相关论文: Realistic Unsupervised CLIP Fine-tuning with Unive…

Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to…

Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty…

The recently proposed unlabeled-unlabeled (UU) classification method allows us to train a binary classifier only from two unlabeled datasets with different class priors. Since this method is based on the empirical risk minimization, it…

Multimodal search has revolutionized the fashion industry, providing a seamless and intuitive way for users to discover and explore fashion items. Based on their preferences, style, or specific attributes, users can search for products by…

We consider unsupervised domain adaptation (UDA) for semantic segmentation in which the model is trained on a labeled source dataset and adapted to an unlabeled target dataset. Unfortunately, current self-training methods are susceptible to…

The problem of detecting whether a test sample is from in-distribution (i.e., training distribution by a classifier) or out-of-distribution sufficiently different from it arises in many real-world machine learning applications. However, the…

State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.…

Contrastive Language-Image Pre-training (CLIP) has demonstrated remarkable generalization ability and strong performance across a wide range of vision-language tasks. However, due to the lack of region-level supervision, CLIP exhibits…

Extending CLIP models to semantic segmentation remains challenging due to the misalignment between their image-level pre-training objectives and the pixel-level visual understanding required for dense prediction. While prior efforts have…

Audio-Visual Video Parsing is a task to predict the events that occur in video segments for each modality. It often performs in a weakly supervised manner, where only video event labels are provided, i.e., the modalities and the timestamps…

Deep learning models are vulnerable to performance degradation when encountering out-of-distribution (OOD) images, potentially leading to misdiagnoses and compromised patient care. These shortcomings have led to great interest in the field…

Ensuring model explainability and robustness is essential for reliable deployment of deep vision systems. Current methods for evaluating robustness rely on collecting and annotating extensive test sets. While this is common practice, the…

Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based…

Vision-language models, such as CLIP, have shown promising Out-of-Distribution (OoD) generalization under various types of distribution shifts. Recent studies attempted to investigate the leading cause of this capability. In this work, we…

Recent advancements in pre-trained vision-language models like CLIP have enabled the task of open-vocabulary segmentation. CLIP demonstrates impressive zero-shot capabilities in various downstream tasks that require holistic image…

Ultrasound foundation models have achieved strong performance on structured prediction tasks but remain exclusively vision-based, limiting zero-shot and few-shot transfer to novel tasks where task-specific annotation is scarce. We address…

Foundation models (e.g., CLIP or DINOv2) have shown their impressive learning and transfer capabilities in a wide range of visual tasks, by training on a large corpus of data and adapting to specific downstream tasks. It is, however,…

Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual…

Visual Grounding (VG) is a crucial topic in the field of vision and language, which involves locating a specific region described by expressions within an image. To reduce the reliance on manually labeled data, unsupervised visual grounding…

In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of annotation often limits the quantity of labels available for training in any…