DeepAI AI Chat
Log In Sign Up

The Devil is in the Decoder

by   Zbigniew Wojna, et al.

Many machine vision applications require predictions for every pixel of the input image (for example semantic segmentation, boundary detection). Models for such problems usually consist of encoders which decreases spatial resolution while learning a high-dimensional representation, followed by decoders who recover the original input resolution and result in low-dimensional predictions. While encoders have been studied rigorously, relatively few studies address the decoder side. Therefore this paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise prediction tasks. Our contributions are: (1) Decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce a novel decoder: bilinear additive upsampling. (3) We introduce new residual-like connections for decoders. (4) We identify two decoder types which give a consistently high performance.


page 2

page 4

page 5

page 6

page 7

page 10

page 15


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

Recent semantic segmentation methods exploit encoder-decoder architectur...

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling

We propose a novel deep architecture, SegNet, for semantic pixel wise im...

Probabilistic Pixel-Adaptive Refinement Networks

Encoder-decoder networks have found widespread use in various dense pred...

Pixel-wise Ear Detection with Convolutional Encoder-Decoder Networks

Object detection and segmentation represents the basis for many tasks in...

Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting

This paper reviews recent deep-learning-based matting research and conce...