Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches [PDF]
SensorsHuman activity recognition (HAR) using wearable sensors has advanced through various machine learning paradigms, each with inherent trade-offs between performance and labeling requirements.
Taoran Sheng, Manfred Huber
doaj +2 more sources
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units [PDF]
IEEE/ACM Transactions on Audio Speech and Language Processing, 2021 Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound ...
Wei-Ning Hsu +5 more
semanticscholar +1 more source
Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning [PDF]
Jisuanji kexue, 2022 Most of the traditional multi-label classification algorithms use supervised learning,but in real life,there are many unlabeled data.Manual tagging of all required data is costly.Semi-supervised learning algorithms can work with a large amount of ...
WU Hong-xin, HAN Meng, CHEN Zhi-qiang, ZHANG Xi-long, LI Mu-hang
doaj +1 more source
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture [PDF]
Computer Vision and Pattern Recognition, 2023 This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self ...
Mahmoud Assran +7 more
semanticscholar +1 more source
Emerging Properties in Self-Supervised Vision Transformers [PDF]
IEEE International Conference on Computer Vision, 2021 In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) [16] that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this architecture works
Mathilde Caron +6 more
semanticscholar +1 more source
SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning [PDF]
International Conference on Learning Representations, 2023 The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance.
Hao Chen +8 more
semanticscholar +1 more source
Masked Autoencoders for Point Cloud Self-supervised Learning [PDF]
European Conference on Computer Vision, 2022 As a promising scheme of self-supervised learning, masked autoencoding has significantly advanced natural language processing and computer vision. Inspired by this, we propose a neat scheme of masked autoencoders for point cloud self-supervised learning,
Yatian Pang +5 more
semanticscholar +1 more source
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [PDF]
Computer Vision and Pattern Recognition, 2021 We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage framework for building anomaly detectors using normal training data only.
Chun-Liang Li +3 more
semanticscholar +1 more source
Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning [PDF]
Computer Vision and Pattern Recognition, 2022 Vision Transformers (ViTs) and their multi-scale and hierarchical variations have been successful at capturing image representations but their use has been generally studied for low-resolution images (e.g. 256 × 256, 384 × 384). For gigapixel whole-slide
Richard J. Chen +6 more
semanticscholar +1 more source