相关论文: Coupling Distant Annotation and Adversarial Traini…

Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other forms of weak…

Most previous approaches to Chinese word segmentation can be roughly classified into character-based and word-based methods. The former regards this task as a sequence-labeling problem, while the latter directly segments character sequence…

Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT, an auxiliary…

In this paper, we empirically investigate applying word-level weights to adapt neural machine translation to e-commerce domains, where small e-commerce datasets and large out-of-domain datasets are available. In order to mine in-domain like…

Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as…

Many complex discourse-level tasks can aid domain experts in their work but require costly expert annotations for data creation. To speed up and ease annotations, we investigate the viability of automatically generated annotation…

Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target domain to improve the performance in the target domain via…

Unnatural text correction aims to automatically detect and correct spelling errors or adversarial perturbation errors in sentences. Existing methods typically rely on fine-tuning or adversarial training to correct errors, which have…

The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…

Deep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability. To still obtain viable models, continual learning aims to train in sequential order, as and when data is available. The main…

Impressive image captioning results are achieved in domains with plenty of training image and sentence pairs (e.g., MSCOCO). However, transferring to a target domain with significant domain shifts but no paired training data (referred to as…

In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images and additional non-annotated images. We present a method…

This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. The DOTN aims to…

This work presents a novel domain adaption paradigm for studying contrastive self-supervised representation learning and knowledge transfer using remote sensing satellite data. Major state-of-the-art remote sensing visual domain efforts…

Most of the Chinese pre-trained models adopt characters as basic units for downstream tasks. However, these models ignore the information carried by words and thus lead to the loss of some important semantics. In this paper, we propose a…

Semantic specialization is the process of fine-tuning pre-trained distributional word vectors using external lexical knowledge (e.g., WordNet) to accentuate a particular semantic relation in the specialized vector space. While…

Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation…

Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models trained on one data domain may not generalize well to other…

This paper addresses the issue of generalization for Semantic Parsing in an adversarial framework. Building models that are more robust to inter-document variability is crucial for the integration of Semantic Parsing technologies in real…

Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can…