Leveraging Activations for Superpixel Explanations

• URL: http://arxiv.org/abs/2406.04933v1
• Date: Fri, 7 Jun 2024 13:37:45 GMT
• Title: Leveraging Activations for Superpixel Explanations
• Authors: Ahcène Boubekki, Samuel G. Fadel, Sebastian Mair,
• Abstract summary: Saliency methods have become standard in the explanation toolkit of deep neural networks. In this paper, we aim to avoid relying on segmenters by extracting a segmentation from the activations of a deep neural network image classifier. Our so-called Neuro-Activated Superpixels (NAS) can isolate the regions of interest in the input relevant to the model's prediction.
• Score: 2.8792218859042453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Saliency methods have become standard in the explanation toolkit of deep neural networks. Recent developments specific to image classifiers have investigated region-based explanations with either new methods or by adapting well-established ones using ad-hoc superpixel algorithms. In this paper, we aim to avoid relying on these segmenters by extracting a segmentation from the activations of a deep neural network image classifier without fine-tuning the network. Our so-called Neuro-Activated Superpixels (NAS) can isolate the regions of interest in the input relevant to the model's prediction, which boosts high-threshold weakly supervised object localization performance. This property enables the semi-supervised semantic evaluation of saliency methods. The aggregation of NAS with existing saliency methods eases their interpretation and reveals the inconsistencies of the widely used area under the relevance curve metric.

Related papers

• CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability [11.076431337488973]
  This study proposes a novel hybrid self-supervised depth estimation network, CCDepth, comprising convolutional neural networks (CNNs) and the white-box CRATE network. This novel network uses CNNs and the CRATE modules to extract local and global information in images, respectively, thereby boosting learning efficiency and reducing model size.
  arXiv  Detail & Related papers  (2024-09-30T04:19:40Z)
• Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks [7.956678963695681]
  We introduce a novel class of Deep Sparse Coding (DSC) models. We derive convergence rates for CNNs in their ability to extract sparse features. Inspired by the strong connection between sparse coding and CNNs, we explore training strategies to encourage neural networks to learn more sparse features.
  arXiv  Detail & Related papers  (2024-08-10T12:43:55Z)
• Chan-Vese Attention U-Net: An attention mechanism for robust segmentation [7.159201285824689]
  We propose a new attention gate based on the use of Chan-Vese energy minimization to control more precisely the segmentation masks given by a standard CNN architecture. The study of the results allows us to observe the spatial information retained by the neural network on the region of interest and obtains competitive results on the binary segmentation.
  arXiv  Detail & Related papers  (2023-06-28T11:00:57Z)
• Interpolation-based Correlation Reduction Network for Semi-Supervised Graph Learning [49.94816548023729]
  We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN) In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Inducing Gaussian Process Networks [80.40892394020797]
  We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points. The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains. We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-21T05:27:09Z)
• GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection [0.9883261192383611]
  We propose a novel Gated Context Attention Network (GCA-Net) that utilizes the non-local attention block for global context learning. We show that our method outperforms state-of-the-art networks by an average of 4.2%-5.4% AUC on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-08T14:13:14Z)
• RSI-Net: Two-Stream Deep Neural Network Integrating GCN and Atrous CNN for Semantic Segmentation of High-resolution Remote Sensing Images [3.468780866037609]
  Two-stream deep neural network for semantic segmentation of remote sensing images (RSI-Net) is proposed in this paper. Experiments are implemented on the Vaihingen, Potsdam and Gaofen RSI datasets. Results demonstrate the superior performance of RSI-Net in terms of overall accuracy, F1 score and kappa coefficient when compared with six state-of-the-art RSI semantic segmentation methods.
  arXiv  Detail & Related papers  (2021-09-19T15:57:20Z)
• MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
  Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
  arXiv  Detail & Related papers  (2021-07-23T06:57:08Z)
• Ventral-Dorsal Neural Networks: Object Detection via Selective Attention [51.79577908317031]
  We propose a new framework called Ventral-Dorsal Networks (VDNets) Inspired by the structure of the human visual system, we propose the integration of a "Ventral Network" and a "Dorsal Network" Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches.
  arXiv  Detail & Related papers  (2020-05-15T23:57:36Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)
• Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning [86.45526827323954]
  Weakly-supervised semantic segmentation is a challenging task as no pixel-wise label information is provided for training. We propose an iterative algorithm to learn such pairwise relations. We show that the proposed algorithm performs favorably against the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-02-19T10:32:03Z)

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.