Abstract Deep Neural Networks (DNNs) learn representation from data with an impressive capability, and brought important breakthroughs for processing images, time-series, natural …
CY Wang, A Bochkovskiy… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Real-time object detection is one of the most important research topics in computer vision. As new approaches regarding architecture optimization and training optimization are …
Q Yu, J He, X Deng, X Shen… - Advances in Neural …, 2024 - proceedings.neurips.cc
Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories in diverse environments. One way to address this …
G Cheng, X Yuan, X Yao, K Yan, Q Zeng… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the …
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer …
Y Wang, X Zhang, T Yang, J Sun - … of the AAAI conference on artificial …, 2022 - ojs.aaai.org
In this paper, we propose a novel query design for the transformer-based object detection. In previous transformer-based detectors, the object queries are a set of learned embeddings …
Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a …
CY Wang, A Bochkovskiy… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining …
Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory …