Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines

• URL: http://arxiv.org/abs/2511.05836v1
• Date: Sat, 08 Nov 2025 04:05:24 GMT
• Title: Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines
• Abstract summary: Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision into real-world applications.<n>Most ICM frameworks utilize learned image compression (LIC) models that operate at a fixed rate and require separate training for each target.<n>We propose a training-free, adaptive quantization step size control scheme that enables flexible entropy adjustment.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision into real-world applications. However, most ICM frameworks utilize learned image compression (LIC) models that operate at a fixed rate and require separate training for each target bitrate, which may limit their practical applications. Existing variable rate LIC approaches mitigate this limitation but typically depend on training, increasing computational cost and deployment complexity. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free, adaptive quantization step size control scheme that enables flexible bitrate adjustment. By leveraging both channel-wise entropy dependencies and spatial scale parameters predicted by the hyperprior network, the proposed method preserves semantically important regions while coarsely quantizing less critical areas. The bitrate can be continuously controlled through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate method.

Related papers

• Training-Free Continuous Bitrate Control for Scalable Image Coding for Humans and Machines [0.0]
  We propose a training-free variable-rate scalable image coding framework.<n>The proposed method achieves continuous control while preserving high-scale information in the machine and enhancement layers.
  arXiv  Detail & Related papers  (2026-05-29T07:37:47Z)
• Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning [52.41928980786654]
  We propose PathCTM to enable token-efficient scale-space continuous reasoning for gigapixel whole slide images.<n>PathCTM formulates diagnostic inference as a dynamic sequential information pursuit.<n>It reduces the number of required image patches by 95.95% and shortens inference time by approximately 95.62%, while maintaining AUC without degradation.
  arXiv  Detail & Related papers  (2026-05-19T07:46:44Z)
• TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration [64.32072516882947]
  Diffusion Policy excels in embodied control but suffers from high inference latency and computational cost.<n>We propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP)<n>TS-DP achieves up to 4.17 times faster inference with over 94% accepted drafts, reaching an inference frequency of 25 Hz.
  arXiv  Detail & Related papers  (2025-12-13T07:53:14Z)
• BitSnap: Checkpoint Sparsification and Quantization in LLM Training [12.420041526429287]
  Large language models (LLMs) continue to grow in size and complexity.<n> efficient checkpoint saving&loading has become crucial for managing storage, memory usage, and fault tolerance in LLM training.<n>This paper proposes a novel checkpoint sparsification and quantization method that adapts dynamically to different training stages and model architectures.
  arXiv  Detail & Related papers  (2025-11-15T22:48:59Z)
• DynaQuant: Dynamic Mixed-Precision Quantization for Learned Image Compression [13.90943929367355]
  DynaQuant is a novel framework for dynamic mixed-precision quantization.<n>We introduce a data-driven, dynamic bit-width selector that learns to assign an optimal bit precision to each layer.<n>Our fully dynamic approach offers substantial flexibility in balancing rate-distortion (R-D) performance and computational cost.
  arXiv  Detail & Related papers  (2025-11-11T06:58:38Z)
• Adacc: An Adaptive Framework Unifying Compression and Activation Recomputation for LLM Training [40.371351103295765]
  Training large language models (LLMs) is often constrained by GPU memory limitations.<n>Adacc is the first adaptive memory optimization framework that unifies activation recomputation and data compression.<n>Adacc improves training throughput by 1.01x to 1.37x compared to state-of-the-art frameworks.
  arXiv  Detail & Related papers  (2025-08-01T17:39:25Z)
• EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning [53.88000987041739]
  Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time.<n>We propose the Elastic Knowledge Preservation and Compensation (EKPC) method, integrating Importance-aware importance Regularization (IPR) and Trainable Semantic Drift Compensation (TSDC) for CIL.
  arXiv  Detail & Related papers  (2025-06-14T05:19:58Z)
• CALLIC: Content Adaptive Learning for Lossless Image Compression [64.47244912937204]
  CALLIC sets a new state-of-the-art (SOTA) for learned lossless image compression.<n>We propose a content-aware autoregressive self-attention mechanism by leveraging convolutional gating operations.<n>During encoding, we decompose pre-trained layers, including depth-wise convolutions, using low-rank matrices and then adapt the incremental weights on testing image by Rate-guided Progressive Fine-Tuning (RPFT)<n>RPFT fine-tunes with gradually increasing patches that are sorted in descending order by estimated entropy, optimizing learning process and reducing adaptation time.
  arXiv  Detail & Related papers  (2024-12-23T10:41:18Z)
• HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization [55.972018549438964]
  Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy.<n>We propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable fine-tuning of LLMs in heterogeneous environments.<n> Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.
  arXiv  Detail & Related papers  (2024-11-10T19:59:54Z)
• Accelerating Augmentation Invariance Pretraining [7.772780341646099]
  We tackle the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs) We propose an acceleration framework, leveraging ViT's unique ability to generalize across inputs of varying sequence lengths. Our method employs a mix of sequence compression strategies, including randomized token dropout and flexible patch scaling, to reduce the cost of gradient estimation and accelerate convergence.
  arXiv  Detail & Related papers  (2024-10-27T21:53:33Z)
• MOSEAC: Streamlined Variable Time Step Reinforcement Learning [14.838483990647697]
  We introduce the Multi-Objective Soft Elastic Actor-Critic (MOSEAC) method. MOSEAC features an adaptive reward scheme based on observed trends in task rewards during training. We validate the MOSEAC method through simulations in a Newtonian kinematics environment.
  arXiv  Detail & Related papers  (2024-06-03T16:51:57Z)
• LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression [27.02281402358164]
  We propose Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression. We introduce a few large kernelbased depth-wise convolutions to reduce more redundancy while maintaining modest complexity. Our LLIC models achieve state-of-the-art performances and better trade-offs between performance and complexity.
  arXiv  Detail & Related papers  (2023-04-19T11:19:10Z)
• Unifying Synergies between Self-supervised Learning and Dynamic Computation [53.66628188936682]
  We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-01-22T17:12:58Z)
• Remote Multilinear Compressive Learning with Adaptive Compression [107.87219371697063]
  MultiIoT Compressive Learning (MCL) is an efficient signal acquisition and learning paradigm for multidimensional signals. We propose a novel optimization scheme that enables such a feature for MCL models.
  arXiv  Detail & Related papers  (2021-09-02T19:24:03Z)

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.