Papers › DNN Feature Map Compression using Learned Representation over GF(2)

DNN Feature Map Compression using Learned Representation over GF(2)

15 Aug 2018ICLR 2018 1arXiv:1808.05285archive 2025-07-28

Denis A. Gudovskiy, Alec Hodgkinson, Luca Rigazio

In this paper, we introduce a method to compress intermediate feature maps of deep neural networks (DNNs) to decrease memory storage and bandwidth requirements during inference. Unlike previous works, the proposed method is based on converting fixed-point activations into vectors over the smallest GF(2) finite field followed by nonlinear dimensionality reduction (NDR) layers embedded into a DNN. Such an end-to-end learned representation finds more compact feature maps by exploiting quantization redundancies within the fixed-point activations along the channel or spatial dimensions. We apply the proposed network architectures derived from modified SqueezeNet and MobileNetV2 to the tasks of ImageNet classification and PASCAL VOC object detection. Compared to prior approaches, the conducted experiments show a factor of 2 decrease in memory requirements with minor degradation in accuracy while adding only bitwise computations.

PaperPDFConference PDFCode

Code

gudovskiy/fmap_compression officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dimensionality ReductionGeneral ClassificationObject DetectionQuantizationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingConvolutionDropoutFire ModuleGlobal Average PoolingMax PoolingReLUResidual ConnectionSoftmaxSqueezeNetXavier Initialization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections