DeepAI AI Chat
Log In Sign Up

Deep Feature Pyramid Reconfiguration for Object Detection

by   Tao Kong, et al.

State-of-the-art object detectors usually learn multi-scale representations to get better results by employing feature pyramids. However, the current designs for feature pyramids are still inefficient to integrate the semantic information over different scales. In this paper, we begin by investigating current feature pyramids solutions, and then reformulate the feature pyramid construction as the feature reconfiguration process. Finally, we propose a novel reconfiguration architecture to combine low-level representations with high-level semantic features in a highly-nonlinear yet efficient way. In particular, our architecture which consists of global attention and local reconfigurations, is able to gather task-oriented features across different spatial locations and scales, globally and locally. Both the global attention and local reconfiguration are lightweight, in-place, and end-to-end trainable. Using this method in the basic SSD system, our models achieve consistent and significant boosts compared with the original model and its other variations, without losing real-time processing speed.


Feature Pyramid Networks for Object Detection

Feature pyramids are a basic component in recognition systems for detect...

AugFPN: Improving Multi-scale Feature Learning for Object Detection

Current state-of-the-art detectors typically exploit feature pyramid to ...

Global Context Aware RCNN for Object Detection

RoIPool/RoIAlign is an indispensable process for the typical two-stage o...

GraphFPN: Graph Feature Pyramid Network for Object Detection

Feature pyramids have been proven powerful in image understanding tasks ...

Centralized Feature Pyramid for Object Detection

Visual feature pyramid has shown its superiority in both effectiveness a...

Learning Feature Interactions with Lorentzian Factorization Machine

Learning representations for feature interactions to model user behavior...

Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture for Scene Segmentation

Despite the growing success of Convolution neural networks (CNN) in the ...