Mitigating Bias: Enhancing Image Classification by Improving Model
Explanations
- URL: http://arxiv.org/abs/2307.01473v3
- Date: Fri, 22 Sep 2023 05:00:27 GMT
- Title: Mitigating Bias: Enhancing Image Classification by Improving Model
Explanations
- Authors: Raha Ahmadi, Mohammad Javad Rajabi, Mohammad Khalooie, Mohammad
Sabokrou
- Abstract summary: Deep learning models tend to rely heavily on simple and easily discernible features in the background of images.
We introduce a mechanism that encourages the model to allocate sufficient attention to the foreground.
Our findings highlight the importance of foreground attention in enhancing model understanding and representation of the main concepts within images.
- Score: 9.791305104409057
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Deep learning models have demonstrated remarkable capabilities in learning
complex patterns and concepts from training data. However, recent findings
indicate that these models tend to rely heavily on simple and easily
discernible features present in the background of images rather than the main
concepts or objects they are intended to classify. This phenomenon poses a
challenge to image classifiers as the crucial elements of interest in images
may be overshadowed. In this paper, we propose a novel approach to address this
issue and improve the learning of main concepts by image classifiers. Our
central idea revolves around concurrently guiding the model's attention toward
the foreground during the classification task. By emphasizing the foreground,
which encapsulates the primary objects of interest, we aim to shift the focus
of the model away from the dominant influence of the background. To accomplish
this, we introduce a mechanism that encourages the model to allocate sufficient
attention to the foreground. We investigate various strategies, including
modifying the loss function or incorporating additional architectural
components, to enable the classifier to effectively capture the primary concept
within an image. Additionally, we explore the impact of different foreground
attention mechanisms on model performance and provide insights into their
effectiveness. Through extensive experimentation on benchmark datasets, we
demonstrate the efficacy of our proposed approach in improving the
classification accuracy of image classifiers. Our findings highlight the
importance of foreground attention in enhancing model understanding and
representation of the main concepts within images. The results of this study
contribute to advancing the field of image classification and provide valuable
insights for developing more robust and accurate deep-learning models.
Related papers
- Zero-Shot Object-Centric Representation Learning [72.43369950684057]
We study current object-centric methods through the lens of zero-shot generalization.
We introduce a benchmark comprising eight different synthetic and real-world datasets.
We find that training on diverse real-world images improves transferability to unseen scenarios.
arXiv Detail & Related papers (2024-08-17T10:37:07Z) - 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) - Enhancing Generative Class Incremental Learning Performance with Model Forgetting Approach [50.36650300087987]
This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism.
We have found that integrating the forgetting mechanisms significantly enhances the models' performance in acquiring new knowledge.
arXiv Detail & Related papers (2024-03-27T05:10:38Z) - Foveation in the Era of Deep Learning [6.602118206533142]
We introduce an end-to-end differentiable foveated active vision architecture that leverages a graph convolutional network to process foveated images.
Our model learns to iteratively attend to regions of the image relevant for classification.
We find that our model outperforms a state-of-the-art CNN and foveated vision architectures of comparable parameters and a given pixel or budget.
arXiv Detail & Related papers (2023-12-03T16:48:09Z) - Food Image Classification and Segmentation with Attention-based Multiple
Instance Learning [51.279800092581844]
The paper presents a weakly supervised methodology for training food image classification and semantic segmentation models.
The proposed methodology is based on a multiple instance learning approach in combination with an attention-based mechanism.
We conduct experiments on two meta-classes within the FoodSeg103 data set to verify the feasibility of the proposed approach.
arXiv Detail & Related papers (2023-08-22T13:59:47Z) - Understanding Self-Supervised Pretraining with Part-Aware Representation
Learning [88.45460880824376]
We study the capability that self-supervised representation pretraining methods learn part-aware representations.
Results show that the fully-supervised model outperforms self-supervised models for object-level recognition.
arXiv Detail & Related papers (2023-01-27T18:58:42Z) - Benchmarking the Robustness of Instance Segmentation Models [3.1287804585804073]
This paper presents a comprehensive evaluation of instance segmentation models with respect to real-world image corruptions and out-of-domain image collections.
The out-of-domain image evaluation shows the generalization capability of models, an essential aspect of real-world applications.
Specifically, this benchmark study includes state-of-the-art network architectures, network backbones, normalization layers, models trained starting from scratch or ImageNet pretrained networks.
arXiv Detail & Related papers (2021-09-02T17:50:07Z) - Playing to distraction: towards a robust training of CNN classifiers
through visual explanation techniques [1.2321022105220707]
We present a novel and robust training scheme that integrates visual explanation techniques in the learning process.
In particular, we work on the challenging EgoFoodPlaces dataset, achieving state-of-the-art results with a lower level of complexity.
arXiv Detail & Related papers (2020-12-28T10:24:32Z) - Saliency-driven Class Impressions for Feature Visualization of Deep
Neural Networks [55.11806035788036]
It is advantageous to visualize the features considered to be essential for classification.
Existing visualization methods develop high confidence images consisting of both background and foreground features.
In this work, we propose a saliency-driven approach to visualize discriminative features that are considered most important for a given task.
arXiv Detail & Related papers (2020-07-31T06:11:06Z)
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.