mlsanityData to 14 Oct 2026

PECAN: A Product-Quantized Content Addressable Memory Network

arXiv 2208.13571 ↗First posted 13 Aug 2022cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

A novel deep neural network (DNN) architecture is proposed wherein the filtering and linear transform are realized solely with product quantization (PQ). This results in a natural implementation via content addressable memory (CAM), which transcends regular DNN layer operations and requires only simple table lookup. Two schemes are developed for the end-to-end PQ prototype training, namely, through angle- and distance-based similarities, which differ in their multiplicative and additive natures with different complexity-accuracy tradeoffs. Even more, the distance-based scheme constitutes a truly multiplier-free DNN solution. Experiments confirm the feasibility of such Product-Quantized Content Addressable Memory Network (PECAN), which has strong implication on hardware-efficient deployments especially for in-memory computing.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 13 Aug 2022.

Builds on

22 of 30 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  5. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  6. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  7. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 217
  8. 2022Patches Are All You Need?cited by 201
  9. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  10. 2019AdderNet: Do We Really Need Multiplications in Deep Learning?cited by 82
  11. 2019DeepShift: Towards Multiplication-Less Neural Networkscited by 54
  12. 2020ShiftAddNet: A Hardware-Inspired Deep Networkcited by 52
10 more
  1. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 52
  2. 2018Automatically designing CNN architectures using genetic algorithm for image classificationcited by 48
  3. 2019CBNet: A Novel Composite Backbone Network Architecture for Object Detectioncited by 44
  4. 2021Learning Frequency Domain Approximation for Binary Neural Networkscited by 38
  5. 2019Differentiable Product Quantization for End-to-End Embedding Compressioncited by 36
  6. 2020Robust High-dimensional Memory-augmented Neural Networkscited by 31
  7. 2021Multiplying Matrices Without Multiplyingcited by 30
  8. 2020Kernel Based Progressive Distillation for Adder Neural Networkscited by 19
  9. 2017ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networkscited by 13
  10. 2021Self-Distribution Binary Neural Networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2024LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Modelscited by 12
  2. 2025LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Acceleratorcited by 9
  3. 2023PQA: Exploring the Potential of Product Quantization in DNN Hardware Accelerationcited by 6
  4. 2023Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplicationcited by 1
  5. 2026FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compressioncited by 1
  6. 2024Full-Stack Optimization for CAM-Only DNN Inferencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
  2. 2022FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks
  3. 2023Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings
  4. 2023Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives
  5. 2023Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization
  6. 2025Low-bit Model Quantization for Deep Neural Networks: A Survey
  7. 2021Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration
  8. 2024Quality Scalable Quantization Methodology for Deep Learning on Edge