Hardware–Algorithm Co-Design for Efficient Bit-Serial Acceleration of Lightweight CNNs With Standard and Depthwise Convolutions on FPGA
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 34 (9) , 1-13
Abstract
No abstract availableFunding Information
- Science and Technology Planning Project of Fuzhou (2023B01J0007)
- National Natural Science Foundation of China (62301165)
This publication has 34 references indexed in Scilit:
- An efficient DSP packing framework for FPGA-based mixed-precision DCNN processorJournal of Systems Architecture, 2025
- A DSP-Based Precision-Scalable MAC With Hybrid Dataflow for Arbitrary-Basis-Quantization CNN AcceleratorIEEE Computer Architecture Letters, 2025
- BitWave: Exploiting Column-Based Bit-Level Sparsity for Deep Learning Acceleration2024
- Single-shot pruning and quantization for hardware-friendly neural network accelerationEngineering Applications of Artificial Intelligence, 2023
- MSD: Mixing Signed Digit Representations for Hardware-efficient DNN Acceleration on FPGA with Heterogeneous Resources2023
- S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration2022
- LETA: A lightweight exchangeable-track accelerator for efficientnet based on FPGA2021
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Loom: Exploiting Weight and Activation Precisions to Accelerate Convolutional Neural Networks2018
- Deep Residual Learning for Image Recognition2016