Distributed Semantic Segmentation With Improved Rate-Distortion Trade-Off

• URL: http://arxiv.org/abs/2608.28684v1
• Date: Wed, 26 Aug 2026 10:14:04 GMT
• Title: Distributed Semantic Segmentation With Improved Rate-Distortion Trade-Off
• Abstract summary: We propose two novel source codecs that textitenable extremely lows, while improving RD performance.<n>We demonstrate the effectiveness of our proposed source codecs by achieving state-of-the-art performance in distributed semantic segmentation at below 0.2 bits per pixel, measured using the mean intersection-over-union metric on ADE20K (Cityscapes)
• Score: 17.99789411135595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Distributed deep neural networks (DNNs) for dense perception tasks such as semantic segmentation execute an encoder DNN on edge devices, and a decoder DNN typically on a large-scale cloud platform with a particular constraint on transmission bitrate. Recent works employ source codecs to enable bitrate-efficient transmission between the edge device and the cloud. However, as these approaches are typically bound to a particular type of source codec and alternative network architectures are often not explored, this results in a suboptimal rate-distortion (RD) trade-off in the low-bitrate regime. In this work, we propose two novel source codecs that \textit{enable extremely low bitrates, while improving RD performance}. We demonstrate the effectiveness of our proposed source codecs by achieving state-of-the-art performance in distributed semantic segmentation at below 0.2 (0.03) bits per pixel, measured using the mean intersection-over-union metric on ADE20K (Cityscapes).

Related papers

• Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding [56.066799081747845]
  The ever-growing size of neural networks poses serious challenges on resource-constrained devices.<n>We propose a novel post-training compression framework that combines rate-aware quantization with entropy coding.<n>Our method allows for very fast decoding and is compatible with arbitrary quantization grids.
  arXiv  Detail & Related papers  (2025-05-24T15:52:49Z)
• Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints [66.63250537475973]
  This paper introduces a diffusion-driven semantic communication framework with advanced VAE-based compression for bandwidth-constrained generative model.<n>Our experimental results demonstrate significant improvements in pixel-level metrics like peak signal to noise ratio (PSNR) and semantic metrics like learned perceptual image patch similarity (LPIPS)
  arXiv  Detail & Related papers  (2024-07-26T02:34:25Z)
• Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding [18.8803233019656]
  Deep neural networks (DNNs) execute one part of the network on edge devices and the other part on a large-scale cloud platform. In this work, we propose joint source and task decoding, as it allows for a smaller network size in the cloud. We demonstrate the effectiveness of our method by achieving a distributed semantic segmentation SOTA over a wide range of intersections.
  arXiv  Detail & Related papers  (2024-07-15T20:20:04Z)
• FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing [5.815300670677979]
  We introduce a novel framework for resource-conscious compression models and extensively evaluate our method in an asymmetric environment. Our method achieves 60% lower than a state-of-the-art SC method without decreasing accuracy and is up 16x faster than offloading with existing standards.
  arXiv  Detail & Related papers  (2023-02-21T14:03:22Z)
• Attention-based Feature Compression for CNN Inference Offloading in Edge Computing [93.67044879636093]
  This paper studies the computational offloading of CNN inference in device-edge co-inference systems. We propose a novel autoencoder-based CNN architecture (AECNN) for effective feature extraction at end-device. Experiments show that AECNN can compress the intermediate data by more than 256x with only about 4% accuracy loss.
  arXiv  Detail & Related papers  (2022-11-24T18:10:01Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• DeepWiVe: Deep-Learning-Aided Wireless Video Transmission [0.0]
  We present DeepWiVe, the first-ever end-to-end joint source-channel coding (JSCC) video transmission scheme. We use deep neural networks (DNNs) to map video signals to channel symbols, combining video compression, channel coding, and modulation steps into a single neural transform. Our results show that DeepWiVe can overcome the cliff-effect, which is prevalent in conventional separation-based digital communication schemes.
  arXiv  Detail & Related papers  (2021-11-25T11:34:24Z)
• Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation [98.05643473345474]
  We propose a novel decoder, termed dynamic neural representational decoder (NRD) As each location on the encoder's output corresponds to a local patch of the semantic labels, in this work, we represent these local patches of labels with compact neural networks. This neural representation enables our decoder to leverage the smoothness prior in the semantic label space, and thus makes our decoder more efficient.
  arXiv  Detail & Related papers  (2021-07-30T04:50:56Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence [32.03465747357384]
  In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a lightweight device such as a mobile phone or edge device. This paper presents a novel lightweight compression technique designed specifically to quantize and compress the features output by the intermediate layer of a split DNN.
  arXiv  Detail & Related papers  (2021-05-15T00:10:12Z)
• Scalable and Efficient Neural Speech Coding [24.959825692325445]
  This work presents a scalable and efficient neural waveform (NWC) for speech compression. The proposed CNN autoencoder also defines quantization and coding as a trainable module. Compared to the other autoregressive decoder-based neural speech, our decoder has significantly smaller architecture.
  arXiv  Detail & Related papers  (2021-03-27T00:10:16Z)
• Efficient Adaptation of Neural Network Filter for Video Compression [10.769305738505071]
  We present an efficient finetuning methodology for neural-network filters. The fine-tuning is performed at encoder side to adapt the neural network to the specific content that is being encoded. The proposed method achieves much faster than conventional finetuning approaches.
  arXiv  Detail & Related papers  (2020-07-28T14:24:28Z)

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.