Related papers: Dataset Bias Mitigation in Multiple-Choice Visual …

AI-enhanced personality assessments are increasingly shaping hiring decisions, using affective computing to predict traits from the Big Five (OCEAN) model. However, integrating AI into these assessments raises ethical concerns, especially…

Machine learning models built on datasets containing discriminative instances attributed to various underlying factors result in biased and unfair outcomes. It's a well founded and intuitive fact that existing bias mitigation strategies…

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data…

Vision Language Models (VLMs) such as CLIP are powerful models; however they can exhibit unwanted biases, making them less safe when deployed directly in applications such as text-to-image, text-to-video retrievals, reverse search, or…

Synthetic data is emerging as a substitute for authentic data to solve ethical and legal challenges in handling authentic face data. The current models can create real-looking face images of people who do not exist. However, it is a known…

The imbalance problem is widespread in the field of machine learning, which also exists in multimodal learning areas caused by the intrinsic discrepancy between modalities of samples. Recent works have attempted to solve the modality…

Missing data can pose a challenge for machine learning (ML) modeling. To address this, current approaches are categorized into feature imputation and label prediction and are primarily focused on handling missing data to enhance ML…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Metaphor detection (MD) suffers from limited training data. In this paper, we started with a linguistic rule called Metaphor Identification Procedure and then proposed a novel multi-task learning framework to transfer knowledge in basic…

Contrastive Language-Image Pre-training (CLIP) achieves remarkable performance in various downstream tasks through the alignment of image and text input embeddings and holds great promise for anomaly detection. However, our empirical…

Learning with limited data is one of the biggest problems of machine learning. Current approaches to this issue consist in learning general representations from huge amounts of data before fine-tuning the model on a small dataset of…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Recently, many bias detection methods have been proposed to determine the level of bias a large language model captures. However, tests to identify which parts of a large language model are responsible for bias towards specific groups…

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

Recent work on counterfactual visual explanations has contributed to making artificial intelligence models more explainable by providing visual perturbation to flip the prediction. However, these approaches neglect the causal relationships…

In this early study, we observe an Easy-Options Bias (EOB) issue in some multiple-choice Visual Question Answering (VQA) benchmarks such as MMStar, RealWorldQA, SEED-Bench, Next-QA, STAR benchmark and Video-MME. This bias allows…

ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversarial examples and…

It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…

Visual question answering (VQA) models respond to open-ended natural language questions about images. While VQA is an increasingly popular area of research, it is unclear to what extent current VQA architectures learn key semantic…

Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic…