Exploring Resiliency to Natural Image Corruptions in Deep Learning using Design Diversity

• URL: http://arxiv.org/abs/2303.09283v1
• Date: Wed, 15 Mar 2023 08:54:10 GMT
• Title: Exploring Resiliency to Natural Image Corruptions in Deep Learning using Design Diversity
• Authors: Rafael Rosales, Pablo Munoz, Michael Paulitsch
• Abstract summary: We investigate the relationship between diversity metrics, accuracy, and resiliency to natural image corruptions of Deep Learning (DL) image ensembles. Our motivation is based on analytical studies of design diversity that have shown that a reduction of common failure modes is possible if diversity of design choices is achieved.
• Score: 0.6445605125467573
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we investigate the relationship between diversity metrics, accuracy, and resiliency to natural image corruptions of Deep Learning (DL) image classifier ensembles. We investigate the potential of an attribution-based diversity metric to improve the known accuracy-diversity trade-off of the typical prediction-based diversity. Our motivation is based on analytical studies of design diversity that have shown that a reduction of common failure modes is possible if diversity of design choices is achieved. Using ResNet50 as a comparison baseline, we evaluate the resiliency of multiple individual DL model architectures against dataset distribution shifts corresponding to natural image corruptions. We compare ensembles created with diverse model architectures trained either independently or through a Neural Architecture Search technique and evaluate the correlation of prediction-based and attribution-based diversity to the final ensemble accuracy. We evaluate a set of diversity enforcement heuristics based on negative correlation learning to assess the final ensemble resilience to natural image corruptions and inspect the resulting prediction, activation, and attribution diversity. Our key observations are: 1) model architecture is more important for resiliency than model size or model accuracy, 2) attribution-based diversity is less negatively correlated to the ensemble accuracy than prediction-based diversity, 3) a balanced loss function of individual and ensemble accuracy creates more resilient ensembles for image natural corruptions, 4) architecture diversity produces more diversity in all explored diversity metrics: predictions, attributions, and activations.

Related papers

• Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization [33.5861323022684]
  This paper introduces a flexible synthetic testbed that combines a statistical stream of generic tokens with an abstract factual stream of source-target token pairs.<n>We find that while higher contextual diversity delays in-distribution (ID) factual accuracy, its impact on out-of-distribution (OOD) factual generalization depends critically on contextual structure.
  arXiv  Detail & Related papers  (2025-10-17T17:58:01Z)
• A Robust Adversarial Ensemble with Causal (Feature Interaction) Interpretations for Image Classification [9.945272787814941]
  We present a deep ensemble model that combines discriminative features with generative models to achieve both high accuracy and adversarial robustness. Our approach integrates a bottom-level pre-trained discriminative network for feature extraction with a top-level generative classification network that models adversarial input distributions.
  arXiv  Detail & Related papers  (2024-12-28T05:06:20Z)
• Dynamic Post-Hoc Neural Ensemblers [55.15643209328513]
  In this study, we explore employing neural networks as ensemble methods. Motivated by the risk of learning low-diversity ensembles, we propose regularizing the model by randomly dropping base model predictions. We demonstrate this approach lower bounds the diversity within the ensemble, reducing overfitting and improving generalization capabilities.
  arXiv  Detail & Related papers  (2024-10-06T15:25:39Z)
• Unsupervised Feature Orthogonalization for Learning Distortion-Invariant Representations [0.13108652488669734]
  This study introduces unORANIC+, a novel method that integrates unsupervised feature orthogonalization with the ability of a Vision Transformer. The streamlined architecture of unORANIC+ effectively separates anatomical and image-specific attributes, resulting in robust and unbiased latent representations. Extensive experimentation demonstrates unORANIC+'s reconstruction proficiency, corruption resilience, as well as capability to revise existing image distortions. We confirm its adaptability to diverse datasets of varying image sources and sample sizes which positions the method as a promising algorithm for advanced medical image analysis.
  arXiv  Detail & Related papers  (2024-09-18T19:25:38Z)
• A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking [54.89987482509155]
  robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts. We establish a comprehensive benchmark robustness called textbfARES-Bench on the image classification task. By designing the training settings accordingly, we achieve the new state-of-the-art adversarial robustness.
  arXiv  Detail & Related papers  (2023-02-28T04:26:20Z)
• Interpretable Diversity Analysis: Visualizing Feature Representations In Low-Cost Ensembles [0.0]
  This paper introduces several interpretability methods that can be used to qualitatively analyze diversity. We demonstrate these techniques by comparing the diversity of feature representations between child networks using two low-cost ensemble algorithms.
  arXiv  Detail & Related papers  (2023-02-12T00:32:03Z)
• Trusted Multi-View Classification with Dynamic Evidential Fusion [73.35990456162745]
  We propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC) TMC provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.
  arXiv  Detail & Related papers  (2022-04-25T03:48:49Z)
• Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions [91.63716984911278]
  We introduce a novel Mixture of Normal-Inverse Gamma distributions (MoNIG) algorithm, which efficiently estimates uncertainty in principle for adaptive integration of different modalities and produces a trustworthy regression result. Experimental results on both synthetic and different real-world data demonstrate the effectiveness and trustworthiness of our method on various multimodal regression tasks.
  arXiv  Detail & Related papers  (2021-11-11T14:28:12Z)
• Diversity and Generalization in Neural Network Ensembles [0.0]
  We combine and expand previously published results in a theoretically sound framework that describes the relationship between diversity and ensemble performance. We provide sound answers to the following questions: how to measure diversity, how diversity relates to the generalization error of an ensemble, and how diversity is promoted by neural network ensemble algorithms.
  arXiv  Detail & Related papers  (2021-10-26T15:41:10Z)
• Neural Network Ensembles: Theory, Training, and the Importance of Explicit Diversity [6.495473856599276]
  Ensemble learning is a process by which multiple base learners are strategically generated and combined into one composite learner. The right balance of learner accuracy and ensemble diversity can improve the performance of machine learning tasks on benchmark and real-world data sets. Recent theoretical and practical work has demonstrated the subtle trade-off between accuracy and diversity in an ensemble.
  arXiv  Detail & Related papers  (2021-09-29T00:43:57Z)
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift [67.57720300323928]
  Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. We propose two methods for automatically constructing ensembles with emphvarying architectures. We show that the resulting ensembles outperform deep ensembles not only in terms of accuracy but also uncertainty calibration and robustness to dataset shift.
  arXiv  Detail & Related papers  (2020-06-15T17:38:15Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)

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.