Related papers: A Two-Stage Framework with Self-Supervised Distill…
Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA).…
The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…
High-quality labeled data is essential for training accurate document conversion models, particularly in domains with complex formats such as tables, formulas, and multi-column text. However, manual annotation is both costly and…
Contextualized word embeddings such as ELMo and BERT provide a foundation for strong performance across a wide range of natural language processing tasks by pretraining on large corpora of unlabeled text. However, the applicability of this…
We present a supervised learning algorithm for text categorization which has brought the team of authors the 2nd place in the text categorization division of the 2012 Cybersecurity Data Mining Competition (CDMC'2012) and a 3rd prize…
Unsupervised domain adaptation aims to transfer the classifier learned from the source domain to the target domain in an unsupervised manner. With the help of target pseudo-labels, aligning class-level distributions and learning the…
We do not pursue a novel method in this paper, but aim to study if a modern text-to-image diffusion model can tailor any task-adaptive image classifier across domains and categories. Existing domain adaptive image classification works…
To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that…
In this study, we propose a method that distils representations of word meaning in context from a pre-trained masked language model in both monolingual and crosslingual settings. Word representations are the basis for context-aware lexical…
In real applications, object detectors based on deep networks still face challenges of the large domain gap between the labeled training data and unlabeled testing data. To reduce the gap, recent techniques are proposed by aligning the…
The goal of domain adaptation is to adapt models learned on a source domain to a particular target domain. Most methods for unsupervised domain adaptation proposed in the literature to date, assume that the set of classes present in the…
In many multilingual text classification problems, the documents in different languages often share the same set of categories. To reduce the labeling cost of training a classification model for each individual language, it is important to…
Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributions. In practice, annotations are scarce, and images are…
In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…
Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce satisfactory dense predictions on unlabeled target domain. One popular solution to this challenging task is self-training,…
Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting…
The behavior of users in certain services could be a clue that can be used to infer their preferences and may be used to make recommendations for other services they have never used. However, the cross-domain relationships between items and…
We present an approach for unsupervised domain adaptation---with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution shift---from a class-conditioned domain alignment…
Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted…