A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-Labels

@article{Aksoy2021ACC,
  title={A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-Labels},
  author={Ahmet Aksoy and Mahdyar Ravanbakhsh and Tristan Kreuziger and Beg{\"u}m Demir},
  journal={2021 IEEE International Conference on Image Processing (ICIP)},
  year={2021},
  pages={3842-3846}
}
Collecting a large number of reliable training images annotated by multiple land-cover class labels in the framework of multi-label classification is time-consuming and costly in remote sensing (RS). To address this problem, publicly available thematic products are often used for annotating RS images with zero-labeling-cost. However, such an approach may result in constructing a training set with noisy multi-labels, distorting the learning process. To address this problem, we propose a… 

Figures and Tables from this paper

Multi-Label Noise Robust Collaborative Learning Method for Remote Sensing Image Classification

TLDR
A novel multi-label noise robust collaborative learning (RCML) method to alleviate the negative effects of multi- label noise during the training phase of a CNN model and makes no prior assumption about the type of noise in the training set.

References

SHOWING 1-10 OF 23 REFERENCES

Deep Residual Learning for Image Recognition

TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

A Kernel Two-Sample Test

TLDR
This work proposes a framework for analyzing and comparing distributions, which is used to construct statistical tests to determine if two samples are drawn from different distributions, and presents two distribution free tests based on large deviation bounds for the maximum mean discrepancy (MMD).

Densely Connected Convolutional Networks

TLDR
The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.

BigEarthNet-MM: A Large-Scale, Multimodal, Multilabel Benchmark Archive for Remote Sensing Image Classification and Retrieval [Software and Data Sets]

TLDR
The multi-modal BigEarthNet (BigEarthNet-MM) benchmark archive made up of 590,326 pairs of Sentinel-1 and Sentinel-2 image patches is presented to support the deep learning studies in multi- modal multi-label remote sensing image retrieval and classification.

Learning Multi-Label Aerial Image Classification Under Label Noise: A Regularization Approach Using Word Embeddings

TLDR
Results indicate that networks trained using the proposed regularization method outperform those directly learned from noisy labels and that the benefits increase proportionally to the amount of noise present.

A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise

TLDR
By tuning the softmax temperature, this work improves accuracy, log-likelihood and calibration on both image classification benchmarks with controlled label noise as well as Imagenet-21k which has naturally occurring label noise.

A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification

TLDR
This paper analyzes and compares different deep learning loss functions in the framework of multi-label remote sensing (RS) image scene classification problems and some guidelines are derived for a proper selection of a loss function in multi- label RS scene classification Problems.

A Novel Approach to the Unsupervised Extraction of Reliable Training Samples From Thematic Products

  • C. ParisL. Bruzzone
  • Computer Science, Environmental Science
    IEEE Transactions on Geoscience and Remote Sensing
  • 2021
TLDR
A novel approach that aims to extract reliable labeled data from existing thematic products by performing a domain understanding to detect the discrepancies between the thematic map domain and the RS data domain and extracts a database of informative and reliable training samples.

A Deep Multi-Attention Driven Approach for Multi-Label Remote Sensing Image Classification

TLDR
Experiments carried out on BigEarthNet show the effectiveness of the proposed approach in terms of multi-label classification accuracy compared to the state-of-the-art approaches.

Learning from Noisy Labels via Discrepant Collaborative Training

TLDR
A collaborative training framework is modified to utilize discrepancy constraints between respective feature extractors enabling the learning of distinct, yet discriminative features, pacifying the adverse effects of noise.