AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments

• URL: http://arxiv.org/abs/2410.08256v1
• Date: Thu, 10 Oct 2024 16:41:39 GMT
• Title: AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments
• Authors: Cheng Fang, Sicong Liu, Zimu Zhou, Bin Guo, Jiaqi Tang, Ke Ma, Zhiwen Yu,
• Abstract summary: This paper presents AdaShadow, a responsive test-time adaptation framework for non-stationary mobile data distribution and resource dynamics. AdaShadow addresses challenges in estimating layer importance and latency, as well as scheduling the optimal layer update plan. Results show that AdaShadow achieves the best accuracy-latency balance under continual shifts.
• Score: 24.606016498430407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences in evolving environments. Test-time adaptation (TTA) emerges as a promising solution by tuning model parameters with unlabeled live data immediately before prediction. However, TTA's unique forward-backward-reforward pipeline notably increases the latency over standard inference, undermining the responsiveness in time-sensitive mobile applications. This paper presents AdaShadow, a responsive test-time adaptation framework for non-stationary mobile data distribution and resource dynamics via selective updates of adaptation-critical layers. Although the tactic is recognized in generic on-device training, TTA's unsupervised and online context presents unique challenges in estimating layer importance and latency, as well as scheduling the optimal layer update plan. AdaShadow addresses these challenges with a backpropagation-free assessor to rapidly identify critical layers, a unit-based runtime predictor to account for resource dynamics in latency estimation, and an online scheduler for prompt layer update planning. Also, AdaShadow incorporates a memory I/O-aware computation reuse scheme to further reduce latency in the reforward pass. Results show that AdaShadow achieves the best accuracy-latency balance under continual shifts. At low memory and energy costs, Adashadow provides a 2x to 3.5x speedup (ms-level) over state-of-the-art TTA methods with comparable accuracy and a 14.8% to 25.4% accuracy boost over efficient supervised methods with similar latency.

