相关论文: DPL: Decoupled Prototype Learning for Enhancing Ro…

Prompt learning methods have significantly extended the transferability of pre-trained Vision-Language Models (VLMs) like CLIP for various downstream tasks. These methods adopt handcraft templates or learnable vectors to provide text or…

Medical images are often more difficult to acquire than natural images due to the specialism of the equipment and technology, which leads to less medical image datasets. So it is hard to train a strong pretrained medical vision model. How…

All-in-One Image Restoration (AiOIR), which addresses diverse degradation types with a unified model, presents significant challenges in designing task-aware prompts that effectively guide restoration across multiple degradation scenarios.…

Decision-Focused Learning (DFL) is an emerging learning paradigm that tackles the task of training a machine learning (ML) model to predict missing parameters of an incomplete optimization problem, where the missing parameters are…

Recent progress in deterministic prompt learning has become a promising alternative to various downstream vision tasks, enabling models to learn powerful visual representations with the help of pre-trained vision-language models. However,…

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…

How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…

Standard decoding approaches rely on model-based channel estimation methods to compensate for varying channel effects, which degrade in performance whenever there is a model mismatch. Recently proposed Deep learning based neural decoders…

Vision-language models (VLMs) have demonstrated remarkable zero-shot performance across various classification tasks. Nonetheless, their reliance on hand-crafted text prompts for each task hinders efficient adaptation to new tasks. While…

Vision In-Context Learning (VICL) enables inpainting models to quickly adapt to new visual tasks from only a few prompts. However, existing methods suffer from two key issues: (1) selecting only the most similar prompt discards…

Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics…

Recent Vision-Language Models (VLMs) enable zero-shot classification by aligning images and text in a shared space, a promising approach for data-scarce conditions. However, the influence of prompt design on recognizing visually similar…

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…

Although person re-identification has made impressive progress, occlusion caused by obstacles remains an unsettled issue in real applications. The difficulty lies in the mismatch between incomplete occluded samples and holistic identity…

In continual learning, solving the catastrophic forgetting problem may make the models fall into the stability-plasticity dilemma. Moreover, inter-task confusion will also occur due to the lack of knowledge exchanges between different…

Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semi-supervised approach to…

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the…

Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models…

Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…

In Zero-Shot Learning (ZSL), embedding-based methods enable knowledge transfer from seen to unseen classes by learning a visual-semantic mapping from seen-class images to class-level semantic prototypes (e.g., attributes). However, these…