Related papers: Linguistics-aware Masked Image Modeling for Self-s…
Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character…
Image captioning can automatically generate captions for the given images, and the key challenge is to learn a mapping function from visual features to natural language features. Existing approaches are mostly supervised ones, i.e., each…
Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual features that may constitute a classification decision. Recently,…
Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this…
When captioning an image, people describe objects in diverse ways, such as by using different terms and/or including details that are perceptually noteworthy to them. Descriptions can be especially unique across languages and cultures.…
Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…
Hyperspectral images (HSIs) capture rich spectral signatures that reveal vital material properties, offering broad applicability across various domains. However, the scarcity of labeled HSI data limits the full potential of deep learning,…
In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment…
Recently, Referring Image Segmentation (RIS) frameworks that pair the Multimodal Large Language Model (MLLM) with the Segment Anything Model (SAM) have achieved impressive results. However, adapting MLLM to segmentation is computationally…
Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities. For this purpose, inspired by the success of masked language modeling (MLM) tasks…
Inspired by the masked language modeling (MLM) in natural language processing tasks, the masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. However, the high random mask ratio…
Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent…
We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation. While existing work has largely focused on…
Recent advances in text-to-image (T2I) generation have enabled visually coherent image synthesis from descriptions, but generating images containing multiple given subjects remains challenging. As the number of reference identities…
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…
Continual learning is essential for medical image classification systems to adapt to dynamically evolving clinical environments. The integration of multimodal information can significantly enhance continual learning of image classes.…
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…
Recent masked image modeling (MIM) has received much attention in self-supervised learning (SSL), which requires the target model to recover the masked part of the input image. Although MIM-based pre-training methods achieve new…
Semantic segmentation plays a crucial role in enabling machines to understand and interpret visual scenes at a pixel level. While traditional segmentation methods have achieved remarkable success, their generalization to diverse scenes and…
Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method…