Related papers: ZAYAN: Disentangled Contrastive Transformer for Ta…

Medical datasets and especially biobanks, often contain extensive tabular data with rich clinical information in addition to images. In practice, clinicians typically have less data, both in terms of diversity and scale, but still wish to…

TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerable to label shift, often overfitting…

Zero-shot learning (ZSL) aims to recognize unseen classes without visual instances. However, existing methods usually assume clean labels, overlooking real-world label noise and ambiguity, which degrades performance. To bridge this gap, we…

Zero-shot learning (ZSL) aims to recognize the novel object categories using the semantic representation of categories, and the key idea is to explore the knowledge of how the novel class is semantically related to the familiar classes.…

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…

Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across datasets, making the definition of clusters highly…

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently…

Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always…

StyleGAN has shown strong potential for disentangled semantic control, thanks to its special design of multi-layer intermediate latent variables. However, existing semantic discovery methods on StyleGAN rely on manual selection of modified…

Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed…

Change detection (CD) is a fundamental and important task for monitoring the land surface dynamics in the earth observation field. Existing deep learning-based CD methods typically extract bi-temporal image features using a weight-sharing…

It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not match. Although transductive ZSL (TZSL) attempts to improve…

In this paper, we propose a novel framework, Disentangled Style-Content GAN (DISC-GAN), which integrates style-content disentanglement with a cluster-specific training strategy towards photorealistic underwater image synthesis. The quality…

Self-supervised contrastive representation learning has proved incredibly successful in the vision and natural language domains, enabling state-of-the-art performance with orders of magnitude less labeled data. However, such methods are…

We propose a novel reconstruction-based model for anomaly detection, called Y-GAN. The model consists of a Y-shaped auto-encoder and represents images in two separate latent spaces. The first captures meaningful image semantics, key for…

Learning disentangled representations without supervision or inductive biases, often leads to non-interpretable or undesirable representations. On the other hand, strict supervision requires detailed knowledge of the true generative…

Task-oriented semantic communication systems have emerged as a promising approach to achieving efficient and intelligent data transmission in next-generation networks, where only information relevant to a specific task is communicated. This…

Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks. However, contrastive learning in the context of domain adaptation remains…

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a…

Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN). While previous works mostly attempt to…