Identifying bias in CNN image classification using image scrambling and transforms

• URL: http://arxiv.org/abs/2510.10383v1
• Date: Sun, 12 Oct 2025 00:43:29 GMT
• Title: Identifying bias in CNN image classification using image scrambling and transforms
• Authors: Sai Teja Erukude,
• Abstract summary: CNNs are prevalent as the primary choice for most machine vision problems due to their superior rate of classification and the availability of user-friendly libraries.<n>Here we discuss examples of such hidden biases and propose techniques for identifying them.<n>We also explore whether CNNs learn from irrelevant features.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: CNNs are now prevalent as the primary choice for most machine vision problems due to their superior rate of classification and the availability of user-friendly libraries. These networks effortlessly identify and select features in a non-intuitive data-driven manner, making it difficult to determine which features were most influential. That leads to a ``black box", where users cannot know how the image data are analyzed but rely on empirical results. Therefore the decision-making process can be biased by background information that is difficult to detect. Here we discuss examples of such hidden biases and propose techniques for identifying them, methods to distinguish between contextual information and background noise, and explore whether CNNs learn from irrelevant features. One effective approach to identify dataset bias is to classify blank background parts of the images. However, in some situations a blank background in the images is not available, making it more difficult to separate the foreground information from the blank background. Such parts of the image can also be considered contextual learning, not necessarily bias. To overcome this, we propose two approaches that were tested on six different datasets, including natural, synthetic, and hybrid datasets. The first method involves dividing images into smaller, non-overlapping tiles of various sizes, which are then shuffled randomly, making classification more challenging. The second method involves the application of several image transforms, including Fourier, Wavelet transforms, and Median filter, and their combinations. These transforms help recover background noise information used by CNN to classify images. Results indicate that this method can effectively distinguish between contextual information and background noise, and alert on the presence of background noise even without the need to use background information.

Related papers

• Identifying Bias in Deep Neural Networks Using Image Transforms [0.0]
  CNNs have become one of the most commonly used computational tools in the past two decades.<n>One of the primary downsides of CNNs is that they work as a black box', where the user cannot necessarily know how the image data are analyzed.<n>This can lead to hidden biases that affect the performance evaluation of neural networks, but are difficult to identify.
  arXiv  Detail & Related papers  (2024-12-17T16:51:44Z)
• Targeted Background Removal Creates Interpretable Feature Visualizations [0.0]
  We argue that by using background removal techniques as a form of robust training, a network is forced to learn more human recognizable features. Four different training methods were used to verify this hypothesis. The feature visualization results show that the background removed images reveal a significant improvement over the baseline model.
  arXiv  Detail & Related papers  (2023-06-22T19:39:06Z)
• Invariant Learning via Diffusion Dreamed Distribution Shifts [121.71383835729848]
  We propose a dataset called Diffusion Dreamed Distribution Shifts (D3S) D3S consists of synthetic images generated through StableDiffusion using text prompts and image guides obtained by pasting a sample foreground image onto a background template image. Due to the incredible photorealism of the diffusion model, our images are much closer to natural images than previous synthetic datasets.
  arXiv  Detail & Related papers  (2022-11-18T17:07:43Z)
• Decoupled Mixup for Generalized Visual Recognition [71.13734761715472]
  We propose a novel "Decoupled-Mixup" method to train CNN models for visual recognition. Our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions to train CNN models. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts.
  arXiv  Detail & Related papers  (2022-10-26T15:21:39Z)
• On Background Bias in Deep Metric Learning [5.368313160283353]
  We analyze the influence of the image background on Deep Metric Learning models. We show that replacing the background of images during training with random background images alleviates this issue.
  arXiv  Detail & Related papers  (2022-10-04T13:57:39Z)
• Comparative Analysis of Non-Blind Deblurring Methods for Noisy Blurred Images [0.0]
  Wiener deconvolution, Lucy-Richardson deconvolution, and regularized deconvolution were analyzed for noisy images featuring salt-and-pepper noise. Results were compared to determine the best approach for deblurring noisy images.
  arXiv  Detail & Related papers  (2022-05-06T20:07:29Z)
• Learning to See by Looking at Noise [87.12788334473295]
  We investigate a suite of image generation models that produce images from simple random processes. These are then used as training data for a visual representation learner with a contrastive loss. Our findings show that it is important for the noise to capture certain structural properties of real data but that good performance can be achieved even with processes that are far from realistic.
  arXiv  Detail & Related papers  (2021-06-10T17:56:46Z)
• Deep Universal Blind Image Denoising [26.77629755630694]
  Deep convolutional neural networks (CNNs) have shown great success in image denoising by incorporating large-scale synthetic datasets. We present a CNN-based method that leverages the advantages of both methods based on the Bayesian perspective.
  arXiv  Detail & Related papers  (2021-01-18T11:49:21Z)
• Attention-Aware Noisy Label Learning for Image Classification [97.26664962498887]
  Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision. The cheapest way to obtain a large body of labeled visual data is to crawl from websites with user-supplied labels, such as Flickr. This paper proposes the attention-aware noisy label learning approach to improve the discriminative capability of the network trained on datasets with potential label noise.
  arXiv  Detail & Related papers  (2020-09-30T15:45:36Z)
• Data-driven Meta-set Based Fine-Grained Visual Classification [61.083706396575295]
  We propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition. Specifically, guided by a small amount of clean meta-set, we train a selection net in a meta-learning manner to distinguish in- and out-of-distribution noisy images.
  arXiv  Detail & Related papers  (2020-08-06T03:04:16Z)
• Distilling Localization for Self-Supervised Representation Learning [82.79808902674282]
  Contrastive learning has revolutionized unsupervised representation learning. Current contrastive models are ineffective at localizing the foreground object. We propose a data-driven approach for learning in variance to backgrounds.
  arXiv  Detail & Related papers  (2020-04-14T16:29:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.