Speed/accuracy trade-offs for modern convolutional object detectors

The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems... (read more)

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Detection COCO test-dev Faster R-CNN box AP 34.7 # 100

Methods used in the Paper


METHOD TYPE
ReLU
Activation Functions
Dropout
Regularization
Dense Connections
Feedforward Networks
Max Pooling
Pooling Operations
VGG
Convolutional Neural Networks
Non Maximum Suppression
Proposal Filtering
1x1 Convolution
Convolutions
SSD
Object Detection Models
RPN
Region Proposal
Softmax
Output Functions
Position-Sensitive RoI Pooling
RoI Feature Extractors
Convolution
Convolutions
RoIPool
RoI Feature Extractors
Faster R-CNN
Object Detection Models
R-FCN
Object Detection Models