Related papers: A new semi-supervised inductive transfer learning …
While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labeled source data must be available. In this work we overcome…
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…
One of the central problems in machine learning is domain adaptation. Unlike past theoretical work, we consider a new model for subpopulation shift in the input or representation space. In this work, we propose a provably effective…
In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there…
Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware. Distillation from a trained source model may represent a solution for the first but does not…
One of the most important factors in training object recognition networks using convolutional neural networks (CNNs) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation,…
Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire…
Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…
Sequential sensor data is generated in a wide variety of practical applications. A fundamental challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent…
The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these…
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source…
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training. Despite the promising results, the label mismatch problem is not yet fully explored in the previous works, leading to…
We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct…
In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to…
Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferring bi-knowledge…
Unsupervised pretraining has achieved great success and many recent works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream target datasets. But…
Unsupervised domain adaptation seeks to learn an invariant and discriminative representation for an unlabeled target domain by leveraging the information of a labeled source dataset. We propose to improve the discriminative ability of the…
Domain adaptive semantic segmentation is recognized as a promising technique to alleviate the domain shift between the labeled source domain and the unlabeled target domain in many real-world applications, such as automatic pilot. However,…
Semi-supervised domain adaptation aims to classify data belonging to a target domain by utilizing a related label-rich source domain and very few labeled examples of the target domain. Here, we propose a novel framework, Pred&Guide, which…
Existing Source-free Unsupervised Domain Adaptation (SUDA) approaches inherently exhibit catastrophic forgetting. Typically, models trained on a labeled source domain and adapted to unlabeled target data improve performance on the target…