Related papers: DARA: Domain- and Relation-aware Adapters Make Par…

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness.…

Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the…

Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications. However,…

Visual Place Recognition (VPR) localizes a query image by matching it against a database of geo-tagged reference images, making it essential for navigation and mapping in robotics. Although Vision Transformer (ViT) solutions deliver high…

The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques…

Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and…

Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP) models, prompt tuning often requires a large number of…

Domain Adaptation (DA) aims to transfer knowledge from a labeled source domain to an unlabeled or sparsely labeled target domain under domain shifts. Most prior works focus on capturing the inter-domain transferability but largely overlook…

Cancer detection and prognosis relies heavily on medical imaging, particularly CT and PET scans. Deep Neural Networks (DNNs) have shown promise in tumor segmentation by fusing information from these modalities. However, a critical…

Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…

In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage…

As model sizes continue to grow, parameter-efficient fine-tuning has emerged as a powerful alternative to full fine-tuning. While LoRA is widely adopted among these methods, recent research has explored vector-based adaptation methods due…

In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting,…

We revisit continual learning~(CL), which enables pre-trained vision transformers (ViTs) to sequentially fine-tune on new downstream tasks over time. However, as the scale of these models increases, catastrophic forgetting remains a more…

Conventional Low-Rank Adaptation (LoRA) methods employ a fixed rank, imposing uniform adaptation across transformer layers and attention heads despite their heterogeneous learning dynamics. This paper introduces Adaptive Rank Dynamic LoRA…

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,…

Domain adaptation is critical for learning in new and unseen environments. With domain adversarial training, deep networks can learn disentangled and transferable features that effectively diminish the dataset shift between the source and…

In recent years, deep neural networks (DNNs) trained with transformed data have been applied to various applications such as privacy-preserving learning, access control, and adversarial defenses. However, the use of transformed data…

Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many…

Domain-specific languages (DSLs) for visualization aim to facilitate visualization creation by providing abstractions that offload implementation and execution details from users to the system layer. Therefore, DSLs often execute…