mlsanityData to 7 Oct 2026

Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization

arXiv 2106.03088 ↗First posted 6 Jun 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Visual pattern recognition over agricultural areas is an important application of aerial image processing. In this paper, we consider the multi-modality nature of agricultural aerial images and show that naively combining different modalities together without taking the feature divergence into account can lead to sub-optimal results. Thus, we apply a Switchable Normalization block to our DeepLabV3 segmentation model to alleviate the feature divergence. Using the popular symmetric Kullback Leibler divergence measure, we show that our model can greatly reduce the divergence between RGB and near-infrared channels. Together with a hybrid loss function, our model achieves nearly 10% improvements in mean IoU over previously published baseline.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 6 Jun 2021.

Builds on

16 of 21 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  8. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  9. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  11. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  12. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
4 more
  1. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  2. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  3. 2020Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysiscited by 61
  4. 2018Differentiable Learning-to-Normalize via Switchable Normalizationcited by 33

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 1; 2024: 0; 2025: 1.

5 papers.

  1. 2022Augmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Imagescited by 8
  2. 2023HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Informationcited by 8
  3. 2021A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Imagescited by 6
  4. 2021Rail-5k: a Real-World Dataset for Rail Surface Defects Detectioncited by 4
  5. 2025Dual Atrous Separable Convolution for Improving Agricultural Semantic Segmentationcited by 1