Related papers: CzSL: Learning from citizen science, experts and u…

The exponential growth of astronomical datasets provides an unprecedented opportunity for humans to gain insight into the Universe. However, effectively analyzing this vast amount of data poses a significant challenge. Astronomers are…

A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize unlabeled images from unseen classes (i.e transductive…

Technological and computational advances continuously drive forward the broad field of deep learning. In recent years, the derivation of quantities describing theuncertainty in the prediction - which naturally accompanies the modeling…

In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can…

Multi-label classification (MLC) is a supervised learning problem in which, contrary to standard multiclass classification, an instance can be associated with several class labels simultaneously. In this chapter, we advocate a rule-based…

The distribution of illustrations on social media, such as Twitter and Pixiv has increased with the growing popularity of animation, games, and animated movies. The "atmosphere" of illustrations plays an important role in user preferences.…

This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein the model is trained to recognize multiple unseen classes within a sample (e.g., an image) based on seen classes and auxiliary…

Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to learn and understand the world. While considerable progress…

High-quality data is crucial for the success of machine learning, but labeling large datasets is often a time-consuming and costly process. While semi-supervised learning can help mitigate the need for labeled data, label quality remains an…

Citizen science refers to scientific research conducted or participated by non-professional scientists (such as hobbyists or members from the general public). Citizen astronomy is a classic example of citizen science. Citizen astronomers…

This paper introduces a novel heterogenous domain adaptation (HDA) method for hyperspectral image classification with a limited amount of labeled samples in both domains. The method is achieved in the way of cross-domain collaborative…

Multi-label image recognition with incomplete labels is a challenging yet vital task in computer vision, which faces two fundamental challenges: learning semantic-aware features and recovering missing labels. In this paper, we propose a…

Astronomers have typically set out to solve supervised machine learning problems by creating their own representations from scratch. We show that deep learning models trained to answer every Galaxy Zoo DECaLS question learn meaningful…

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel…

Decentralized learning has been advocated and widely deployed to make efficient use of distributed datasets, with an extensive focus on supervised learning (SL) problems. Unfortunately, the majority of real-world data are unlabeled and can…

Supervised learning, especially supervised deep learning, requires large amounts of labeled data. One approach to collect large amounts of labeled data is by using a crowdsourcing platform where numerous workers perform the annotation…

Self-supervised pretraining on unlabeled data followed by supervised fine-tuning on labeled data is a popular paradigm for learning from limited labeled examples. We extend this paradigm to the classical positive unlabeled (PU) setting,…

Semi-supervised learning (SSL) has been extensively studied to improve the generalization ability of deep neural networks for visual recognition. To involve the unlabelled data, most existing SSL methods are based on common density-based…

We introduce Galaxy Zoo Evo, a labeled dataset for building and evaluating foundation models on images of galaxies. GZ Evo includes 104M crowdsourced labels for 823k images from four telescopes. Each image is labeled with a series of…

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…