DeepAI AI Chat
Log In Sign Up

Dynamic Feature Pyramid Networks for Object Detection

by   Mingjian Zhu, et al.
HUAWEI Technologies Co., Ltd.
Zhejiang University

This paper studies feature pyramid network (FPN), which is a widely used module for aggregating multi-scale feature information in the object detection system. The performance gain in most of the existing works is mainly contributed to the increase of computation burden, especially the floating number operations (FLOPs). In addition, the multi-scale information within each layer in FPN has not been well investigated. To this end, we first introduce an inception FPN in which each layer contains convolution filters with different kernel sizes to enlarge the receptive field and integrate more useful information. Moreover, we point out that not all objects need such a complicated calculation module and propose a new dynamic FPN (DyFPN). Each layer in the DyFPN consists of multiple branches with different computational costs. Specifically, the output features of DyFPN will be calculated by using the adaptively selected branch according to a learnable gating operation. Therefore, the proposed method can provide a more efficient dynamic inference for achieving a better trade-off between accuracy and detection performance. Extensive experiments conducted on benchmarks demonstrate that the proposed DyFPN significantly improves performance with the optimal allocation of computation resources. For instance, replacing the FPN with the inception FPN improves detection accuracy by 1.6 AP using the Faster R-CNN paradigm on COCO minival, and the DyFPN further reduces about 40 similar performance.


ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection

Feature Pyramid Network (FPN) has been an essential module for object de...

Selective Multi-Scale Learning for Object Detection

Pyramidal networks are standard methods for multi-scale object detection...

RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection

Feature pyramid networks (FPN) are widely exploited for multi-scale feat...

Fast Object Detection with Latticed Multi-Scale Feature Fusion

Scale variance is one of the crucial challenges in multi-scale object de...

Delving into the Scale Variance Problem in Object Detection

Object detection has made substantial progress in the last decade, due t...

DRPN: Making CNN Dynamically Handle Scale Variation

Based on our observations of infrared targets, serious scale variation a...

Efficient Human Pose Estimation by Learning Deeply Aggregated Representations

In this paper, we propose an efficient human pose estimation network (DA...