A 1Mb mixed-precision quantized encoder for image classification and patch-based compression

• URL: http://arxiv.org/abs/2501.05097v1
• Date: Thu, 09 Jan 2025 09:25:22 GMT
• Title: A 1Mb mixed-precision quantized encoder for image classification and patch-based compression
• Authors: Van Thien Nguyen, William Guicquero, Gilles Sicard,
• Abstract summary: We show that an ASIC neural network accelerator can be applied to multiple tasks of different levels. The key component is a reconfigurable, mixed-precision (3b/2b/1b) encoder that takes advantage of proper weight and activation quantizations. We also show that this quantized encoder can be used to compress image patch-by-patch while the reconstruction can performed remotely, by a dedicated full-frame decoder.
• Score: 2.7036595757881323
• License:
• Abstract: Even if Application-Specific Integrated Circuits (ASIC) have proven to be a relevant choice for integrating inference at the edge, they are often limited in terms of applicability. In this paper, we demonstrate that an ASIC neural network accelerator dedicated to image processing can be applied to multiple tasks of different levels: image classification and compression, while requiring a very limited hardware. The key component is a reconfigurable, mixed-precision (3b/2b/1b) encoder that takes advantage of proper weight and activation quantizations combined with convolutional layer structural pruning to lower hardware-related constraints (memory and computing). We introduce an automatic adaptation of linear symmetric quantizer scaling factors to perform quantized levels equalization, aiming at stabilizing quinary and ternary weights training. In addition, a proposed layer-shared Bit-Shift Normalization significantly simplifies the implementation of the hardware-expensive Batch Normalization. For a specific configuration in which the encoder design only requires 1Mb, the classification accuracy reaches 87.5% on CIFAR-10. Besides, we also show that this quantized encoder can be used to compress image patch-by-patch while the reconstruction can performed remotely, by a dedicated full-frame decoder. This solution typically enables an end-to-end compression almost without any block artifacts, outperforming patch-based state-of-the-art techniques employing a patch-constant bitrate.

Related papers

• PALQA: A Novel Parameterized Position-Aware Lossy Quantum Autoencoder using LSB Control Qubit for Efficient Image Compression [7.340017786387768]
  This work introduces a novel parameterized position-aware lossy quantum autoencoder (PALQA) circuit that utilizes the least significant bit control qubit for image compression. The PALQA circuit demonstrates superior performance in terms of the number of gates required and PSNR metrics.
  arXiv  Detail & Related papers  (2025-02-04T10:08:02Z)
• Accelerating Error Correction Code Transformers [56.75773430667148]
  We introduce a novel acceleration method for transformer-based decoders. We achieve a 90% compression ratio and reduce arithmetic operation energy consumption by at least 224 times on modern hardware.
  arXiv  Detail & Related papers  (2024-10-08T11:07:55Z)
• DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Coding [27.875207681547074]
  progressive image coding (PIC) aims to compress various qualities of images into a single bitstream. Research on neural network (NN)-based PIC is in its early stages. We propose an NN-based progressive coding method that firstly utilizes learned quantization step sizes via learning for each quantization layer.
  arXiv  Detail & Related papers  (2024-08-22T06:32:53Z)
• Rate-Distortion-Cognition Controllable Versatile Neural Image Compression [47.72668401825835]
  We propose a rate-distortion-cognition controllable versatile image compression method. Our method yields satisfactory ICM performance and flexible Rate-DistortionCognition controlling.
  arXiv  Detail & Related papers  (2024-07-16T13:17:51Z)
• AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution [53.23803932357899]
  We introduce the first on-the-fly adaptive quantization framework that accelerates the processing time from hours to seconds. We achieve competitive performance with the previous adaptive quantization methods, while the processing time is accelerated by x2000.
  arXiv  Detail & Related papers  (2024-04-04T08:37:27Z)
• Wavelet Feature Maps Compression for Image-to-Image CNNs [3.1542695050861544]
  We propose a novel approach for high-resolution activation maps compression integrated with point-wise convolutions. We achieve compression rates equivalent to 1-4bit activation quantization with relatively small and much more graceful degradation in performance.
  arXiv  Detail & Related papers  (2022-05-24T20:29:19Z)
• Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder [73.48927855855219]
  We propose a system that learns to improve the encoding performance by enhancing its internal neural representations on both the encoder and decoder ends. Experiments demonstrate that our approach successfully improves the rate-distortion performance over JPEG across various quality metrics.
  arXiv  Detail & Related papers  (2022-01-27T20:20:03Z)
• CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network [24.418215098116335]
  We propose a new deep image compression framework called Complexity and Bitrate Adaptive Network (CBANet) Our CBANet considers the trade-off between the rate and distortion under dynamic computational complexity constraints. As a result, our CBANet enables one single to support multiple decoding under various computational complexity constraints.
  arXiv  Detail & Related papers  (2021-05-26T08:13:56Z)
• Modeling Lost Information in Lossy Image Compression [72.69327382643549]
  Lossy image compression is one of the most commonly used operators for digital images. We propose a novel invertible framework called Invertible Lossy Compression (ILC) to largely mitigate the information loss problem.
  arXiv  Detail & Related papers  (2020-06-22T04:04:56Z)
• Quantization Guided JPEG Artifact Correction [69.04777875711646]
  We develop a novel architecture for artifact correction using the JPEG files quantization matrix. This allows our single model to achieve state-of-the-art performance over models trained for specific quality settings.
  arXiv  Detail & Related papers  (2020-04-17T00:10:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.