Related papers: Multi-label classification for multi-temporal, mul…

Detecting temporal changes in geographical landscapes is critical for applications like environmental monitoring and urban planning. While remote sensing data is abundant, existing vision-language models (VLMs) often fail to capture…

Vision Transformers (ViTs) have been widely adopted in vision tasks due to their strong transferability. In Federated Learning (FL), where full fine-tuning is communication heavy, Low-Rank Adaptation (LoRA) provides an efficient and…

The performance of deep learning models is known to scale with data quantity and diversity. In pathology, as in many other medical imaging domains, the availability of labeled images for a specific task is often limited. Self-supervised…

This study investigates the efficacy of Low-Rank Adaptation (LoRA) for fine-tuning large Vision Models, DinoV2 and SwinV2, to diagnose Radiation-Induced Lung Injury (RILI) from X-ray CT scans following Stereotactic Body Radiation Therapy…

Speech foundation models struggle with low-resource Pacific Indigenous languages because of severe data scarcity. Furthermore, full fine-tuning risks catastrophic forgetting. To address this gap, we present an empirical study adapting…

Recently, pre-trained model and efficient parameter tuning have achieved remarkable success in natural language processing and high-level computer vision with the aid of masked modeling and prompt tuning. In low-level computer vision,…

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), but it still incurs notable overhead and suffers from parameter interference in complex datasets. While recent…

We address vision-language-driven indoor navigation to assist visually impaired individuals in reaching a target location using images and natural language guidance. Traditional navigation systems are ineffective indoors due to the lack of…

The classification and recognition of maritime objects are crucial for enhancing maritime safety, monitoring, and intelligent sea environment prediction. However, existing unsupervised methods for maritime object classification often…

The current state-of-the-art methods in domain adaptive object detection (DAOD) use Mean Teacher self-labelling, where a teacher model, directly derived as an exponential moving average of the student model, is used to generate labels on…

Low-rank adaptations (LoRAs) have revolutionized the finetuning of large foundation models, enabling efficient adaptation even with limited computational resources. The resulting proliferation of LoRAs presents exciting opportunities for…

Foundation models such as Wav2Vec2 excel at representation learning in speech tasks, including audio deepfake detection. However, after being fine-tuned on a fixed set of bonafide and spoofed audio clips, they often fail to generalize to…

Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models due to its efficiency and zero additional inference cost. Many real-world applications require foundation models to specialize in several specific…

In this chapter, we present CORrelation ALignment (CORAL), a simple yet effective method for unsupervised domain adaptation. CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without…

Fine-tuning large pre-trained vision foundation models in a parameter-efficient manner is critical for downstream vision tasks, considering the practical constraints of computational and storage costs. Low-rank adaptation (LoRA) is a…

Oyster reefs are critical ecosystem species that sustain biodiversity, filter water, and protect coastlines, yet they continue to decline globally. Restoring these ecosystems requires regular underwater monitoring to assess reef health, a…

The autonomous driving community is increasingly focused on addressing corner case problems, particularly those related to ensuring driving safety under adverse conditions (e.g., nighttime, fog, rain). To this end, the task of Adverse…

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

Low-Rank Adaptation (LoRA) has emerged as a powerful and popular technique for personalization, enabling efficient adaptation of pre-trained image generation models for specific tasks without comprehensive retraining. While employing…

Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the…