Meta-learning is a practical learning paradigm to transfer skills across tasks from a few
examples. Nevertheless, the existence of task distribution shifts tends to weaken meta …

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

Recent VLMs, pre-trained on large amounts of image-text pairs to align both modalities,
have opened the way to open-vocabulary semantic segmentation. Given an arbitrary set of …

Pre-trained vision-language models like CLIP have remarkably adapted to various
downstream tasks. Nonetheless, their performance heavily depends on the specificity of the …

Foundation models enable prompt-based classifiers for zero-shot and few-shot learning.
Nonetheless, the conventional method of employing fixed prompts suffers from distributional …

In real-world scenarios, achieving domain adaptation and generalization poses significant
challenges, as models must adapt to or generalize across unknown target distributions …

Test-time prompt tuning enhances zero-shot generalization of vision-language models but
tends to ignore the relatedness among test samples during inference. Online test-time …

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 …

Despite being a successful example of emerging capability, vision-language foundation
models for low-shot vision classification have a limited ability to sufficiently generalize to the …

Vision language model (VLM) has been designed for large scale image-text alignment as a
pretrained foundation model. For downstream few shot classification tasks, parameter …