paper-with-me

홈 › Papers

Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognition

2024-12-28 · Junyao Wang, Mohammad Abdullah Al Faruque

Deep learning has been widely adopted for human activity recognition (HAR) while generalizing a trained model across diverse users and scenarios remains challenging due to distribution shifts. The inherent low-resource challenge in HAR, i.e., collecting and labeling adequate human-involved data can be prohibitively costly, further raising the difficulty of tackling DS. We propose TACO, a novel transformer-based contrastive meta-learning approach for generalizable HAR. TACO addresses DS by synthesizing virtual target domains in training with explicit consideration of model generalizability. Additionally, we extract expressive feature with the attention mechanism of Transformer and incorporate the supervised contrastive loss function within our meta-optimization to enhance representation learning. Our evaluation demonstrates that TACO achieves notably better performance across various low-resource DS scenarios.

📄 PDF Abstract BibTeX arXiv:2412.20290

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionHuman Activity RecognitionMeta-LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning

2023-05-25 · Xin Qin, Jindong Wang, Shuo Ma, Wang Lu 외

Human activity recognition (HAR) is a time series classification task that focuses on identifying the motion patterns from human sensor readings. Adequate data is essential but a major bottleneck for training a generaliz…

Activity RecognitionContrastive LearningDiversityHuman Activity Recognition+3

CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning

2021-09-30 · Garrett Wilson, Janardhan Rao Doppa, Diane J. Cook

Unsupervised domain adaptation (UDA) provides a strategy for improving machine learning performance in data-rich (target) domains where ground truth labels are inaccessible but can be found in related (source) domains. I…

Activity RecognitionContrastive LearningData AugmentationDomain Adaptation+4

MetaboNet: The Largest Publicly Available Consolidated Dataset for Type 1 Diabetes Management

2026-01-16 · Miriam K. Wolff, Peter Calhoun, Eleonora Maria Aiello, Yao Qin 외 arxiv

Progress in Type 1 Diabetes (T1D) algorithm development is limited by the fragmentation and lack of standardization across existing T1D management datasets. Current datasets differ substantially in structure and are time…

Driver Activity Classification Using Generalizable Representations from Vision-Language Models

2024-04-23 · Ross Greer, Mathias Viborg Andersen, Andreas Møgelmose, Mohan Trivedi

Driver activity classification is crucial for ensuring road safety, with applications ranging from driver assistance systems to autonomous vehicle control transitions. In this paper, we present a novel approach leveragin…

Action Recognition

BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition

2026-05-08 · Yize Cai, Rui Feng, Anlan Yu, Baoshen Guo 외 arxiv

Human Activity Recognition (HAR) from wearable sensors supports broad healthcare and behavior science applications. However, data heterogeneity and the scarcity of labeled data limit its real-world generalization. Recent…

Human Activity RecognitionSelf-Supervised Learning