相关论文: Disentanglement and Generalization Under Correlati…

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style". In this paper, we show that this condition is not…

Learning individual-level treatment effect is a fundamental problem in causal inference and has received increasing attention in many areas, especially in the user growth area which concerns many internet companies. Recently, disentangled…

Causal disentanglement seeks a representation of data involving latent variables that relate to one another via a causal model. A representation is identifiable if both the latent model and the transformation from latent to observed…

As Diffusion Models have shown promising performance, a lot of efforts have been made to improve the controllability of Diffusion Models. However, how to train Diffusion Models to have the disentangled latent spaces and how to naturally…

This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features…

One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in…

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability…

Vision-language models like CLIP excel at recognizing the single, prominent object in a scene. However, they struggle in complex scenes containing multiple objects. We identify a fundamental reason for this limitation: VLM feature space…

Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. Initially consisting of unsupervised models with independence…

Accuracy and consistency are two key factors in computer-assisted magnetic resonance (MR) image analysis. However, contrast variation from site to site caused by lack of standardization in MR acquisition impedes consistent measurements. In…

Predictive models can fail to generalize from training to deployment environments because of dataset shift, posing a threat to model reliability and the safety of downstream decisions made in practice. Instead of using samples from the…

Disentangling data into interpretable and independent factors is critical for controllable generation tasks. With the availability of labeled data, supervision can help enforce the separation of specific factors as expected. However, it is…

Various controls over the generated data can be extracted from the latent space of a pre-trained GAN, as it implicitly encodes the semantics of the training data. The discovered controls allow to vary semantic attributes in the generated…

Adjusting for latent covariates is crucial for estimating causal effects from observational textual data. Most existing methods only account for confounding covariates that affect both treatment and outcome, potentially leading to biased…

Disentangled encoding is an important step towards a better representation learning. However, despite the numerous efforts, there still is no clear winner that captures the independent features of the data in an unsupervised fashion. In…

Recent text-to-image models produce high-quality images, yet text ambiguity hinders precise control when specific styles or objects are required. There have been a number of recent works dealing with learning and composing multiple objects…

Generalization beyond the training distribution is a core challenge in machine learning. The common practice of mixing and shuffling examples when training neural networks may not be optimal in this regard. We show that partitioning the…

A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream…