The Devil is in the Decoder: Classification, Regression and GANs
arXiv:1707.05847
Abstract
Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consist of encoders which decrease 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. This paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise tasks ranging from classification, regression to synthesis. Our contributions are: (1) Decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce new residual-like connections for decoders. (3) We introduce a novel decoder: bilinear additive upsampling. (4) We explore prediction artifacts.
References in corpus (7)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Spectral Normalization for Generative Adversarial Networks
- Improved Training of Wasserstein GANs
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Are GANs Created Equal? A Large-Scale Study
- Situational Object Boundary Detection
Cited by in corpus (8)
- Augmentation for small object detection
- Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
- Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models
- A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation
- Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
- DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis
- Spectrally Consistent UNet for High Fidelity Image Transformations
- Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation