Related papers: CoBA: Counterbias Text Augmentation for Mitigating…

This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA),…

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…

Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Recent progress in self-supervised learning has demonstrated promising results in multiple visual tasks. An important ingredient in high-performing self-supervised methods is the use of data augmentation by training models to place…

Being widely used in learning unbiased visual question answering (VQA) models, Data Augmentation (DA) helps mitigate language biases by generating extra training samples beyond the original samples. While today's DA methods can generate…

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

Models trained on datasets with texture bias usually perform poorly on out-of-distribution samples since biased representations are embedded into the model. Recently, various image translation and debiasing methods have attempted to…

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e.g., race, gender,…

Large foundation models trained on extensive datasets demonstrate strong zero-shot capabilities in various domains. To replicate their success when data and model size are constrained, knowledge distillation has become an established tool…

Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily…

Paraphrase detection is an important task in text analytics with numerous applications such as plagiarism detection, duplicate question identification, and enhanced customer support helpdesks. Deep models have been proposed for representing…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Self-supervised representation learning on image-text data facilitates crucial medical applications, such as image classification, visual grounding, and cross-modal retrieval. One common approach involves contrasting semantically similar…

Unsupervised sentence representation learning aims to transform input sentences into fixed-length vectors enriched with intricate semantic information while obviating the reliance on labeled data. Recent strides within this domain have been…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

Despite dropout's ubiquity in machine learning, its effectiveness as a form of data augmentation remains under-explored. We address two key questions: (i) When is dropout effective as an augmentation strategy? (ii) Is dropout uniquely…

Knowledge graphs (KGs) often contain various errors. Previous works on detecting errors in KGs mainly rely on triplet embedding from graph structure. We conduct an empirical study and find that these works struggle to discriminate noise…