Related papers: SSMBA: Self-Supervised Manifold Based Data Augment…

We present analyses of data augmentation for machine learning redshift estimation. Data augmentation makes a training sample more closely resemble a test sample, if the two base samples differ, in order to improve measured statistics of the…

Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on narrow, task-specific data, often degrading their general knowledge and reasoning abilities. We propose SA-SFT, a lightweight…

Data augmentation techniques play an important role in enhancing the performance of deep learning models. Despite their proven benefits in computer vision tasks, their application in the other domains remains limited. This paper proposes a…

Semi-Supervised Domain Adaptation (SSDA) leverages knowledge from a fully labeled source domain to classify data in a partially labeled target domain. Due to the limited number of labeled samples in the target domain, there can be intrinsic…

Self-supervised representation learning follows a paradigm of withholding some part of the data and tasking the network to predict it from the remaining part. Among many techniques, data augmentation lies at the core for creating the…

In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization. Recent strong augmentation…

Contrastive learning has recently achieved compelling performance in unsupervised sentence representation. As an essential element, data augmentation protocols, however, have not been well explored. The pioneering work SimCSE resorting to a…

Pathological diagnosis is highly reliant on image analysis, where Regions of Interest (ROIs) serve as the primary basis for diagnostic evidence, while whole-slide image (WSI)-level tasks primarily capture aggregated patterns. To extract…

Despite its widespread adoption as the prominent neural architecture, the Transformer has spurred several independent lines of work to address its limitations. One such approach is selective state space models, which have demonstrated…

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…

Maximum Mean Discrepancy (MMD) is widely used in a number of domain adaptation (DA) methods and shows its effectiveness in aligning data distributions across domains. However, in previous DA research, MMD-based DA methods focus mostly on…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data…

The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their generalization problem, where their performance drastically decreases when evaluated on examples that differ from the training dataset, known…

Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cost of manually labeling data in real-world applications such…

A dominant approach for addressing unsupervised domain adaptation is to map data points for the source and the target domains into an embedding space which is modeled as the output-space of a shared deep encoder. The encoder is trained to…

Automatic data augmentation (AutoDA) plays an important role in enhancing the generalization of neural networks. However, mainstream AutoDA methods often encounter two challenges: either the search process is excessively time-consuming,…

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial attacks by adding…

As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasing popularity. While extensive studies…

Data augmentation integrates domain knowledge into a dataset by making domain-informed modifications to existing data points. For example, image data can be augmented by duplicating images in different tints or orientations, thereby…