Fractal Pyramid Networks

06/28/2021
by   Zhiqiang Deng, et al.
0

We propose a new network architecture, the Fractal Pyramid Networks (PFNs) for pixel-wise prediction tasks as an alternative to the widely used encoder-decoder structure. In the encoder-decoder structure, the input is processed by an encoding-decoding pipeline that tries to get a semantic large-channel feature. Different from that, our proposed PFNs hold multiple information processing pathways and encode the information to multiple separate small-channel features. On the task of self-supervised monocular depth estimation, even without ImageNet pretrained, our models can compete or outperform the state-of-the-art methods on the KITTI dataset with much fewer parameters. Moreover, the visual quality of the prediction is significantly improved. The experiment of semantic segmentation provides evidence that the PFNs can be applied to other pixel-wise prediction tasks, and demonstrates that our models can catch more global structure information.

READ FULL TEXT

page 3

page 7

page 8

research
08/26/2019

SPGNet: Semantic Prediction Guidance for Scene Parsing

Multi-scale context module and single-stage encoder-decoder structure ar...
research
02/01/2017

Pixel-wise Ear Detection with Convolutional Encoder-Decoder Networks

Object detection and segmentation represents the basis for many tasks in...
research
03/05/2019

Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation

Recent semantic segmentation methods exploit encoder-decoder architectur...
research
07/29/2022

Transfer Learning for Segmentation Problems: Choose the Right Encoder and Skip the Decoder

It is common practice to reuse models initially trained on different dat...
research
01/03/2020

Segmentation of Cellular Patterns in Confocal Images of Melanocytic Lesions in vivo via a Multiscale Encoder-Decoder Network (MED-Net)

In-vivo optical microscopy is advancing into routine clinical practice f...
research
09/13/2021

CarNet: A Lightweight and Efficient Encoder-Decoder Architecture for High-quality Road Crack Detection

Pixel-wise crack detection is a challenging task because of poor continu...
research
12/21/2021

Generalizing Interactive Backpropagating Refinement for Dense Prediction

As deep neural networks become the state-of-the-art approach in the fiel...

Please sign up or login with your details

Forgot password? Click here to reset