# Feature Map Transform Coding for Energy-Efficient CNN Inference

arXiv: https://arxiv.org/abs/1905.10830 · HTML: https://mlsanity.com/paper/1905.10830/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2019.

## Built on by (most cited first, 11 of 11)

- [MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2401.14895/) (2024)
- [TSPTQ-ViT: Two-scaled post-training quantization for vision transformer](https://mlsanity.com/paper/2305.12901/) (2023)
- [Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression](https://mlsanity.com/paper/2110.06155/) (2021)
- [Compression-aware Projection with Greedy Dimension Reduction for Convolutional Neural Network Activations](https://mlsanity.com/paper/2110.08828/) (2021)
- [Bimodal Distributed Binarized Neural Networks](https://mlsanity.com/paper/2204.02004/) (2022)
- [Lossy and Lossless (L2) Post-training Model Size Compression](https://mlsanity.com/paper/2308.04269/) (2023)
- [AMED: Automatic Mixed-Precision Quantization for Edge Devices](https://mlsanity.com/paper/2205.15437/) (2022)
- [Learnable Mixed-precision and Dimension Reduction Co-design for Low-storage Activation](https://mlsanity.com/paper/2207.07931/) (2022)
- [Improved Projection Learning for Lower Dimensional Feature Maps](https://mlsanity.com/paper/2210.15170/) (2022)
- [Bandwidth-efficient Inference for Neural Image Compression](https://mlsanity.com/paper/2309.02855/) (2023)
- [Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding](https://mlsanity.com/paper/2505.18758/) (2025)

## Abstract (arXiv)

Convolutional neural networks (CNNs) achieve state-of-the-art accuracy in a variety of tasks in computer vision and beyond. One of the major obstacles hindering the ubiquitous use of CNNs for inference on low-power edge devices is their high computational complexity and memory bandwidth requirements. The latter often dominates the energy footprint on modern hardware. In this paper, we introduce a lossy transform coding approach, inspired by image and video compression, designed to reduce the memory bandwidth due to the storage of intermediate activation calculation results. Our method does not require fine-tuning the network weights and halves the data transfer volumes to the main memory by compressing feature maps, which are highly correlated, with variable length coding. Our method outperform previous approach in term of the number of bits per value with minor accuracy degradation on ResNet-34 and MobileNetV2. We analyze the performance of our approach on a variety of CNN architectures and demonstrate that FPGA implementation of ResNet-18 with our approach results in a reduction of around 40% in the memory energy footprint, compared to quantized network, with negligible impact on accuracy. When allowing accuracy degradation of up to 2%, the reduction of 60% is achieved. A reference implementation is available at https://github.com/CompressTeam/TransformCodingInference