Related papers: SoMA: Singular Value Decomposed Minor Components A…
Single source domain generalization (SDG) holds promise for more reliable and consistent image segmentation across real-world clinical settings particularly in the medical domain, where data privacy and acquisition cost constraints often…
Low-Rank Adaptation (LoRA) and other parameter-efficient fine-tuning (PEFT) methods provide low-memory, storage-efficient solutions for personalizing text-to-image models. However, these methods offer little to no improvement in wall-clock…
Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role…
A major technique for tackling unsupervised domain adaptation involves mapping data points from both the source and target domains into a shared embedding space. The mapping encoder to the embedding space is trained such that the embedding…
Multi-modal unsupervised domain adaptation (MM-UDA) for 3D semantic segmentation is a practical solution to embed semantic understanding in autonomous systems without expensive point-wise annotations. While previous MM-UDA methods can…
With the increasing utilization of deep learning in outdoor settings, its robustness needs to be enhanced to preserve accuracy in the face of distribution shifts, such as compression artifacts. Data augmentation is a widely used technique…
Deep neural networks suffer from significant performance deterioration when there exists distribution shift between deployment and training. Domain Generalization (DG) aims to safely transfer a model to unseen target domains by only relying…
The rapid development of large language models has revolutionized natural language processing, but their fine-tuning remains computationally expensive, hindering broad deployment. Parameter-efficient fine-tuning (PEFT) methods, such as…
Parameter-efficient fine-tuning (PEFT) is a flexible and efficient method for adapting large language models (LLMs) to downstream tasks. Among these methods, weight-decomposed low-rank adaptation (DoRA) is a promising approach that…
Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…
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…
Domain adaptation aims to bridge the domain shifts between the source and the target domain. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge…
Recent advancements in domain generalization for deepfake detection have attracted significant attention, with previous methods often incorporating additional modules to prevent overfitting to domain-specific patterns. However, such…
Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during training, optimization…
In search of robust and generalizable machine learning models, Domain Generalization (DG) has gained significant traction during the past few years. The goal in DG is to produce models which continue to perform well when presented with data…
Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains.…
Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising…
Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…
Domain Generalization (DG) studies the capability of a deep learning model to generalize to out-of-training distributions. In the last decade, literature has been massively filled with training methodologies that claim to obtain more…
Parameter-efficient fine-tuning (PEFT) has emerged as a scalable solution for adapting large foundation models. While low-rank adaptation (LoRA) is widely used in speech applications, its state-of-the-art variants, e.g., VeRA, DoRA, PiSSA,…