chen, Stephen J. Carey, Walterio W. Mayol-Cuevas
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 |
|---|---|---|---|
| run inference on analog SCAMP-5 hardware instead of PC floating evaluation (two-layer) | binary/ternary CNN · MNIST | accuracy: 95 -> 92%-94% | Hurt |
| run inference on analog SCAMP-5 hardware instead of PC evaluation (three-layer) | binary/ternary CNN · MNIST | accuracy: 97 -> 92%-94% | Hurt |
| add a second convolutional layer (three-layer vs two-layer network) | SCAMP-5 PPA CNN · MNIST | throughput (fps): 3676 -> 224 | Hurt |
| add a second convolutional layer (three-layer vs two-layer network) | SCAMP-5 PPA CNN · MNIST | accuracy: 92%-94% | No clear effect |
| use digital pixel counting instead of analog global summation for activations | SCAMP-5 PPA CNN · three-layer network | summation accuracy: 260 us, perfectly accurate | Improved |
Closest papers by meaning
- A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays (ICCV 2019 · similarity 0.94)
- Focal Plane Visual Feature Generation and Matching on a Pixel Processor Array (ICCV 2025 · similarity 0.87)
- Fast Image Processing With Fully-Convolutional Networks (ICCV 2017 · similarity 0.87)
- Designing Extremely Memory-Efficient CNNs for On-device Vision and Audio Tasks (IJCV 2026 · similarity 0.86)
- Descriptor-In-Pixel : Point-Feature Tracking For Pixel Processor Arrays (CVPR 2025 · similarity 0.86)
- Bilinear Convolutional Neural Networks for Fine-Grained Visual Recognition (TPAMI 2017 · similarity 0.86)
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.
