Search Results for author:
Found 5 papers, 0 papers with code
Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs
To address this issue, We propose a language-assisted diagnostic method that uses texts instead of images to diagnose bugs in vision models based on multi-modal models (eg CLIP).
A Multi-Task Deep Learning Approach for Sensor-based Human Activity Recognition and Segmentation
Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years.
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition
Compared with SimCLR, it redefines the negative pairs in the contrastive loss function by using unsupervised clustering methods to generate soft labels that mask other samples of the same cluster to avoid regarding them as negative samples.
Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data
Deep network models perform excellently on In-Distribution (ID) data, but can significantly fail on Out-Of-Distribution (OOD) data.
Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition
The experiment results show that the resampling augmentation method outperforms all state-of-the-art methods under a small amount of labeled data, on SimCLRHAR and MoCoHAR, with mean F1-score as the evaluation metric.
