相关论文: Vision Transformer Adapters for Generalizable Mult…

Transferring knowledge from an image synthesis model trained on a large dataset is a promising direction for learning generative image models from various domains efficiently. While previous works have studied GAN models, we present a…

Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the…

Vision-Language Models (VLMs) have been widely used in various visual recognition tasks due to their remarkable generalization capabilities. As these models grow in size and complexity, fine-tuning becomes costly, emphasizing the need to…

Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additional parameters are introduced to excavate the task-specific…

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…

While parameter efficient tuning (PET) methods have shown great potential with transformer architecture on Natural Language Processing (NLP) tasks, their effectiveness with large-scale ConvNets is still under-studied on Computer Vision (CV)…

Aiming towards a holistic understanding of multiple downstream tasks simultaneously, there is a need for extracting features with better transferability. Though many latest self-supervised pre-training methods have achieved impressive…

Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive transformer network (ADAPTER), a simple but effective solution…

Visual recognition algorithms are required today to exhibit adaptive abilities. Given a deep model trained on a specific, given task, it would be highly desirable to be able to adapt incrementally to new tasks, preserving scalability as the…

To bridge the gap between vision and language modalities, Multimodal Large Language Models (MLLMs) usually learn an adapter that converts visual inputs to understandable tokens for Large Language Models (LLMs). However, most adapters…

Meta-learning is widely used in few-shot classification and function regression due to its ability to quickly adapt to unseen tasks. However, it has not yet been well explored on regression tasks with high dimensional inputs such as images.…

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and…

Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing…

Pre-trained Vision-Language Models (VLMs), \textit{e.g.} CLIP, have become essential tools in multimodal transfer learning. However, fine-tuning VLMs in few-shot scenarios poses significant challenges in balancing task-specific adaptation…

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…

Prompt learning is a dominant paradigm for adapting pre-trained Vision-Language Models (VLMs) to downstream tasks. However, existing methods often rely on a simplistic, layer-centric view, assuming shallow layers capture general features…