Related papers: Exploiting Layer Normalization Fine-tuning in Visu…
Conventional fine-tuning encounters increasing difficulties given the size of current Pre-trained Language Models, which makes parameter-efficient tuning become the focal point of frontier research. Previous methods in this field add…
When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…
Super-resolution is widely used in medical imaging to enhance low-quality data, reducing scan time and improving abnormality detection. Conventional super-resolution approaches typically rely on paired datasets of downsampled and original…
Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks…
Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and…
Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…
Medical vision foundation models remain limited in downstream tasks, particularly volumetric medical image segmentation. While fine-tuning on labeled target-domain data improves performance, existing approaches typically rely on randomly…
With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised…
Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot…
Vision-language models (VLMs) like CLIP have shown impressive generalization capabilities, yet their potential for Cross-Domain Few-Shot Learning (CDFSL) remains underexplored, where the model needs to transfer source-domain information to…
Recently, the pretrain-finetuning paradigm has attracted tons of attention in graph learning community due to its power of alleviating the lack of labels problem in many real-world applications. Current studies use existing techniques, such…
Dynamic imaging is a beneficial tool for interventions to assess physiological changes. Nonetheless during dynamic MRI, while achieving a high temporal resolution, the spatial resolution is compromised. To overcome this spatio-temporal…
While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…
Vision Transformers (ViTs) have underpinned the recent breakthroughs in computer vision. However, designing the architectures of ViTs is laborious and heavily relies on expert knowledge. To automate the design process and incorporate…
Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…
Unsupervised domain adaptation methods have been widely explored to bridge domain gaps. However, in real-world remote-sensing scenarios, privacy and transmission constraints often preclude access to source domain data, which limits their…
Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained…
Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing…
A prevalent approach in Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViT) involves freezing the majority of the backbone parameters and solely learning low-rank adaptation weight matrices to accommodate…
Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated…