To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Denoising diffusion models, a class of generative models, have garnered immense interest
lately in various deep-learning problems. A diffusion probabilistic model defines a forward …

Abstract We introduce the Segment Anything (SA) project: a new task, model, and dataset for
image segmentation. Using our efficient model in a data collection loop, we built the largest …

Medical image segmentation is a critical component in clinical practice, facilitating accurate
diagnosis, treatment planning, and disease monitoring. However, existing methods, often …

Modern autonomous driving system is characterized as modular tasks in sequential order,
ie, perception, prediction, and planning. In order to perform a wide diversity of tasks and …

In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO
series and is easily extensible for many object recognition tasks such as instance …

In the realm of medical image segmentation, both CNN-based and Transformer-based
models have been extensively explored. However, CNNs exhibit limitations in long-range …

Camouflaged object detection (COD) aims to address the tough issue of identifying
camouflaged objects visually blended into the surrounding backgrounds. COD is a …

In semi-supervised medical image segmentation, there exist empirical mismatch problems
between labeled and unlabeled data distribution. The knowledge learned from the labeled …

Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-
shot transfer performance and high versatility for numerous vision applications (like image …