.png){kind=icon}
返回
Sparse attention block: Aggregating contextual information for object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2021.108418.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
It is well recognized that the contextual information of surrounding objects is beneficial for object detection. Such contextual information can often be obtained from long-range dependencies. This paper proposes a sparse attention block to capture long-range dependencies in an efficient way. Unlike the conventional non-local block, which generates a dense attention map to characterize the dependency between any two positions of the input feature map, our sparse attention block samples the most representative positions for contextual information aggregation. After searching for local peaks in a heat map of the given input feature map, it adaptively selects a sparse set of positions to represent the relationship between query and key elements. With the obtained sparse positions, our sparse attention block can well model long-range dependencies, and greatly improve the object detection performance at the additional cost of < 2% GPU memory and computation of the conventional non-local block. This sparse attention block can be easily plugged into various object detection frameworks, such as Faster R-CNN, RetinaNet and Mask R-CNN. Experiments on COCO benchmark confirm that our sparse attention block can boost the detection accuracy with significant gains ranging from 1.4% to 1.9% and negligible overhead of computation and memory usage.
Keyword:
Object detection
Self-attention
Convolution neural network
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Semantic segmentation using stride spatial pyramid pooling and dual attention decoder.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Generation of hydroxyl radicals by urban suspended particulate air matter. The role of iron ions城市悬浮颗粒物产生羟基自由基。铁离子的作用:
PREAI
分享收藏MDFN: Multi-scale deep feature learning network for object detectionMDFN: 用于目标检测的多尺度深度特征学习网络PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Multi-model ensemble with rich spatial information for object detectionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Attention CoupleNet: Fully Convolutional Attention Coupling Network for Object Detection注意力耦合网: 用于物体检测的全卷积注意力耦合网络
PREAI
分享收藏分享收藏
查看更多内容