Related papers: Conditional Variance Penalties and Domain Shift Ro…

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…

Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalization ability, which limits the real-world applications. The…

Change detection has essential significance for the region's development, in which pseudo-changes between bitemporal images induced by imaging environmental factors are key challenges. Existing transformation-based methods regard…

As we deploy machine learning systems in the real world, a core challenge is to maintain a model that is performant even as the data shifts. Such shifts can take many forms: new classes may emerge that were absent during training, a problem…

For reliable deployment of deep-learning systems, out-of-distribution (OOD) detection is indispensable. In the real world, where test-time inputs often arrive as streaming mixtures of in-distribution (ID) and OOD samples under evolving…

The goal of image ordinal estimation is to estimate the ordinal label of a given image with a convolutional neural network. Existing methods are mainly based on ordinal regression and particularly focus on modeling the ordinal mapping from…

Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Traditional methods for ensuring fairness either blindly learn…

Diffusion models have shown great promise in synthesizing visually appealing images. However, it remains challenging to condition the synthesis at a fine-grained level, for instance, synthesizing image pixels following some generic color…

Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform…

We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision. Many prior approaches to this problem have focused on learning "disentangled" representations so that as…

We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to…

Most conditional generation tasks expect diverse outputs given a single conditional context. However, conditional generative adversarial networks (cGANs) often focus on the prior conditional information and ignore the input noise vectors,…

Characterizing domains is essential for models analyzing dynamic environments, as it allows them to adapt to evolving conditions or to hand the task over to backup systems when facing conditions outside their operational domain. Existing…

Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\text{inv}}$ where the conditional distribution $Y…

Generative Adversarial Networks (GANs) are able to learn mappings between simple, relatively low-dimensional, random distributions and points on the manifold of realistic images in image-space. The semantics of this mapping, however, are…

In the field of computer vision, the persistent presence of color bias, resulting from fluctuations in real-world lighting and camera conditions, presents a substantial challenge to the robustness of models. This issue is particularly…

Deep learning has enjoyed a great deal of success because of its ability to learn useful features for tasks such as classification. But there has been less exploration in learning the factors of variation apart from the classification…

Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Bayesian inference for inverse problems involves computing expectations under posterior distributions -- e.g., posterior means, variances, or predictive quantities -- typically via Monte Carlo (MC) estimation. When the quantity of interest…