M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

11/12/2018
by   Qijie Zhao, et al.
6

Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R-CNN, DetNet) to alleviate the problem arising from scale variation across object instances. Although these object detectors with feature pyramids achieve encouraging results, they have some limitations due to that they only simply construct the feature pyramid according to the inherent multi-scale, pyramidal architecture of the backbones which are actually designed for object classification task. Newly, in this work, we present a method called Multi-Level Feature Pyramid Network (MLFPN) to construct more effective feature pyramids for detecting objects of different scales. First, we fuse multi-level features (i.e. multiple layers) extracted by backbone as the base feature. Second, we feed the base feature into a block of alternating joint Thinned U-shape Modules and Feature Fusion Modules and exploit the decoder layers of each u-shape module as the features for detecting objects. Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels. To evaluate the effectiveness of the proposed MLFPN, we design and train a powerful end-to-end one-stage object detector we call M2Det by integrating it into the architecture of SSD, which gets better detection performance than state-of-the-art one-stage detectors. Specifically, on MS-COCO benchmark, M2Det achieves AP of 41.0 at speed of 11.8 FPS with single-scale inference strategy and AP of 44.2 with multi-scale inference strategy, which is the new state-of-the-art results among one-stage detectors. The code will be made available on <https://github.com/qijiezhao/M2Det.>

READ FULL TEXT

page 3

page 7

research
12/20/2019

MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection

Feature pyramids are widely exploited in many detectors to solve the sca...
research
11/05/2020

Fast Object Detection with Latticed Multi-Scale Feature Fusion

Scale variance is one of the crucial challenges in multi-scale object de...
research
12/11/2019

AugFPN: Improving Multi-scale Feature Learning for Object Detection

Current state-of-the-art detectors typically exploit feature pyramid to ...
research
08/07/2020

Multi-Level Temporal Pyramid Network for Action Detection

Currently, one-stage frameworks have been widely applied for temporal ac...
research
05/06/2020

Scale-Equalizing Pyramid Convolution for Object Detection

Feature pyramid has been an efficient method to extract features at diff...
research
11/16/2020

DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection

Although object detection has reached a milestone thanks to the great su...
research
12/06/2020

Towards Better Object Detection in Scale Variation with Adaptive Feature Selection

It is a common practice to exploit pyramidal feature representation to t...

Please sign up or login with your details

Forgot password? Click here to reset