[PDF][PDF] 多尺度目标检测的深度学习研究综述
陈科圻， 朱志亮， 邓小明， 马翠霞， 王宏安 - 软件学报, 2020 - jos.org.cn
目标检测一直以来都是计算机视觉领域的研究热点之一, 其任务是返回给定图像中的单个或多个
特定目标的类别与矩形包围框坐标. 随着神经网络研究的飞速进展, R-CNN 检测器的诞生标志着 …
特定目标的类别与矩形包围框坐标. 随着神经网络研究的飞速进展, R-CNN 检测器的诞生标志着 …
Uni-perceiver v2: A generalist model for large-scale vision and vision-language tasks
Despite the remarkable success of foundation models, their task-specific fine-tuning
paradigm makes them inconsistent with the goal of general perception modeling. The key to …
paradigm makes them inconsistent with the goal of general perception modeling. The key to …
Uni-perceiver: Pre-training unified architecture for generic perception for zero-shot and few-shot tasks
Biological intelligence systems of animals perceive the world by integrating information in
different modalities and processing simultaneously for various tasks. In contrast, current …
different modalities and processing simultaneously for various tasks. In contrast, current …
The all-seeing project: Towards panoptic visual recognition and understanding of the open world
We present the All-Seeing (AS) project: a large-scale data and model for recognizing and
understanding everything in the open world. Using a scalable data engine that incorporates …
understanding everything in the open world. Using a scalable data engine that incorporates …
Towards all-in-one pre-training via maximizing multi-modal mutual information
To effectively exploit the potential of large-scale models, various pre-training strategies
supported by massive data from different sources are proposed, including supervised pre …
supported by massive data from different sources are proposed, including supervised pre …
Uni-perceiver-moe: Learning sparse generalist models with conditional moes
To build an artificial neural network like the biological intelligence system, recent works have
unified numerous tasks into a generalist model, which can process various tasks with shared …
unified numerous tasks into a generalist model, which can process various tasks with shared …
Contrastive language-image pre-training with knowledge graphs
Recent years have witnessed the fast development of large-scale pre-training frameworks
that can extract multi-modal representations in a unified form and achieve promising …
that can extract multi-modal representations in a unified form and achieve promising …
Deep learning for multi-scale object detection: A survey
陈科圻， 朱志亮， 邓小明， 马翠霞， 王宏安 - Journal of Software, 2020 - jos.org.cn
目标检测一直以来都是计算机视觉领域的研究热点之一, 其任务是返回给定图像中的单个或多个
特定目标的类别与矩形包围框坐标. 随着神经网络研究的飞速进展, R-CNN 检测器的诞生标志着 …
特定目标的类别与矩形包围框坐标. 随着神经网络研究的飞速进展, R-CNN 检测器的诞生标志着 …
Dynamic zoom-in network for fast object detection in large images
We introduce a generic framework that reduces the computational cost of object detection
while retaining accuracy for scenarios where objects with varied sizes appear in high …
while retaining accuracy for scenarios where objects with varied sizes appear in high …
Transgaga: Geometry-aware unsupervised image-to-image translation
Unsupervised image-to-image translation aims at learning a mapping between two visual
domains. However, learning a translation across large geometry variations al-ways ends up …
domains. However, learning a translation across large geometry variations al-ways ends up …