Related papers: Improving Distribution Alignment with Diversity-ba…
Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the…
Domain adaptation is crucial in many real-world applications where the distribution of the training data differs from the distribution of the test data. Previous Deep Learning-based approaches to domain adaptation need to be trained jointly…
Micro-batch clipping, a gradient clipping method, has recently shown potential in enhancing auto-speech recognition (ASR) model performance. However, the underlying mechanism behind this improvement remains mysterious, particularly the…
Detecting the presence of animal vocalisations in nature is essential to study animal populations and their behaviors. A recent development in the field is the introduction of the task known as few-shot bioacoustic sound event detection,…
Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrowed from the single source setting. However, with diverse…
Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its…
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques…
In the training of large deep neural networks, there is a need for vast amounts of training data. To meet this need, data is collected from multiple domains, such as Wikipedia and GitHub. These domains are heterogeneous in both data quality…
In machine learning models, the estimation of errors is often complex due to distribution bias, particularly in spatial data such as those found in environmental studies. We introduce an approach based on the ideas of importance sampling to…
Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, unsupervised domain adaptation (UDA) has achieved significant progress in addressing this issue via learning…
Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…
Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of these shifts, for…
Blood cell identification is critical for hematological analysis as it aids physicians in diagnosing various blood-related diseases. In real-world scenarios, blood cell image datasets often present the issues of domain shift and data…
State-of-the-art anomalous sound detection (ASD) systems in domain-shifted conditions rely on projecting audio signals into an embedding space and using distance-based outlier detection to compute anomaly scores. One of the major…
Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do…
In this paper, we propose a stochastic optimization method that adaptively controls the sample size used in the computation of gradient approximations. Unlike other variance reduction techniques that either require additional storage or the…
In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…
We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…
Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representative ones. Although the introduction of generative models has…
Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a label-scarce domain (the target domain). Most domain adaptation methods require the co-existence of source and target domain samples to…