Related papers: One-shot Text Field Labeling using Attention and B…
Text-guided image retrieval is to incorporate conditional text to better capture users' intent. Traditionally, the existing methods focus on minimizing the embedding distances between the source inputs and the targeted image, using the…
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…
The problem of change detection in images finds application in different domains like diagnosis of diseases in the medical field, detecting growth patterns of cities through remote sensing, and finding changes in legal documents and…
This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with…
Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to each image makes the…
Within the field of image and video recognition, the traditional approach is a dataset split into fixed training and test partitions. However, the labelling of the training set is time-consuming, especially as datasets grow in size and…
Generating images from text has become easier because of the scaling of diffusion models and advancements in the field of vision and language. These models are trained using vast amounts of data from the Internet. Hence, they often contain…
We present a framework to take advantage of existing labels at inference, called \textit{exemplars}, in order to improve the performance of object detection in medical images. The method, \textit{exemplar diffusion}, leverages existing…
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This…
Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries. Recently, template-based and sequence-to-sequence approaches were proposed to support complex queries,…
Image translation between two domains is a class of problems aiming to learn mapping from an input image in the source domain to an output image in the target domain. It has been applied to numerous domains, such as data augmentation,…
The success of deep learning methods hinges on the availability of large training datasets annotated for the task of interest. In contrast to human intelligence, these methods lack versatility and struggle to learn and adapt quickly to new…
A foundational task for the digital analysis of documents is text line segmentation. However, automating this process with deep learning models is challenging because it requires large, annotated datasets that are often unavailable for…
With their combined spectral depth and geometric resolution, hyperspectral remote sensing images embed a wealth of complex, non-linear information that challenges traditional computer vision techniques. Yet, deep learning methods known for…
Since the low quality of document images will greatly undermine the chances of success in automatic text recognition and analysis, it is necessary to assess the quality of document images uploaded in online business process, so as to reject…
Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes…
We present a comprehensive system for addressing Tasks A, B, and C of the LLMs4OL 2025 challenge, which together span the full ontology construction pipeline: term extraction, typing, and taxonomy discovery. Our approach combines…
Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases,…
Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a…
Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the problem of cross-domain few-shot learning where there is a large…