Large-scale pre-trained vision models (PVMs) have shown great potential for adaptability
across various downstream vision tasks. However, with state-of-the-art PVMs growing to …

Continual Learning (CL) enables machine learning models to learn from continuously
shifting new training data in absence of data from old tasks. Recently pre-trained vision …

Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …

Adversarial attacks in computer vision exploit the vulnerabilities of machine learning models
by introducing subtle perturbations to input data, often leading to incorrect predictions or …

Deep neural networks have achieved remarkable success in a variety of computer vision
applications. However, there is a problem of degrading accuracy when the data distribution …

Prompt learning is an effective way to exploit the potential of large-scale pre-trained
foundational models. Continuous prompts parameterize context tokens in prompts by turning …

This survey delves into the realm of Parameter-Efficient Fine-Tuning (PEFT) within the
context of Foundation Models (FMs). PEFT, a cost-effective fine-tuning technique, minimizes …

Self-supervised learning is crucial for super-resolution because ground-truth images are
usually unavailable for real-world settings. Existing methods derive self-supervision from low …

Previous research on retinal vessel segmentation is targeted at a specific image domain,
mostly color fundus photography (CFP). In this paper we make a brave attempt to attack a …

Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-
Tuning (PEFT) of pre-trained Vision Transformer (ViT) models on downstream vision tasks …