Related papers: Labeled Data Selection for Category Discovery

Active domain adaptation (ADA) studies have mainly addressed query selection while following existing domain adaptation strategies. However, we argue that it is critical to consider not only query selection criteria but also domain…

The availability of large labeled datasets is the key component for the success of deep learning. However, annotating labels on large datasets is generally time-consuming and expensive. Active learning is a research area that addresses the…

Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to each image makes the…

When faced with distribution shift at test time, deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. While improving the robustness of neural networks is one promising approach to mitigate this…

Decision making algorithms, in practice, are often trained on data that exhibits a variety of biases. Decision-makers often aim to take decisions based on some ground-truth target that is assumed or expected to be unbiased, i.e., equally…

Zero-shot text classifiers based on label descriptions embed an input text and a set of labels into the same space: measures such as cosine similarity can then be used to select the most similar label description to the input text as the…

We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities…

Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for…

Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model. However, the estimation and classifier…

We quantify the separation between the numbers of labeled examples required to learn in two settings: Settings with and without the knowledge of the distribution of the unlabeled data. More specifically, we prove a separation by…

The need for labeled data is among the most common and well-known practical obstacles to deploying deep learning algorithms to solve real-world problems. The current generation of learning algorithms requires a large volume of data labeled…

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution…

The premise of semi-supervised learning (SSL) is that combining labeled and unlabeled data yields significantly more accurate models. Despite empirical successes, the theoretical understanding of SSL is still far from complete. In this…

Ensemble learning aims to improve generalization ability by using multiple base learners. It is well-known that to construct a good ensemble, the base learners should be accurate as well as diverse. In this paper, unlabeled data is…

In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labels. This paper studies a new problem setting in which there…

In this paper, we tackle the problem of Generalized Category Discovery (GCD). Given a dataset containing both labelled and unlabelled images, the objective is to categorize all images in the unlabelled subset, irrespective of whether they…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new…