mlsanityData to 7 Oct 2026

On Classification of Distorted Images with Deep Convolutional Neural Networks

arXiv 1701.01924 ↗First posted 8 Jan 2017cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Image blur and image noise are common distortions during image acquisition. In this paper, we systematically study the effect of image distortions on the deep neural network (DNN) image classifiers. First, we examine the DNN classifier performance under four types of distortions. Second, we propose two approaches to alleviate the effect of image distortion: re-training and fine-tuning with noisy images. Our results suggest that, under certain conditions, fine-tuning with noisy images can alleviate much effect due to distorted inputs, and is more practical than re-training.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 7; 2023: 9; 2024: 4; 2025: 0; 2026: 1.

26 papers.

Sort:

By area:

  1. 2021Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Functioncited by 11
  2. 2021Early-exit deep neural networks for distorted images: providing an efficient edge offloadingcited by 8
  3. 2021Inverse Problems Leveraging Pre-trained Contrastive Representationscited by 7
  4. 2023On the Robustness of Object Detection Models on Aerial Imagescited by 7
  5. 2021AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systemscited by 6
  6. 2023Confidence-based Reliable Learning under Dual Noisescited by 6
  7. 2022Certifying Model Accuracy under Distribution Shiftscited by 5
  8. 2022A New Approach to Improve Learning-based Deepfake Detection in Realistic Conditionscited by 3
  9. 2023Enhancing object detection robustness: A synthetic and natural perturbation approachcited by 3
  10. 2023Picking Up Quantization Steps for Compressed Image Classificationcited by 2
  11. 2024Collaboratively Learning Federated Models from Noisy Decentralized Datacited by 2
  12. 2022Perspective Transformation Layercited by 1
14 more
  1. 2023What's color got to do with it? Face recognition in grayscalecited by 1
  2. 2024Impacts of Color and Texture Distortions on Earth Observation Data in Deep Learningcited by 1
  3. 2024Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustnesscited by 1
  4. 2021Fast and Robust Structural Damage Analysis of Civil Infrastructure Using UAV Imagerycited by 0
  5. 2022A Novel Framework for Assessment of Learning-based Detectors in Realistic Conditions with Application to Deepfake Detectioncited by 0
  6. 2022On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networkscited by 0
  7. 2022Impact of Scaled Image on Robustness of Deep Neural Networkscited by 0
  8. 2022Impact of Colour Variation on Robustness of Deep Neural Networkscited by 0
  9. 2023Blur Invariants for Image Recognitioncited by 0
  10. 2023Noise robust neural network architecturecited by 0
  11. 2023Impact of Light and Shadow on Robustness of Deep Neural Networkscited by 0
  12. 2023Pruning Distorted Images in MNIST Handwritten Digitscited by 0
  13. 2024Predicting the Reliability of an Image Classifier under Image Distortioncited by 0
  14. 2026The RealDefocus Benchmark for Defocus Deblurringcited by 0