Related papers: CLIP-Guided Multi-Task Regression for Multi-View P…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

The CLIP model has established itself as a cornerstone of large-scale retrieval systems. However, its performance often degrades under distributional shifts such as multilingual, long-form, or multimodal queries. To avoid the prohibitive…

Mixed modality search -- retrieving information across a heterogeneous corpus composed of images, texts, and multimodal documents -- is an important yet underexplored real-world application. In this work, we investigate how contrastive…

Concept-based models naturally lend themselves to the development of inherently interpretable skin lesion diagnosis, as medical experts make decisions based on a set of visual patterns of the lesion. Nevertheless, the development of these…

Image-language learning has made unprecedented progress in visual understanding. These developments have come at high costs, as contemporary vision-language models require large model scales and amounts of data. We here propose a much…

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…

Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Accurate crop yield prediction is of utmost importance for informed decision-making in agriculture, aiding farmers, and industry stakeholders. However, this task is complex and depends on multiple factors, such as environmental conditions,…

Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and…

The number of leaves a plant has is one of the key traits (phenotypes) describing its development and growth. Here, we propose an automated, deep learning based approach for counting leaves in model rosette plants. While state-of-the-art…

The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP…

As Vision Language Models (VLMs) become increasingly accessible to farmers and agricultural experts, there is a growing need to evaluate their potential in specialized tasks. We present AgEval, a comprehensive benchmark for assessing VLMs'…

Plant phenology-the study of recurrent life cycle events-is essential for understanding ecosystem dynamics and their responses to climate change impacts. While Unmanned Aerial Vehicles (UAVs) and near-surface cameras enable high-resolution…

Existing vision-language models (VLMs) such as CLIP have showcased an impressive capability to generalize well across various downstream tasks. These models leverage the synergy between visual and textual information, enabling them to…

Test-time adaptation with pre-trained vision-language models, such as CLIP, aims to adapt the model to new, potentially out-of-distribution test data. Existing methods calculate the similarity between visual embedding and learnable class…

Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking with images aims to address this by generating an…

Recent face anti-spoofing (FAS) methods have shown remarkable cross-domain performance by employing vision-language models like CLIP. However, existing CLIP-based FAS models do not fully exploit CLIP's patch embedding tokens, failing to…

Multi-view clustering (MVC) has emerged as a powerful technique for extracting valuable insights from data characterized by multiple perspectives or modalities. Despite significant advancements, existing MVC methods struggle with…