Related papers: Context-Aware Query Selection for Active Learning …

State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level prediction tasks like…

Activity recognition is the ability to identify and recognize the action or goals of the agent. The agent can be any object or entity that performs action that has end goals. The agents can be a single agent performing the action or group…

Spatio-temporal action detection encompasses the tasks of localizing and classifying individual actions within a video. Recent works aim to enhance this process by incorporating interaction modeling, which captures the relationship between…

Deep learning models have achieved state-of-the- art performance in recognizing human activities, but often rely on utilizing background cues present in typical computer vision datasets that predominantly have a stationary camera. If these…

Acoustic event detection is essential for content analysis and description of multimedia recordings. The majority of current literature on the topic learns the detectors through fully-supervised techniques employing strongly labeled data.…

Network operators are generally aware of common attack vectors that they defend against. For most networks the vast majority of traffic is legitimate. However new attack vectors are continually designed and attempted by bad actors which…

Though quite challenging, leveraging large-scale unlabeled or partially labeled data in learning systems (e.g., model/classifier training) has attracted increasing attentions due to its fundamental importance. To address this problem, many…

Credit card fraud detection is a very challenging problem because of the specific nature of transaction data and the labeling process. The transaction data is peculiar because they are obtained in a streaming fashion, they are strongly…

Active Learning (AL) is a human-in-the-loop framework to interactively and adaptively label data instances, thereby enabling significant gains in model performance compared to random sampling. AL approaches function by selecting the hardest…

Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection. However, the widely used active detection benchmarks conduct image-level evaluation, which is unrealistic in…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of deep learning models suffer from those changes as data and…

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural…

Sequential recommendation models are crucial for next-item recommendations in online platforms, capturing complex patterns in user interactions. However, many focus on a single behavior, overlooking valuable implicit interactions like…

Label aggregation such as majority voting is commonly used to resolve annotator disagreement in dataset creation. However, this may disregard minority values and opinions. Recent studies indicate that learning from individual annotations…

Human brain is continuously inundated with the multisensory information and their complex interactions coming from the outside world at any given moment. Such information is automatically analyzed by binding or segregating in our brain.…

Training a real-time gesture recognition model heavily relies on annotated data. However, manual data annotation is costly and demands substantial human effort. In order to address this challenge, we propose a framework that can…

Active learning allows machine learning models to be trained using fewer labels while retaining similar performance to traditional supervised learning. An active learner selects the most informative data points, requests their labels, and…

Machine learning-based classifiers have been used for text classification, such as sentiment analysis, news classification, and toxic comment classification. However, supervised machine learning models often require large amounts of labeled…

Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework,…