Efficient Edge Test-Time Adaptation via Latent Feature Coordinate Correction

• URL: http://arxiv.org/abs/2510.11068v1
• Date: Mon, 13 Oct 2025 07:08:52 GMT
• Title: Efficient Edge Test-Time Adaptation via Latent Feature Coordinate Correction
• Authors: Xinyu Luo, Jie Liu, Kecheng Chen, Junyi Yang, Bo Ding, Arindam Basu, Haoliang Li,
• Abstract summary: We propose a novel test-time adaptation (TTA) method tailored for edge devices (TED)<n>TED employs forward-only coordinate optimization in the principal subspace of latent using the covariance matrix adaptation evolution strategy (CMA-ES)<n>TED achieves state-of-the-art performance while $textitreducing computational complexity by up to 63 times$, offering a practical and scalable solution for real-world edge applications.
• Score: 43.48832321879385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Edge devices face significant challenges due to limited computational resources and distribution shifts, making efficient and adaptable machine learning essential. Existing test-time adaptation (TTA) methods often rely on gradient-based optimization or batch processing, which are inherently unsuitable for resource-constrained edge scenarios due to their reliance on backpropagation and high computational demands. Gradient-free alternatives address these issues but often suffer from limited learning capacity, lack flexibility, or impose architectural constraints. To overcome these limitations, we propose a novel single-instance TTA method tailored for edge devices (TED), which employs forward-only coordinate optimization in the principal subspace of latent using the covariance matrix adaptation evolution strategy (CMA-ES). By updating a compact low-dimensional vector, TED not only enhances output confidence but also aligns the latent representation closer to the source latent distribution within the latent principal subspace. This is achieved without backpropagation, keeping the model parameters frozen, and enabling efficient, forgetting-free adaptation with minimal memory and computational overhead. Experiments on image classification and keyword spotting tasks across the ImageNet and Google Speech Commands series datasets demonstrate that TED achieves state-of-the-art performance while $\textit{reducing computational complexity by up to 63 times}$, offering a practical and scalable solution for real-world edge applications. Furthermore, we successfully $\textit{deployed TED on the ZYNQ-7020 platform}$, demonstrating its feasibility and effectiveness for resource-constrained edge devices in real-world deployments.

Related papers

• LQA: A Lightweight Quantized-Adaptive Framework for Vision-Language Models on the Edge [12.772499009055194]
  We propose a lightweight, quantized-adaptive framework for Vision-Language Models (VLMs)<n>We introduce Selective Hybrid Quantization (SHQ) and a quantized, gradient-free adaptation mechanism to enable robust and efficient VLM deployment on resource-constrained hardware.<n> Experiments show that LQA improves overall adaptation performance by 4.5%, uses less memory, and significantly outperforms gradient-based TTA methods.
  arXiv  Detail & Related papers  (2026-02-08T07:37:37Z)
• Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing [21.83974330459537]
  Visual Place Recognition (VPR) has advanced significantly with high-capacity foundation models like DINOv2.<n>Their substantial computational cost makes deployment on resource-constrained devices impractical.<n>We introduce an efficient asymmetric VPR framework that incorporates a high-capacity gallery model for offline feature extraction with a lightweight query network for online processing.
  arXiv  Detail & Related papers  (2025-12-15T07:30:17Z)
• Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning [52.03884701766989]
  offline reinforcement learning (RL) algorithms typically impose constraints on action selection.<n>We propose a new neighborhood constraint that restricts action selection in the Bellman target to the union of neighborhoods of dataset actions.<n>We develop a simple yet effective algorithm, Adaptive Neighborhood-constrained Q learning (ANQ), to perform Q learning with target actions satisfying this constraint.
  arXiv  Detail & Related papers  (2025-11-04T13:42:05Z)
• EdgeInfinite-Instruct: Bridging SFT-Based Optimization and NPU-Level Efficiency for Edge Devices [3.5487823143282657]
  This paper introduces a Segmented Supervised Fine-Tuning (S-SFT) strategy tailored to long-sequence tasks such as summarization and question answering.<n> Experiments on long-context benchmarks and real-world mobile tasks show that our approach improves domain-specific performance while maintaining efficiency on NPU-accelerated edge devices.
  arXiv  Detail & Related papers  (2025-08-01T07:03:16Z)
• Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation [0.6554326244334866]
  We present an efficient and scalable Federated Learning framework tailored for real-world client adaptation in industrial settings.<n>By freezing the backbone and classifier during client adaptation on resource-constrained devices, we allow the domain adaptive linear layer to handle target domain adaptation.<n>Our framework accommodates sporadic model updates within resource-constrained environments, ensuring practical and seamless deployment.
  arXiv  Detail & Related papers  (2025-07-14T11:18:33Z)
• The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks [56.37880529653111]
  The demand for large computation model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications.<n>In this paper, we investigate the LAIM-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment.
  arXiv  Detail & Related papers  (2025-05-14T08:18:55Z)
• LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices [13.355021314836852]
  We present LeanTTA, a novel backpropagation-free and stateless framework for quantized test-time adaptation tailored to edge devices.<n>Our approach minimizes computational costs by dynamically updating normalization statistics without backpropagation.<n>We validate our framework across sensor modalities, demonstrating significant improvements over state-of-the-art TTA methods.
  arXiv  Detail & Related papers  (2025-03-20T06:27:09Z)
• Efficient Domain Adaptation of Multimodal Embeddings using Constrastive Learning [0.08192907805418582]
  Current approaches either yield subpar results when using pretrained models without task-specific adaptation, or require substantial computational resources for fine-tuning.<n>We propose a novel method for adapting foundational, multimodal embeddings to downstream tasks, without the need of expensive fine-tuning processes.
  arXiv  Detail & Related papers  (2025-02-04T06:30:12Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)
• Deep Adaptive Inference Networks for Single Image Super-Resolution [72.7304455761067]
  Single image super-resolution (SISR) has witnessed tremendous progress in recent years owing to the deployment of deep convolutional neural networks (CNNs) In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR) Our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth.
  arXiv  Detail & Related papers  (2020-04-08T10:08:20Z)

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.