Zobrazeno 1 - 10
of 39
pro vyhledávání: '"yang, Seunghan"'
Federated learning, a distributed learning paradigm, utilizes multiple clients to build a robust global model. In real-world applications, local clients often operate within their limited domains, leading to a `domain shift' across clients. Privacy c
Externí odkaz:
http://arxiv.org/abs/2407.08245
The customization of large language models (LLMs) for user-specified tasks gets important. However, maintaining all the customized LLMs on cloud servers incurs substantial memory and computational overheads, and uploading user data can also lead to p
Externí odkaz:
http://arxiv.org/abs/2406.07007
Few-shot keyword spotting (FS-KWS) models usually require large-scale annotated datasets to generalize to unseen target keywords. However, existing KWS datasets are limited in scale and gathering keyword-like labeled data is costly undertaking. To mi
Externí odkaz:
http://arxiv.org/abs/2309.00647
Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in real-world scenarios, most previous TTA approaches typically assume t
Externí odkaz:
http://arxiv.org/abs/2308.08810
Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains. Image augmentation based on Random Convolutions (RandConv), consisting of one convolution layer randomly
Externí odkaz:
http://arxiv.org/abs/2304.00424
This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained model trained
Externí odkaz:
http://arxiv.org/abs/2302.13435
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to alleviate the performance degradation due to the distribution shift between t
Externí odkaz:
http://arxiv.org/abs/2207.11707
This technical report describes the details of our TASK1A submission of the DCASE2021 challenge. The goal of the task is to design an audio scene classification system for device-imbalanced datasets under the constraints of model complexity. This rep
Externí odkaz:
http://arxiv.org/abs/2206.13909
Keyword spotting (KWS) plays an essential role in enabling speech-based user interaction on smart devices, and conventional KWS (C-KWS) approaches have concentrated on detecting user-agnostic pre-defined keywords. However, in practice, most user inte
Externí odkaz:
http://arxiv.org/abs/2206.13708
Deep learning models for verification systems often fail to generalize to new users and new environments, even though they learn highly discriminative features. To address this problem, we propose a few-shot domain generalization framework that learn
Externí odkaz:
http://arxiv.org/abs/2206.13700