FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction

Abstract

In this paper, we focus on devising a versatile framework for dense pixelwise prediction whose goal is to assign a discrete or continuous label to each pixel for an image. It is well-known that the reduced feature resolution due to repeated subsampling operations poses a serious challenge to Fully Convolutional Network (FCN) based models. In contrast to the commonly-used strategies, such as dilated convolution and encoder-decoder structure, we introduce the Flattening Module to produce high-resolution predictions without either removing any subsampling operations or building a complicated decoder module. In addition, the Flattening Module is lightweight and can be easily combined with any existing FCNs, allowing the model builder to trade off among model size, computational cost and accuracy by simply choosing different backbone networks. We empirically demonstrate the effectiveness of the proposed Flattening Module through competitive results in human pose estimation on MPII, semantic segmentation on PASCAL-Context and object detection on PASCAL VOC. We hope that the proposed approach can serve as a simple and strong alternative of current dominant dense pixelwise prediction frameworks.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Rethinking Atrous Convolution for Semantic Image Segmentation
• A guide to convolution arithmetic for deep learning
• High-Resolution Representations for Labeling Pixels and Regions
• OCNet: Object Context Network for Scene Parsing
• Deformable Convolutional Networks
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
• Convolutional Neural Fabrics
• CenterNet: Keypoint Triplets for Object Detection
• Deep High-Resolution Representation Learning for Human Pose Estimation
• Pixel Deconvolutional Networks
• Dual Path Networks

Cited by in corpus (2)

• Artificial Intelligence in the Creative Industries: A Review
• The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation