mlsanityData to 14 Oct 2026

The Devil is in the Decoder: Classification, Regression and GANs

arXiv 1707.05847 ↗First posted 18 Jul 2017cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 7; 2023: 5; 2024: 2; 2025: 1.

22 papers.

Sort:

  1. 2021ResViT: Residual vision transformers for multi-modal medical image synthesiscited by 177
  2. 2021Unpaired Deep Image Deraining Using Dual Contrastive Learningcited by 60
  3. 2023Towards Unified Deep Image Deraining: A Survey and A New Benchmarkcited by 34
  4. 2022SAPA: Similarity-Aware Point Affiliation for Feature Upsamplingcited by 32
  5. 2021Prototype Guided Federated Learning of Visual Feature Representationscited by 22
  6. 2022Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advancescited by 22
  7. 2021Do We Really Need Dice? The Hidden Region-Size Biases of Segmentation Lossescited by 12
  8. 2024HS3-Bench: A Benchmark and Strong Baseline for Hyperspectral Semantic Segmentation in Driving Scenarioscited by 12
  9. 2025Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Derainingcited by 11
  10. 2021Double Encoder-Decoder Networks for Gastrointestinal Polyp Segmentationcited by 7
  11. 2022Context-Aware Scene Prediction Network (CASPNet)cited by 7
  12. 2024A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsamplingcited by 7
10 more
  1. 2023MRI Scan Synthesis Methods based on Clustering and Pix2Pixcited by 6
  2. 2021Improved-Mask R-CNN: Towards an Accurate Generic MSK MRI instance segmentation platform (Data from the Osteoarthritis Initiative)cited by 3
  3. 2021Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Losscited by 1
  4. 2022DXM-TransFuse U-net: Dual Cross-Modal Transformer Fusion U-net for Automated Nerve Identificationcited by 1
  5. 2022VoloGAN: Adversarial Domain Adaptation for Synthetic Depth Datacited by 1
  6. 2023On Point Affiliation in Feature Upsamplingcited by 1
  7. 2022HCFormer: Unified Image Segmentation with Hierarchical Clusteringcited by 0
  8. 2022Deformably-Scaled Transposed Convolutioncited by 0
  9. 2023Learning to Detect Touches on Cluttered Tablescited by 0
  10. 2023Feature Aggregation in Joint Sound Classification and Localization Neural Networkscited by 0