Related papers: Bipartite Mode Matching for Vision Training Set Se…
Machine translation (MT) systems, especially when designed for an industrial setting, are trained with general parallel data derived from the Web. Thus, their style is typically driven by word/structure distribution coming from the average…
Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection. Existing unsupervised DAOD methods usually perform feature alignments from the target to…
In modern data center networks, thousands of hosts contend for shared link capacity; the scale of these systems makes centralized scheduling impractical. This article models such scheduling as a bipartite matching problem under…
Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation. We propose a novel…
Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…
In bipartite matching problems, vertices on one side of a bipartite graph are paired with those on the other. In its online variant, one side of the graph is available offline, while the vertices on the other side arrive online. When a…
Unsupervised Domain Adaptation (UDA) seeks to transfer knowledge from a labeled source domain to an unlabeled target domain but often suffers from severe domain and scale gaps that degrade performance. Existing cross-attention-based…
In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…
Deep learning techniques have been widely used in autonomous driving systems for the semantic understanding of urban scenes. However, they need a huge amount of labeled data for training, which is difficult and expensive to acquire. A…
Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…
Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not generalize well in presence of a domain shift between training and…
Semi-Supervised Domain Adaptation (SSDA) leverages knowledge from a fully labeled source domain to classify data in a partially labeled target domain. Due to the limited number of labeled samples in the target domain, there can be intrinsic…
A key topic in classification is the accuracy loss produced when the data distribution in the training (source) domain differs from that in the testing (target) domain. This is being recognized as a very relevant problem for many computer…
The standard paradigm for training deep learning models on sensor data assumes that more data is always better. However, raw sensor streams are often imbalanced and contain significant redundancy, meaning that not all data points contribute…
Cloud solutions have gained significant popularity in the technology industry as they offer a combination of services and tools to tackle specific problems. However, despite their widespread use, the task of identifying appropriate company…
While huge volumes of unlabeled data are generated and made available in many domains, the demand for automated understanding of visual data is higher than ever before. Most existing machine learning models typically rely on massive amounts…
Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirement of identical class space shared across domains hinders…
Multi-source Domain Adaptation (MDA) seeks to adapt models trained on data from multiple labeled source domains to perform effectively on an unlabeled target domain data, assuming access to sources data. To address the challenges of model…
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…
Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. Present UDA models focus on alleviating the domain shift by minimizing the feature discrepancy…