paper-with-me

Papers

Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition

2025-09-10 · Matthew Nolan, Lina Yao, Robert Davidson arxiv

Human Activity Recognition (HAR) has seen significant advancements with the adoption of deep learning techniques, yet challenges remain in terms of data requirements, reliability and robustness. This paper explores a novel application of Ensemble Distribution Distillation (EDD) within a self-supervised learning framework for HAR aimed at overcoming these challenges. By leveraging unlabeled data and a partially supervised training strategy, our approach yields an increase in predictive accuracy, robust estimates of uncertainty, and substantial increases in robustness against adversarial perturbation; thereby significantly improving reliability in real-world scenarios without increasing computational complexity at inference. We demonstrate this with an evaluation on several publicly available datasets. The contributions of this work include the development of a self-supervised EDD framework, an innovative data augmentation technique designed for HAR, and empirical validation of the proposed method's effectiveness in increasing robustness and reliability.

📄 PDF Abstract BibTeX arXiv:2509.08225

Code (0)

등록된 구현이 없습니다.

Tasks

Human Activity RecognitionSelf-Supervised LearningData Augmentation

Similar Papers 제목 키워드 기반

Self-Distribution Distillation: Efficient Uncertainty Estimation

2022-03-15 · Yassir Fathullah, Mark J. F. Gales

Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model's prediction to ensure appropriate decisions are made by the system.…

Out-of-Distribution Detection

Data Distillation: Towards Omni-Supervised Learning

2017-12-12 · CVPR 2018 6 · Ilija Radosavovic, Piotr Dollár, Ross Girshick, Georgia Gkioxari 외

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lo…

Keypoint Detectionobject-detectionObject Detection

Ensemble knowledge distillation of self-supervised speech models

2023-02-24 · Kuan-Po Huang, Tzu-hsun Feng, Yu-Kuan Fu, Tsu-Yuan Hsu 외

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we per…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Emotion RecognitionKnowledge Distillation+4

EDF: Ensemble, Distill, and Fuse for Easy Video Labeling

2018-12-10 · Giulio Zhou, Subramanya Dulloor, David G. Andersen, Michael Kaminsky

We present a way to rapidly bootstrap object detection on unseen videos using minimal human annotations. We accomplish this by combining two complementary sources of knowledge (one generic and the other specific) using b…

Data AugmentationObjectobject-detectionObject Detection

Semi-Supervised Learning with Online Knowledge Distillation for Skin Lesion Classification

2025-08-15 · Siyamalan Manivannan arxiv

Deep Learning has emerged as a promising approach for skin lesion analysis. However, existing methods mostly rely on fully supervised learning, requiring extensive labeled data, which is challenging and costly to obtain.…

Skin Lesion ClassificationKnowledge DistillationEnsemble Learning