Related papers: ConceptScope: Characterizing Dataset Bias via Dise…

A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a…

The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading…

While machine learning approaches to visual emotion recognition offer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts. Our analysis identifies an important…

Machine learning systems are increasingly deployed in high-stakes domains, yet they remain vulnerable to bias systematic disparities that disproportionately impact specific demographic groups. Traditional bias detection methods often depend…

Discovering visual knowledge from weakly labeled data is crucial to scale up computer vision recognition system, since it is expensive to obtain fully labeled data for a large number of concept categories. In this paper, we propose…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on the data they are fed with and can…

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample…

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to…

In computer vision, a prevailing method for quantifying dataset bias is to train a model to distinguish between datasets. High classification accuracy is then interpreted as evidence of meaningful semantic differences. This approach assumes…

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…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Time-series data is widely studied in various scenarios, like weather forecast, stock market, customer behavior analysis. To comprehensively learn about the dynamic environments, it is necessary to comprehend features from multiple data…

High-performing vision language models still produce incorrect answers, yet their failure modes are often difficult to explain. To make model internals more accessible and enable systematic debugging, we introduce VisualScratchpad, an…

Streaming sources of data are becoming more common as the ability to collect data in real-time grows. A major concern in dealing with data streams is concept drift, a change in the distribution of data over time, for example, due to changes…

Most datasets used for supervised machine learning consist of a single label per data point. However, in cases where more information than just the class label is available, would it be possible to train models more efficiently? We…

Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets due to two inconsistencies among detection datasets: taxonomy…

Classification models learn to generalize the associations between data samples and their target classes. However, researchers have increasingly observed that machine learning practice easily leads to systematic errors in AI applications, a…