Receptive Field Block

Introduced by Liu et al. in Receptive Field Block Net for Accurate and Fast Object Detection

Receptive Field Block (RFB) is a module for strengthening the deep features learned from lightweight CNN models so that they can contribute to fast and accurate detectors. Specifically, RFB makes use of multi-branch pooling with varying kernels corresponding to RFs of different sizes, applies dilated convolution layers to control their eccentricities, and reshapes them to generate final representation.

Source: Receptive Field Block Net for Accurate and Fast Object Detection

Latest Papers

PAPER DATE
Perceptual Extreme Super Resolution Network with Receptive Field Block
Taizhang ShangQiuju DaiShengchen ZhuTong YangYandong Guo
2020-05-26
YOLOv4: Optimal Speed and Accuracy of Object Detection
| Alexey BochkovskiyChien-Yao WangHong-Yuan Mark Liao
2020-04-23
RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation
Liuyuan DengMing YangTianyi LiYuesheng HeChunxiang Wang
2019-06-29
FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
Xiaoye SunGongyan LiShaoyun Xu
2019-05-24
Receptive Field Block Net for Accurate and Fast Object Detection
| Songtao LiuDi HuangYunhong Wang
2017-11-21

Tasks

TASK PAPERS SHARE
Object Detection 3 37.50%
Real-Time Object Detection 2 25.00%
Super-Resolution 1 12.50%
adversarial training 1 12.50%
Semantic Segmentation 1 12.50%

Categories