Search Results for author:
Found 18 papers, 2 papers with code
Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data
Few-shot keyword spotting (FS-KWS) models usually require large-scale annotated datasets to generalize to unseen target keywords.
Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts
Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference.
Progressive Random Convolutions for Single Domain Generalization
Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains.
Scalable Weight Reparametrization for Efficient Transfer Learning
Efficient transfer learning involves utilizing a pre-trained model trained on a larger dataset and repurposing it for downstream tasks with the aim of maximizing the reuse of the pre-trained model.
Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes
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 the source and target domains.
QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design
The goal of the task is to design an audio scene classification system for device-imbalanced datasets under the constraints of model complexity.
Personalized Keyword Spotting through Multi-task Learning
We design two personalized KWS tasks; (1) Target user Biased KWS (TB-KWS) and (2) Target user Only KWS (TO-KWS).
Domain Agnostic Few-shot Learning for Speaker Verification
Deep learning models for verification systems often fail to generalize to new users and new environments, even though they learn highly discriminative features.
Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting
We also verify our method on a standard benchmark, miniImageNet, and D-ProtoNets shows the state-of-the-art open-set detection rate in FSOSR.
Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to get domain-invariant features.
Distribution Estimation to Automate Transformation Policies for Self-Supervision
However, it is observed that image transformations already present in the dataset might be less effective in learning such self-supervised representations.
Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization
Moreover, we introduce an efficient architecture, BC-ResNet-ASC, a modified version of the baseline architecture with a limited receptive field.
Towards Robust Domain Generalization in 2D Neural Audio Processing
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to get domain-invariant features.
Robust Federated Learning with Noisy Labels
To solve these problems, we introduce a novel federated learning scheme that the server cooperates with local models to maintain consistent decision boundaries by interchanging class-wise centroids.
Arbitrary Style Transfer using Graph Instance Normalization
Style transfer is the image synthesis task, which applies a style of one image to another while preserving the content.
Associative Partial Domain Adaptation
Our Associative Partial Domain Adaptation (APDA) utilizes intra-domain association to actively select out non-trivial anomaly samples in each source-private class that sample-level weighting cannot handle.
Partial Domain Adaptation Using Graph Convolutional Networks
Although existing partial domain adaptation methods effectively down-weigh outliers' importance, they do not consider data structure of each domain and do not directly align the feature distributions of the same class in the source and target domains, which may lead to misalignment of category-level distributions.
Combinational Class Activation Maps for Weakly Supervised Object Localization
Most previous methods utilize the activation map corresponding to the highest activation source.
