Related papers: Text-Driven Causal Representation Learning for Sou…

Brain CT report generation is significant to aid physicians in diagnosing cranial diseases. Recent studies concentrate on handling the consistency between visual and textual pathological features to improve the coherence of report. However,…

Multi-label Recognition (MLR) involves assigning multiple labels to each data instance in an image, offering advantages over single-label classification in complex scenarios. However, it faces the challenge of annotating all relevant…

Generalization under the distribution shift has been a great challenge in computer vision. The prevailing practice of directly employing the one-hot labels as the training targets in domain generalization~(DG) can lead to gradient…

This thesis develops methods for causal inference and causal representation learning (CRL) in high-dimensional, time-varying data. The first contribution introduces the Causal Dynamic Variational Autoencoder (CDVAE), a model for estimating…

Long-term action recognition (LTAR) is challenging due to extended temporal spans with complex atomic action correlations and visual confounders. Although vision-language models (VLMs) have shown promise, they often rely on statistical…

Domain-Incremental Learning (DIL) enables vision models to adapt to changing conditions in real-world environments while maintaining the knowledge acquired from previous domains. Given privacy concerns and training time, Rehearsal-Free DIL…

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object…

Learning domain-invariant visual representations is important to train a model that can generalize well to unseen target task domains. Recent works demonstrate that text descriptions contain high-level class-discriminative information and…

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate…

Domain generalization (DG) focuses on transferring domain-invariant knowledge from multiple source domains (available at train time) to an, a priori, unseen target domain(s). This requires a class to be expressed in multiple domains for the…

Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to perform low-level…

Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to a related but unlabeled target domain. While the source model is a key avenue for acquiring target pseudolabels, the generated…

Representation learning on text-attributed graphs (TAGs) has attracted significant interest due to its wide-ranging real-world applications, particularly through Graph Neural Networks (GNNs). Traditional GNN methods focus on encoding the…

Many large-scale applications can be elegantly represented using graph structures. Their scalability, however, is often limited by the domain knowledge required to apply them. To address this problem, we propose a novel Causal Temporal…

Large-scale Vision-Language Models (VLMs) have demonstrated exceptional performance in natural vision tasks, motivating researchers across domains to explore domain-specific VLMs. However, the construction of powerful domain-specific VLMs…

Although foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-grained categorization. Moreover, foundational models…

Unsupervised domain adaptation has been widely adopted to generalize models for unlabeled data in a target domain, given labeled data in a source domain, whose data distributions differ from the target domain. However, existing works are…

We tackle the challenging problem of single-source domain generalization (DG) for medical image segmentation, where we train a network on one domain (e.g., CT) and directly apply it to a different domain (e.g., MR) without adapting the…

Temporal Domain Generalization (TDG) addresses the challenge of training predictive models under temporally varying data distributions. Traditional TDG approaches typically focus on domain data collected at fixed, discrete time intervals,…

Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains. Under the domain-hungry configuration, how to expand the coverage of…