Related papers: Mutual Information-guided Knowledge Transfer for N…

In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes. While NCD has recently gained attention from the community, no framework has yet been proposed for…

Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous work on multi-agent transfer learning accommodate teams of different sizes, heavily relying on the…

Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot…

This paper addresses the problem of transferring useful knowledge from a source network to predict node labels in a newly formed target network. While existing transfer learning research has primarily focused on vector-based data, in which…

Convolutional neural networks (CNNs) are extensively beneficial for medical image processing. Medical images are plentiful, but there is a lack of annotated data. Transfer learning is used to solve the problem of lack of labeled data and…

Zero-shot learning aims to classify visual objects without any training data via knowledge transfer between seen and unseen classes. This is typically achieved by exploring a semantic embedding space where the seen and unseen classes can be…

Multi-label image recognition is a fundamental yet practical task because real-world images inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi-label annotations due to the complexity of both…

Unsupervised open-set domain adaptation (UODA) is a realistic problem where unlabeled target data contain unknown classes. Prior methods rely on the coexistence of both source and target domain data to perform domain alignment, which…

Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution. Recent self-supervised learning methods have shown to be effective when dealing with…

One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations,…

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…

Uncertainty estimation is at the core of Active Learning (AL). Most existing methods resort to complex auxiliary models and advanced training fashions to estimate uncertainty for unlabeled data. These models need special design and hence…

Open set domain recognition has got the attention in recent years. The task aims to specifically classify each sample in the practical unlabeled target domain, which consists of all known classes in the manually labeled source domain and…

Deep learning models heavily rely on large scale annotated datasets for training. Unfortunately, datasets cannot capture the infinite variability of the real world, thus neural networks are inherently limited by the restricted visual and…

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive…

One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging yet…

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while…

Prior works in cross-lingual named entity recognition (NER) with no/little labeled data fall into two primary categories: model transfer based and data transfer based methods. In this paper we find that both method types can complement each…

We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task…