Light-Weight RetinaNet for Object Detection

24 May 2019 Yixing Li Fengbo Ren

Object detection has gained great progress driven by the development of deep learning. Compared with a widely studied task -- classification, generally speaking, object detection even need one or two orders of magnitude more FLOPs (floating point operations) in processing the inference task... (read more)

PDF Abstract

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Pointwise Convolution
Convolutions
Depthwise Convolution
Convolutions
Depthwise Separable Convolution
Convolutions
Inverted Residual Block
Skip Connection Blocks
MobileNetV2
Image Models
Average Pooling
Pooling Operations
Global Average Pooling
Pooling Operations
Batch Normalization
Normalization
Softmax
Output Functions
Leaky ReLU
Activation Functions
Darknet-19
Convolutional Neural Networks
Non Maximum Suppression
Proposal Filtering
Dropout
Regularization
Dense Connections
Feedforward Networks
Max Pooling
Pooling Operations
SSD
Object Detection Models
YOLOv2
Object Detection Models
YOLOv1
Object Detection Models
1x1 Convolution
Convolutions
Convolution
Convolutions
FPN
Feature Extractors
Focal Loss
Loss Functions
RetinaNet
Object Detection Models