Related papers: Leveraging Human-Machine Interactions for Computer…

Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To overcome the challenges of subjective and noisy engagement…

Recent advancements in medical imaging and artificial intelligence (AI) have greatly enhanced diagnostic capabilities, but the development of effective deep learning (DL) models is still constrained by the lack of high-quality annotated…

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…

Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to learn a classification model. While quality labeled dialogue…

As machine learning models continue to increase in complexity, collecting large hand-labeled training sets has become one of the biggest roadblocks in practice. Instead, weaker forms of supervision that provide noisier but cheaper labels…

Partial multi-label learning aims to extract knowledge from incompletely annotated data, which includes known correct labels, known incorrect labels, and unknown labels. The core challenge lies in accurately identifying the ambiguous…

Multi-label image recognition is a practical and challenging task compared to single-label image classification. However, previous works may be suboptimal because of a great number of object proposals or complex attentional region…

We propose a simple approach which combines the strengths of probabilistic graphical models and deep learning architectures for solving the multi-label classification task, focusing specifically on image and video data. First, we show that…

Object detection has advanced rapidly in recent years, driven by increasingly large and diverse datasets. However, label errors often compromise the quality of these datasets and affect the outcomes of training and benchmark evaluations.…

Semantic segmentation is a challenging computer vision task demanding a significant amount of pixel-level annotated data. Producing such data is a time-consuming and costly process, especially for domains with a scarcity of experts, such as…

Compared with multi-class classification, multi-label classification that contains more than one class is more suitable in real life scenarios. Obtaining fully labeled high-quality datasets for multi-label classification problems, however,…

Medical images often contain multiple labels with imbalanced distributions and co-occurrence, leading to bias in multi-label medical image classification. Close collaboration between medical professionals and machine learning practitioners…

Datasets in the computer vision academic research community are primarily static. Once a dataset is accepted as a benchmark for a computer vision task, researchers working on this task will not alter it in order to make their results…

In multi-label text classification, each textual document can be assigned with one or more labels. Due to this nature, the multi-label text classification task is often considered to be more challenging compared to the binary or multi-class…

Modern computer vision foundation models are trained on massive amounts of data, incurring large economic and environmental costs. Recent research has suggested that improving data quality can significantly reduce the need for data…

Multi-label text classification refers to the problem of assigning each given document its most relevant labels from the label set. Commonly, the metadata of the given documents and the hierarchy of the labels are available in real-world…

While deep learning has been incredibly successful in modeling tasks with large, carefully curated labeled datasets, its application to problems with limited labeled data remains a challenge. The aim of the present work is to improve the…

Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually simple yet efficient training…

In many critical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers…

Improving the accessibility and automation capabilities of mobile devices can have a significant positive impact on the daily lives of countless users. To stimulate research in this direction, we release a human-annotated dataset with…