Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation

Johanna Rock, Wolfgang Roth, Mate Andras Toth, Paul Meissner, Franz Pernkopf

Research output: Contribution to journalArticlepeer-review


Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is inevitable and must be dealt with. Algorithms and models operating on radar data are required to run the early processing steps on specialized radar sensor hardware. This specialized hardware typically has strict resource-constraints, i.e. a low memory capacity and low computational power. Convolutional Neural Network (CNN)-based approaches for denoising and interference mitigation yield promising results for radar processing in terms of performance. Regarding resource-constraints, however, CNNs typically exceed the hardware's capacities by far. In this paper we investigate quantization techniques for CNN-based denoising and interference mitigation of radar signals. We analyze the quantization of (i) weights and (ii) activations of different CNN-based model architectures. This quantization results in reduced memory requirements for model storage and during inference. We compare models with fixed and learned bit-widths and contrast two different methodologies for training quantized CNNs, i.e. the straight-through gradient estimator and training distributions over discrete weights. We illustrate the importance of structurally small real-valued base models for quantization and show that learned bit-widths yield the smallest models. We achieve a memory reduction of around 80% compared to the real-valued baseline. Due to practical reasons, however, we recommend the use of 8 bits for weights and activations, which results in models that require only 0.2 megabytes of memory.

Original languageEnglish
Article number9364355
Pages (from-to)927-940
Number of pages14
JournalIEEE Journal on Selected Topics in Signal Processing
Issue number4
Publication statusPublished - Jun 2021


  • Automotive radar
  • binarized convolutional neural networks
  • discrete weight distributions
  • interference mitigation
  • quantization aware training
  • resource-efficiency
  • straight-through estimator
  • uncertainty maps

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fields of Expertise

  • Information, Communication & Computing


Dive into the research topics of 'Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation'. Together they form a unique fingerprint.

Cite this