Related papers: DeceptionNet: Network-Driven Domain Randomization

Semantic segmentation models have reached remarkable performance across various tasks. However, this performance is achieved with extremely large models, using powerful computational resources and without considering training and inference…

We propose a direct domain adaptation (DDA) approach to enrich the training of supervised neural networks on synthetic data by features from real-world data. The process involves a series of linear operations on the input features to the NN…

Domain adaptation aims to mitigate the domain shift problem when transferring knowledge from one domain into another similar but different domain. However, most existing works rely on extracting marginal features without considering class…

Deep learning-based object reconstruction algorithms have shown remarkable improvements over classical methods. However, supervised learning based methods perform poorly when the training data and the test data have different distributions.…

As of today, object categorization algorithms are not able to achieve the level of robustness and generality necessary to work reliably in the real world. Even the most powerful convolutional neural network we can train fails to perform…

Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain. In this paper, we propose to tackle the problem of domain generalization by delivering an effective framework named Variational…

Image denoising is a critical task in various scientific fields such as medical imaging and material characterization, where the accurate recovery of underlying structures from noisy data is essential. Although supervised denoising…

Aiming towards human-level generalization, there is a need to explore adaptable representation learning methods with greater transferability. Most existing approaches independently address task-transferability and cross-domain adaptation,…

Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various distance-based…

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We…

Domain generalization (DG) is a fundamental yet very challenging research topic in machine learning. The existing arts mainly focus on learning domain-invariant features with limited source domains in a static model. Unfortunately, there is…

In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic…

We explore the node classification task in the context of graph domain adaptation, which uses both source and target graph structures along with source labels to enhance the generalization capabilities of Graph Neural Networks (GNNs) on…

In this work we challenge the common approach of using a one-to-one mapping ('translation') between the source and target domains in unsupervised domain adaptation (UDA). Instead, we rely on stochastic translation to capture inherent…

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images,…

Domain shift is a very challenging problem for semantic segmentation. Any model can be easily trained on synthetic data, where images and labels are artificially generated, but it will perform poorly when deployed on real environments. In…

Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…

Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias. Although unsupervised image-to-image translation networks represented by CycleGAN show great potential in dealing with domain gap, it…

This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on…

This report contributes to the field of unsupervised domain adaptation by providing an analysis of existing methods, introducing a new approach, and demonstrating the potential for improving visual recognition tasks across different…