Related papers: Rethinking Content and Style: Exploring Bias for U…
Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details…
Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding…
Unsupervised image-to-image translation methods aim to map images from one domain into plausible examples from another domain while preserving structures shared across two domains. In the many-to-many setting, an additional guidance example…
Deep-embedding methods aim to discover representations of a domain that make explicit the domain's class structure and thereby support few-shot learning. Disentangling methods aim to make explicit compositional or factorial structure. We…
We aim to separate the generative factors of data into two latent vectors in a variational autoencoder. One vector captures class factors relevant to target classification tasks, while the other vector captures style factors relevant to the…
Accurate gland segmentation in histopathology images is essential for cancer diagnosis and prognosis. However, significant variability in Hematoxylin and Eosin (H&E) staining and tissue morphology, combined with limited annotated data,…
The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we…
We consider the problem of constraining diffusion model outputs with a user-supplied reference image. Our key objective is to extract multiple attributes (e.g., color, object, layout, style) from this single reference image, and then…
Enabling generative models to decompose visual concepts from a single image is a complex and challenging problem. In this paper, we study a new and challenging task, customized concept decomposition, wherein the objective is to leverage…
One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…
Correlations between factors of variation are prevalent in real-world data. Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e.g., they may change between domains,…
Independent components within low-dimensional representations are essential inputs in several downstream tasks, and provide explanations over the observed data. Video-based disentangled factors of variation provide low-dimensional…
Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…
Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for…
Recent advances in Text-to-Image (T2I) diffusion models have transformed image generation, enabling significant progress in stylized generation using only a few style reference images. However, current diffusion-based methods struggle with…
Unsupervised image-to-image translation methods have achieved tremendous success in recent years. However, it can be easily observed that their models contain significant entanglement which often hurts the translation performance. In this…
Generalization to previously unseen images with potential domain shifts and different styles is essential for clinically applicable medical image segmentation, and the ability to disentangle domain-specific and domain-invariant features is…
In computer vision, disentangling techniques aim at improving latent representations of images by modeling factors of variation. In this paper, we propose DualDis, a new auto-encoder-based framework that disentangles and linearizes class…
CLIP models have recently shown to exhibit Out of Distribution (OoD) generalization capabilities. However, Compositional Out of Distribution (C-OoD) generalization, which is a crucial aspect of a model's ability to understand unseen…
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…