相关论文: Learning Expressive Prompting With Residuals for V…

Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning a tiny set of context vectors. Nevertheless, in this work,…

Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts. In principle, the well-learned knowledge structure of the VLMs should be inherited…

Distribution shift widely exists in medical images acquired from different medical centres and poses a significant obstacle to deploying the pre-trained semantic segmentation model in real-world applications. Test-time adaptation has proven…

Recent advances in vision Transformers (ViTs) have come with a voracious appetite for computing power, high-lighting the urgent need to develop efficient training methods for ViTs. Progressive learning, a training scheme where the model…

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded…

Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes. Additionally, our…

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of…

The prompt has become an effective linguistic tool for utilizing pre-trained language models. However, in few-shot scenarios, subtle changes in the prompt design always make the result widely different, and the prompt learning methods also…

Prompt learning has become a dominant paradigm for adapting vision-language models (VLMs) such as CLIP to downstream tasks without modifying pretrained weights. While extending prompts to both vision and text encoders across multiple…

Pre-training & fine-tuning is a prevalent paradigm in computer vision (CV). Recently, parameter-efficient transfer learning (PETL) methods have shown promising performance in adapting to downstream tasks with only a few trainable…

Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their…

Large-scale vision-language (V-L) models have demonstrated remarkable generalization capabilities for downstream tasks through prompt tuning. However, the mechanisms behind the learned text representations are unknown, limiting further…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

We investigate whether prompts learned independently for different tasks can be later combined through prompt algebra to obtain a model that supports composition of tasks. We consider Visual Language Models (VLM) with prompt tuning as our…

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Although current prompt learning methods have successfully been designed to effectively reuse the large pre-trained models without fine-tuning their large number of parameters, they still have limitations to be addressed, i.e., without…

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to…

Prompt learning has surfaced as an effective approach to enhance the performance of Vision-Language Models (VLMs) like CLIP when applied to downstream tasks. However, current learnable prompt tokens are primarily used for the single phase…