Data Generation using Texture Co-occurrence and Spatial Self-Similarity for Debiasing

• URL: http://arxiv.org/abs/2110.07920v1
• Date: Fri, 15 Oct 2021 08:04:59 GMT
• Title: Data Generation using Texture Co-occurrence and Spatial Self-Similarity for Debiasing
• Authors: Myeongkyun Kang, Dongkyu Won, Miguel Luna, Kyung Soo Hong, June Hong Ahn, Sang Hyun Park
• Abstract summary: We propose a novel de-biasing approach that explicitly generates additional images using texture representations of oppositely labeled images. Every new generated image contains similar spatial information from a source image while transferring textures from a target image of opposite label. Our model integrates a texture co-occurrence loss that determines whether a generated image's texture is similar to that of the target, and a spatial self-similarity loss that determines whether the spatial details between the generated and source images are well preserved.
• Score: 6.976822832216875
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Classification models trained on biased datasets usually perform poorly on out-of-distribution samples since biased representations are embedded into the model. Recently, adversarial learning methods have been proposed to disentangle biased representations, but it is challenging to discard only the biased features without altering other relevant information. In this paper, we propose a novel de-biasing approach that explicitly generates additional images using texture representations of oppositely labeled images to enlarge the training dataset and mitigate the effect of biases when training a classifier. Every new generated image contains similar spatial information from a source image while transferring textures from a target image of opposite label. Our model integrates a texture co-occurrence loss that determines whether a generated image's texture is similar to that of the target, and a spatial self-similarity loss that determines whether the spatial details between the generated and source images are well preserved. Both generated and original training images are further used to train a classifier that is able to avoid learning unknown bias representations. We employ three distinct artificially designed datasets with known biases to demonstrate the ability of our method to mitigate bias information, and report competitive performance over existing state-of-the-art methods.

Related papers

• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• Data Attribution for Text-to-Image Models by Unlearning Synthesized Images [71.23012718682634]
  The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. We propose a new approach that efficiently identifies highly-influential images.
  arXiv  Detail & Related papers  (2024-06-13T17:59:44Z)
• Mitigating Bias Using Model-Agnostic Data Attribution [2.9868610316099335]
  Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. We propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of images containing bias attributes.
  arXiv  Detail & Related papers  (2024-05-08T13:00:56Z)
• Active Generation for Image Classification [50.18107721267218]
  We propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model. With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation.
  arXiv  Detail & Related papers  (2024-03-11T08:45:31Z)
• Common-Sense Bias Discovery and Mitigation for Classification Tasks [16.8259488742528]
  We propose a framework to extract feature clusters in a dataset based on image descriptions. The analyzed features and correlations are human-interpretable, so we name the method Common-Sense Bias Discovery (CSBD) Experiments show that our method discovers novel biases on multiple classification tasks for two benchmark image datasets.
  arXiv  Detail & Related papers  (2024-01-24T03:56:07Z)
• Discriminative Class Tokens for Text-to-Image Diffusion Models [107.98436819341592]
  We propose a non-invasive fine-tuning technique that capitalizes on the expressive potential of free-form text. Our method is fast compared to prior fine-tuning methods and does not require a collection of in-class images. We evaluate our method extensively, showing that the generated images are: (i) more accurate and of higher quality than standard diffusion models, (ii) can be used to augment training data in a low-resource setting, and (iii) reveal information about the data used to train the guiding classifier.
  arXiv  Detail & Related papers  (2023-03-30T05:25:20Z)
• Person Image Synthesis via Denoising Diffusion Model [116.34633988927429]
  We show how denoising diffusion models can be applied for high-fidelity person image synthesis. Our results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios.
  arXiv  Detail & Related papers  (2022-11-22T18:59:50Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• Does enhanced shape bias improve neural network robustness to common corruptions? [14.607217936005817]
  Recent work indicates that CNNs trained on ImageNet are biased towards features that encode textures. It has been shown that augmenting the training data with different image styles decreases this texture bias in favor of increased shape bias. We perform a systematic study of different ways of composing inputs based on natural images, explicit edge information, and stylization.
  arXiv  Detail & Related papers  (2021-04-20T07:06:53Z)
• Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation [34.45302976822067]
  Semi-supervised learning (SSL) based on generative methods has been proven to be effective in utilizing diverse image characteristics. We propose a new data guided generative method for histopathology image segmentation by leveraging the unlabeled data distributions. Our method is evaluated on glands and nuclei datasets.
  arXiv  Detail & Related papers  (2020-12-17T02:54:19Z)
• Texture image classification based on a pseudo-parabolic diffusion model [0.0]
  The proposed approach is tested on the classification of well established benchmark texture databases and on a practical task of plant species recognition. The good performance can be justified to a large extent by the ability of the pseudo-parabolic operator to smooth possibly noisy details inside homogeneous regions of the image.
  arXiv  Detail & Related papers  (2020-11-14T00:04:07Z)

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.