Related papers

• CANet: ChronoAdaptive Network for Enhanced Long-Term Time Series Forecasting under Non-Stationarity [0.0]
  We introduce a novel architecture, ChoronoAdaptive Network (CANet), inspired by style-transfer techniques. The core of CANet is the Non-stationary Adaptive Normalization module, seamlessly integrating the Style Blending Gate and Adaptive Instance Normalization (AdaIN) experiments on real-world datasets validate CANet's superiority over state-of-the-art methods, achieving a 42% reduction in MSE and a 22% reduction in MAE.
  arXiv  Detail & Related papers  (2025-04-24T20:05:33Z)
• SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity [30.260783715373382]
  Test-time adaptation (TTA) has emerged to improve the performance of deep models by adapting them to unlabeled target data online. Yet, the significant memory cost, particularly in resource-constrained terminals, impedes the effective deployment of most backward-propagation-based TTA methods. To tackle memory constraints, we introduce SURGEON, a method that substantially reduces memory cost while preserving comparable accuracy improvements.
  arXiv  Detail & Related papers  (2025-03-26T09:27:09Z)
• 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. Our approach minimizes computational costs by dynamically updating normalization statistics without backpropagation. 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)
• Centaur: Robust End-to-End Autonomous Driving with Test-Time Training [84.78837437133234]
  We propose Centaur, which updates a planner's behavior via test-time training without relying on hand-engineered rules or cost functions. We develop a novel uncertainty measure, called Cluster Entropy, which is simple, interpretable, and compatible with state-of-the-art planning algorithms.
  arXiv  Detail & Related papers  (2025-03-14T17:59:41Z)
• PreMixer: MLP-Based Pre-training Enhanced MLP-Mixers for Large-scale Traffic Forecasting [30.055634767677823]
  In urban computing, precise and swift forecasting of time series data from traffic networks is crucial. Current research limitations because of inherent inefficiency of model and their unsuitability for large-scale traffic applications due to model complexity. This paper proposes a novel framework, named PreMixer, designed to bridge this gap. It features a predictive model and a pre-training mechanism, both based on the principles of Multi-Layer Perceptrons (MLP) Our framework achieves comparable state-of-theart performance while maintaining high computational efficiency, as verified by extensive experiments on large-scale traffic datasets.
  arXiv  Detail & Related papers  (2024-12-18T08:35:40Z)
• PPT: Pretraining with Pseudo-Labeled Trajectories for Motion Forecasting [90.47748423913369]
  State-of-the-art motion forecasting models rely on large curated datasets with manually annotated or heavily post-processed trajectories. PWT is a simple and scalable alternative that uses unprocessed and diverse trajectories automatically generated from off-the-shelf 3D detectors and tracking. It achieves strong performance across standard benchmarks particularly in low-data regimes, and in cross-domain, end-to-end and multi-class settings.
  arXiv  Detail & Related papers  (2024-12-09T13:48:15Z)
• FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction [11.146015814220858]
  FIRST is an algorithm that reduces inference latency by using layer-specific routers to select a subset of transformer layers adaptively for each input sequence. Our approach reveals that input adaptivity is critical - indeed, different task-specific middle layers play a crucial role in evolving hidden representations depending on task.
  arXiv  Detail & Related papers  (2024-10-16T12:45:35Z)
• STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting [11.208740750755025]
  Traffic is a cornerstone of smart city management enabling efficient allocation and transportation planning. Deep learning, with its ability to capture complex nonlinear patterns in data, has emerged as a powerful tool for traffic forecasting. graph neural networks (GCNs) and transformer-based models have shown promise, but their computational demands often hinder their application to realworld networks. We propose a noveltemporal graph transformer (STG) architecture, enabling efficient modeling of both global and local traffic patterns while maintaining a manageable computational footprint.
  arXiv  Detail & Related papers  (2024-10-01T04:15:48Z)
• Test-Time Model Adaptation with Only Forward Passes [68.11784295706995]
  Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. We propose a test-time Forward-Optimization Adaptation (FOA) method. FOA runs on quantized 8-bit ViT, outperforms gradient-based TENT on full-precision 32-bit ViT, and achieves an up to 24-fold memory reduction on ImageNet-C.
  arXiv  Detail & Related papers  (2024-04-02T05:34:33Z)
• SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving [27.776472262857045]
  This paper presents a Simple and effIcient Motion Prediction baseLine (SIMPL) for autonomous vehicles. We propose a compact and efficient global feature fusion module that performs directed message passing in a symmetric manner. As a strong baseline, SIMPL exhibits highly competitive performance on Argoverse 1 & 2 motion forecasting benchmarks.
  arXiv  Detail & Related papers  (2024-02-04T15:07:49Z)
• Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation [40.03897994619606]
  We introduce a layer-wise auto-weighting algorithm for continual and gradual TTA. We propose an exponential min-max scaler to make certain layers nearly frozen while mitigating outliers. Experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C show our method outperforms conventional continual and gradual TTA approaches.
  arXiv  Detail & Related papers  (2023-11-10T03:54:40Z)
• StreamYOLO: Real-time Object Detection for Streaming Perception [84.2559631820007]
  We endow the models with the capacity of predicting the future, significantly improving the results for streaming perception. We consider multiple velocities driving scene and propose Velocity-awared streaming AP (VsAP) to jointly evaluate the accuracy. Our simple method achieves the state-of-the-art performance on Argoverse-HD dataset and improves the sAP and VsAP by 4.7% and 8.2% respectively.
  arXiv  Detail & Related papers  (2022-07-21T12:03:02Z)
• Real-time Object Detection for Streaming Perception [84.2559631820007]
  Streaming perception is proposed to jointly evaluate the latency and accuracy into a single metric for video online perception. We build a simple and effective framework for streaming perception. Our method achieves competitive performance on Argoverse-HD dataset and improves the AP by 4.9% compared to the strong baseline.
  arXiv  Detail & Related papers  (2022-03-23T11:33:27Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• Amortized Auto-Tuning: Cost-Efficient Transfer Optimization for Hyperparameter Recommendation [83.85021205445662]
  We propose an instantiation--amortized auto-tuning (AT2) to speed up tuning of machine learning models. We conduct a thorough analysis of the multi-task multi-fidelity Bayesian optimization framework, which leads to the best instantiation--amortized auto-tuning (AT2)
  arXiv  Detail & Related papers  (2021-06-17T00:01:18Z)
• Deep Reinforcement Learning with Spatio-temporal Traffic Forecasting for Data-Driven Base Station Sleep Control [39.31623488192675]
  To meet the ever increasing mobile traffic demand in 5G era, base stations (BSs) have been densely deployed in radio access networks (RANs) to increase the network coverage and capacity. As the high density of BSs is designed to accommodate peak traffic, it would consume an unnecessarily large amount of energy if BSs are on during off-peak time. To save the energy consumption of cellular networks, an effective way is to deactivate some idle base stations that do not serve any traffic demand. In this paper, we develop a traffic-aware dynamic BS sleep control framework, named DeepBSC
  arXiv  Detail & Related papers  (2021-01-21T01:39:42Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.