paper-with-me

Papers

Self-Supervised Learning at the Edge: The Cost of Labeling

2025-07-09 · Roberto Pereira, Fernanda Famá, Asal Rangrazi, Marco Miozzo, Charalampos Kalalas, Paolo Dini arxiv

Contrastive learning (CL) has recently emerged as an alternative to traditional supervised machine learning solutions by enabling rich representations from unstructured and unlabeled data. However, CL and, more broadly, self-supervised learning (SSL) methods often demand a large amount of data and computational resources, posing challenges for deployment on resource-constrained edge devices. In this work, we explore the feasibility and efficiency of SSL techniques for edge-based learning, focusing on trade-offs between model performance and energy efficiency. In particular, we analyze how different SSL techniques adapt to limited computational, data, and energy budgets, evaluating their effectiveness in learning robust representations under resource-constrained settings. Moreover, we also consider the energy costs involved in labeling data and assess how semi-supervised learning may assist in reducing the overall energy consumed to train CL models. Through extensive experiments, we demonstrate that tailored SSL strategies can achieve competitive performance while reducing resource consumption by up to 4X, underscoring their potential for energy-efficient learning at the edge.

📄 PDF Abstract BibTeX arXiv:2507.07033

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised LearningContrastive Learning

Similar Papers 제목 키워드 기반

Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches

2025-12-15 · Taoran Sheng, Manfred Huber arxiv

Human activity recognition (HAR) using wearable sensors has advanced through various machine learning paradigms, each with inherent trade-offs between performance and labeling requirements. While fully supervised techniq…

Human Activity RecognitionSelf-Supervised LearningMulti-Task Learning

Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map

2021-03-01 · CVPR 2021 1 · Elmira Amirloo, Mohsen Rohani, Ershad Banijamali, Jun Luo 외

While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed. In contrast, while end-to-end architecture…

Autonomous DrivingMotion Planning

Unsupervised Dense Nuclei Detection and Segmentation with Prior Self-activation Map For Histology Images

2022-10-14 · Pingyi Chen, Chenglu Zhu, Zhongyi Shui, Jiatong Cai 외

The success of supervised deep learning models in medical image segmentation relies on detailed annotations. However, labor-intensive manual labeling is costly and inefficient, especially in dense object segmentation. To…

Image SegmentationMedical Image SegmentationSegmentationSelf-Supervised Learning+1

Mars Traversability Prediction: A Multi-modal Self-supervised Approach for Costmap Generation

2025-09-14 · Zongwu Xie, Kaijie Yun, Yang Liu, Yiming Ji 외 arxiv

We present a robust multi-modal framework for predicting traversability costmaps for planetary rovers. Our model fuses camera and LiDAR data to produce a bird's-eye-view (BEV) terrain costmap, trained self-supervised usi…

Domain Generalization

Uncertainty Based Active Learning Strategy for Interactive Weakly Supervised Learning through Data Programming

2020-10-15 · NeurIPS Workshop HAMLETS 2020 12 · Anonymous

Easy to build and reliable machine learning models are what all data analysts want. Although machine learning is advancing daily, the labeling cost for supervised learning and the black-box nature of machine learning are…

Active LearningBIG-bench Machine Learningtext-classificationText Classification+1