Uncertainty-Aware Decomposed Hybrid Networks

• URL: http://arxiv.org/abs/2503.19096v1
• Date: Mon, 24 Mar 2025 19:30:17 GMT
• Title: Uncertainty-Aware Decomposed Hybrid Networks
• Authors: Sina Ditzel, Achref Jaziri, Iuliia Pliushch, Visvanathan Ramesh,
• Abstract summary: We propose a hybrid approach that combines the adaptability of neural networks with the interpretability, transparency, and robustness of domain-specific operators.<n>Our method decomposes the recognition into multiple task-specific operators that focus on different characteristics, supported by a novel confidence measurement.
• Score: 5.67478985222587
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks with the interpretability, transparency, and robustness of domain-specific quasi-invariant operators. Our method decomposes the recognition into multiple task-specific operators that focus on different characteristics, supported by a novel confidence measurement tailored to these operators. This measurement enables the network to prioritize reliable features and accounts for noise. We argue that our design enhances transparency and robustness, leading to improved performance, particularly in low-data regimes. Experimental results in traffic sign detection highlight the effectiveness of the proposed method, especially in semi-supervised and unsupervised scenarios, underscoring its potential for data-constrained applications.

Related papers

• Network Inversion and Its Applications [9.124933643129538]
  Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes"<n>Network inversion techniques offer a solution by allowing us to peek inside these black boxes, revealing the features and patterns learned by the networks behind their decision-making processes.<n>This paper presents a simple yet effective approach to network inversion using a meticulously conditioned generator that learns the data distribution in the input space of the trained neural network.
  arXiv  Detail & Related papers  (2024-11-26T10:04:52Z)
• Adaptive Pruning with Module Robustness Sensitivity: Balancing Compression and Robustness [7.742297876120561]
  This paper introduces Module Robustness Sensitivity (MRS), a novel metric that quantifies layer-wise sensitivity to adversarial perturbations.<n>We propose Module Robust Pruning and Fine-Tuning (MRPF), an adaptive pruning algorithm compatible with any adversarial training method.
  arXiv  Detail & Related papers  (2024-10-19T18:35:52Z)
• Generative Edge Detection with Stable Diffusion [52.870631376660924]
  Edge detection is typically viewed as a pixel-level classification problem mainly addressed by discriminative methods. We propose a novel approach, named Generative Edge Detector (GED), by fully utilizing the potential of the pre-trained stable diffusion model. We conduct extensive experiments on multiple datasets and achieve competitive performance.
  arXiv  Detail & Related papers  (2024-10-04T01:52:23Z)
• Forward-Forward Learning achieves Highly Selective Latent Representations for Out-of-Distribution Detection in Fully Spiking Neural Networks [6.7236795813629]
  Spiking Neural Networks (SNNs), inspired by biological systems, offer a promising avenue for overcoming limitations. In this work, we explore the potential of the spiking Forward-Forward Algorithm (FFA) to address these challenges. We propose a novel, gradient-free attribution method to detect features that drive a sample away from class distributions.
  arXiv  Detail & Related papers  (2024-07-19T08:08:17Z)
• TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data [50.797729676285876]
  We propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm.
  arXiv  Detail & Related papers  (2024-02-16T16:41:14Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• Variational Voxel Pseudo Image Tracking [127.46919555100543]
  Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving. We propose a Variational Neural Network-based version of a Voxel Pseudo Image Tracking (VPIT) method for 3D Single Object Tracking.
  arXiv  Detail & Related papers  (2023-02-12T13:34:50Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• Bayesian Attention Belief Networks [59.183311769616466]
  Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights. We show that our method outperforms deterministic attention and state-of-the-art attention in accuracy, uncertainty estimation, generalization across domains, and adversarial attacks.
  arXiv  Detail & Related papers  (2021-06-09T17:46:22Z)
• Uncertainty Surrogates for Deep Learning [17.868995105624023]
  We introduce a novel way of estimating prediction uncertainty in deep networks through the use of uncertainty surrogates. These surrogates are features of the penultimate layer of a deep network that are forced to match predefined patterns. We show how our approach can be used for estimating uncertainty in prediction and out-of-distribution detection.
  arXiv  Detail & Related papers  (2021-04-16T14:50:28Z)
• Supervised Feature Selection Techniques in Network Intrusion Detection: a Critical Review [9.177695323629896]
  Machine Learning techniques are becoming an invaluable support for network intrusion detection. Dealing with the vast diversity and number of features that typically characterize data traffic is a hard problem. By reducing the feature space and retaining only the most significant features, Feature Selection (FS) becomes a crucial pre-processing step in network management.
  arXiv  Detail & Related papers  (2021-04-11T08:42:01Z)
• 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.