Related papers: Data Fine-tuning
Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to…
Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other…
The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…
Deep models trained on large amounts of data often incorporate implicit biases present during training time. If later such a bias is discovered during inference or deployment, it is often necessary to acquire new data and retrain the model.…
How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on…
Data Augmentation (DA) is frequently used to provide additional training data without extra human annotation automatically. However, data augmentation may introduce noisy data that impairs training. To guarantee the quality of augmented…
Facial recognition has become a widely used method for authentication and identification, with applications for secure access and locating missing persons. Its success is largely attributed to deep learning, which leverages large datasets…
Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a…
Pre-training on large-scale datasets and then fine-tuning on downstream tasks have become a standard practice in deep learning. However, pre-training data often contain label noise that may adversely affect the generalization of the model.…
Unconstrained face recognition is an active research area among computer vision and biometric researchers for many years now. Still the problem of face recognition in low quality photos has not been well-studied so far. In this paper, we…
Motivated by the problem of tuning hyperparameters in machine learning, we present a new approach for gradually and adaptively optimizing an unknown function using estimated gradients. We validate the empirical performance of the proposed…
Facial expressions are crucial to human communication, offering insights into emotional states. This study examines how specific facial features influence emotion classification, using facial perturbations on the Fer2013 dataset. As…
The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life. However, the omnipresent and all-encompassing nature of the data collection can generate privacy concerns. Hence, there is a…
Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…
Bias in data can have unintended consequences that propagate to the design, development, and deployment of machine learning models. In the financial services sector, this can result in discrimination from certain financial instruments and…
In recent years, large "in the wild" face datasets have been released in an attempt to facilitate progress in tasks such as face detection, face recognition, and other tasks. Most of these datasets are acquired from webpages with automatic…
This paper studies "unsupervised finetuning", the symmetrical problem of the well-known "supervised finetuning". Given a pretrained model and small-scale unlabeled target data, unsupervised finetuning is to adapt the representation…
Facial analysis models are increasingly applied in real-world applications that have significant impact on peoples' lives. However, as literature has shown, models that automatically classify facial attributes might exhibit algorithmic…
We study utilizing auxiliary information in training data to improve the trustworthiness of machine learning models. Specifically, in the context of image classification, we propose to optimize a training objective that incorporates…
Recent studies have shown how self-supervised models can produce accurate speech quality predictions. Speech representations generated by the pre-trained wav2vec 2.0 model allows constructing robust predicting models using small amounts of…