Related papers: Artistic Domain Generalisation Methods are Limited…
In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a…
We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving the model's…
Although humans perform well at predicting what exists beyond the boundaries of an image, deep models struggle to understand context and extrapolation through retained information. This task is known as image outpainting and involves…
Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real…
Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be learned from two image…
There is an emerging sense that the vulnerability of Image Convolutional Neural Networks (CNN), i.e., sensitivity to image corruptions, perturbations, and adversarial attacks, is connected with Texture Bias. This relative lack of Shape Bias…
Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications. To tackle this issue,…
In Domain Generalization (DG) tasks, models are trained by using only training data from the source domains to achieve generalization on an unseen target domain, this will suffer from the distribution shift problem. So it's important to…
Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism of this failure, using image deraining as a primary case study due to its…
Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the…
Traditionally, for most machine learning settings, gaining some degree of explainability that tries to give users more insights into how and why the network arrives at its predictions, restricts the underlying model and hinders performance…
The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle…
Domain generalization aims at training on source domains to uncover a domain-invariant feature space, allowing the model to perform robust generalization ability on unknown target domains. However, due to domain gaps, it is hard to find…
Deep Neural Networks can generalize despite being significantly overparametrized. Recent research has tried to examine this phenomenon from various view points and to provide bounds on the generalization error or measures predictive of the…
Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains. While UDA methods have access to unlabeled…
Domain generalization is a technique aimed at enabling models to maintain high accuracy when applied to new environments or datasets (unseen domains) that differ from the datasets used in training. Generally, the accuracy of models trained…
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.…
Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while…
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…
Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied.…