Related papers: Diversity-Aware Meta Visual Prompting
Action recognition models have achieved impressive results by incorporating scene-level annotations, such as objects, their relations, 3D structure, and more. However, obtaining annotations of scene structure for videos requires a…
Vision models are often vulnerable to out-of-distribution (OOD) samples without adapting. While visual prompts offer a lightweight method of input-space adaptation for large-scale vision models, they rely on a high-dimensional additive…
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a…
Limited labeled data makes it hard to train models from scratch in medical domain, and an important paradigm is pre-training and then fine-tuning. Large pre-trained models contain rich representations, which can be adapted to downstream…
Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…
With the surge of large-scale pre-trained models (PTMs), fine-tuning these models to numerous downstream tasks becomes a crucial problem. Consequently, parameter efficient transfer learning (PETL) of large models has grasped huge attention.…
We introduce Venn Diagram (VD) Prompting, an innovative prompting technique which allows Large Language Models (LLMs) to combine and synthesize information across complex, diverse and long-context documents in knowledge-intensive…
Multimodal few-shot learning is challenging due to the large domain gap between vision and language modalities. Existing methods are trying to communicate visual concepts as prompts to frozen language models, but rely on hand-engineered…
Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features. In DG, the prevalent practice of constraining models to a fixed structure or uniform parameterization to…
Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…
In this paper, we aim to adapt a model at test-time using a few unlabeled data to address distribution shifts. To tackle the challenges of extracting domain knowledge from a limited amount of data, it is crucial to utilize correlated…
Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on…
Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstream tasks with limited data. Its parameter efficiency makes…
Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…
Parameter-Efficient Fine-Tuning (PEFT) has emerged to mitigate the computational demands of large-scale models. Within computer vision, adapter-based PEFT methods are often favored over prompt-based approaches like Visual Prompt Tuning…
With a surge of large-scale pre-trained models, parameter-efficient transfer learning (PETL) of large models has garnered significant attention. While promising, they commonly rely on two optimistic assumptions: 1) full access to the…
Effectively handling the co-occurrence of non-IID data and long-tailed distributions remains a critical challenge in federated learning. While fine-tuning vision-language models (VLMs) like CLIP has shown to be promising in addressing…
Vision-language models (VLMs), such as CLIP, have shown strong generalization under zero-shot settings, yet adapting them to downstream tasks with limited supervision remains a significant challenge. Existing multi-modal prompt learning…
The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of…
Visual prompting, an efficient method for transfer learning, has shown its potential in vision tasks. However, previous works focus exclusively on VP from standard source models, it is still unknown how it performs under the scenario of a…