Related papers: VIPAMIN: Visual Prompt Initialization via Embeddin…
The combination of transformers and masked image modeling (MIM) pre-training framework has shown great potential in various vision tasks. However, the pre-training computational budget is too heavy and withholds the MIM from becoming a…
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning…
Large pretrained vision-language models like CLIP have shown promising generalization capability, but may struggle in specialized domains (e.g., satellite imagery) or fine-grained classification (e.g., car models) where the visual concepts…
How to effectively exploit spatio-temporal information is crucial to capture target appearance changes in visual tracking. However, most deep learning-based trackers mainly focus on designing a complicated appearance model or template…
Vision generation remains a challenging frontier in artificial intelligence, requiring seamless integration of visual understanding and generative capabilities. In this paper, we propose a novel framework, Vision-Driven Prompt Optimization…
Prompt engineering is still the primary way for users of generative text-to-image models to manipulate generated images in a targeted way. Based on treating the model as a continuous function and by passing gradients between the image space…
Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning…
Visual In-Context Learning (VICL) aims to complete vision tasks by imitating pixel demonstrations. Recent work pioneered prompt fusion that combines the advantages of various demonstrations, which shows a promising way to extend VICL.…
As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…
Prompt tuning methods have achieved remarkable success in parameter-efficient fine-tuning on large pre-trained models. However, their application to dual-modal fusion-based visual-language pre-trained models (VLPMs), such as GLIP, has…
Pretrained visual-language models have extensive world knowledge and are widely used in visual and language navigation (VLN). However, they are not sensitive to indoor scenarios for VLN tasks. Another challenge for VLN is how the agent…
Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previous domain generalization algorithms. In this paper, we…
Prompt Learning has recently gained great popularity in bridging the gap between pretraining tasks and various downstream tasks. It freezes Pretrained Language Models (PLMs) and only tunes a few task-related parameters (prompts) for…
We propose structured prompt tuning, a simple and effective method to improve prompt tuning. Instead of prepending a sequence of tunable embeddings to the input, we generate the soft prompt embeddings through a hypernetwork. Our approach…
Prompt-Tuning is an efficient method for adapting pre-trained language models to new tasks with minimal computational overhead by modifying prompt embeddings. In this work, we investigate how crucial the phenomenon of embedding collapse,…
Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the…
Prompt learning represents a promising method for adapting pre-trained vision-language models (VLMs) to various downstream tasks by learning a set of text embeddings. One challenge inherent to these methods is the poor generalization…
As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim…
We introduce a language-grounded visual prompting method to adapt the visual encoder of vision-language models for downstream tasks. By capitalizing on language integration, we devise a parameter-efficient strategy to adjust the input of…
Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on…