相关论文: Label-efficient underwater species classification …

Scientific document classification is a critical task for a wide range of applications, but the cost of obtaining massive amounts of human-labeled data can be prohibitive. To address this challenge, we propose a weakly-supervised approach…

This paper presents a novel method for embedding transfer, a task of transferring knowledge of a learned embedding model to another. Our method exploits pairwise similarities between samples in the source embedding space as the knowledge,…

In model serving, having one fixed model during the entire often life-long inference process is usually detrimental to model performance, as data distribution evolves over time, resulting in lack of reliability of the model trained on…

Maternal-fetal Ultrasound is the primary modality for monitoring fetal development, yet automated segmentation remains challenging due to the scarcity of high-quality annotations. To address this limitation, we propose a semi-supervised…

We propose a new framework for binary classification in transfer learning settings where both covariate and label distributions may shift between source and target domains. Unlike traditional covariate shift or label shift assumptions, we…

Semi supervised learning methods have gained importance in today's world because of large expenses and time involved in labeling the unlabeled data by human experts. The proposed hybrid approach uses SVM and Label Propagation to label the…

Active Learning (AL) is a powerful tool for learning with less labeled data, in particular, for specialized domains, like legal documents, where unlabeled data is abundant, but the annotation requires domain expertise and is thus expensive.…

Sparse labels have been attracting much attention in recent years. However, the performance gap between weakly supervised and fully supervised salient object detection methods is huge, and most previous weakly supervised works adopt complex…

Labeling data (e.g., labeling the people, objects, actions and scene in images) comprehensively and efficiently is a widely needed but challenging task. Numerous models were proposed to label various data and many approaches were designed…

Accurate school detection is essential for supporting education initiatives, including infrastructure planning and expanding internet connectivity to underserved areas. However, many regions around the world face challenges due to outdated,…

Among the three main components (data, labels, and models) of any supervised learning system, data and models have been the main subjects of active research. However, studying labels and their properties has received very little attention.…

Existing weak supervision approaches use all the data covered by weak signals to train a classifier. We show both theoretically and empirically that this is not always optimal. Intuitively, there is a tradeoff between the amount of…

In supervised learning, obtaining a large set of fully-labeled training data is expensive. We show that we do not always need full label information on every single training example to train a competent classifier. Specifically, inspired by…

We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined…

Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose Hierarchy-Aware…

While the performance of machine learning systems has experienced significant improvement in recent years, relatively little attention has been paid to the fundamental question: to what extent can we improve our models? This paper provides…

The memorization effect of deep neural networks (DNNs) plays a pivotal role in recent label noise learning methods. To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of…

Applying deep learning to science is a new trend in recent years which leads DL engineering to become an important problem. Although training data preparation, model architecture design, and model training are the normal processes to build…

Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual…

We present novel active learning strategies dedicated to providing a solution to the cold start stage, i.e. initializing the classification of a large set of data with no attached labels. Moreover, proposed strategies are designed to handle…