Interpret the Predictions of Deep Networks via Re-Label Distillation

• URL: http://arxiv.org/abs/2409.13137v1
• Date: Fri, 20 Sep 2024 00:46:22 GMT
• Title: Interpret the Predictions of Deep Networks via Re-Label Distillation
• Authors: Yingying Hua, Shiming Ge, Daichi Zhang,
• Abstract summary: In this work, we propose a re-label distillation approach to learn a direct map from the input to the prediction in a self-supervision manner. The synthetic images can be annotated into one of two classes by identifying whether their labels shift. In this manner, these re-labeled synthetic images can well describe the local classification mechanism of the deep network.
• Score: 22.2326257454041
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interpreting the predictions of a black-box deep network can facilitate the reliability of its deployment. In this work, we propose a re-label distillation approach to learn a direct map from the input to the prediction in a self-supervision manner. The image is projected into a VAE subspace to generate some synthetic images by randomly perturbing its latent vector. Then, these synthetic images can be annotated into one of two classes by identifying whether their labels shift. After that, using the labels annotated by the deep network as teacher, a linear student model is trained to approximate the annotations by mapping these synthetic images to the classes. In this manner, these re-labeled synthetic images can well describe the local classification mechanism of the deep network, and the learned student can provide a more intuitive explanation towards the predictions. Extensive experiments verify the effectiveness of our approach qualitatively and quantitatively.

Related papers

• Extracting Semantic Knowledge from GANs with Unsupervised Learning [65.32631025780631]
  Generative Adversarial Networks (GANs) encode semantics in feature maps in a linearly separable form. We propose a novel clustering algorithm, named KLiSH, which leverages the linear separability to cluster GAN's features. KLiSH succeeds in extracting fine-grained semantics of GANs trained on datasets of various objects.
  arXiv  Detail & Related papers  (2022-11-30T03:18:16Z)
• LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity [49.84167231111667]
  Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image. We introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion. We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations.
  arXiv  Detail & Related papers  (2022-04-06T17:48:18Z)
• Adversarially robust segmentation models learn perceptually-aligned gradients [0.0]
  We show that adversarially-trained semantic segmentation networks can be used to perform image inpainting and generation. We argue that perceptually-aligned gradients promote a better understanding of a neural network's learned representations and aid in making neural networks more interpretable.
  arXiv  Detail & Related papers  (2022-04-03T16:04:52Z)
• From Heatmaps to Structural Explanations of Image Classifiers [31.44267537307587]
  The paper starts with describing the explainable neural network (XNN), which attempts to extract and visualize several high-level concepts purely from the deep network. Realizing that an important missing piece is a reliable heatmap visualization tool, we have developed I-GOS and iGOS++. Through the research process, we have learned much about insights in building deep network explanations.
  arXiv  Detail & Related papers  (2021-09-13T23:39:57Z)
• HistoTransfer: Understanding Transfer Learning for Histopathology [9.231495418218813]
  We compare the performance of features extracted from networks trained on ImageNet and histopathology data. We investigate if features learned using more complex networks lead to gain in performance.
  arXiv  Detail & Related papers  (2021-06-13T18:55:23Z)
• Knowledge Distillation By Sparse Representation Matching [107.87219371697063]
  We propose Sparse Representation Matching (SRM) to transfer intermediate knowledge from one Convolutional Network (CNN) to another by utilizing sparse representation. We formulate as a neural processing block, which can be efficiently optimized using gradient descent and integrated into any CNN in a plug-and-play manner. Our experiments demonstrate that is robust to architectural differences between the teacher and student networks, and outperforms other KD techniques across several datasets.
  arXiv  Detail & Related papers  (2021-03-31T11:47:47Z)
• An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation [80.02124918255059]
  Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. We learn two networks to mutually teach each other. The more reliable predictions on easy images in each network are used to teach the other network to learn about the corresponding hard images.
  arXiv  Detail & Related papers  (2020-11-25T03:29:52Z)
• Graph Neural Networks for UnsupervisedDomain Adaptation of Histopathological ImageAnalytics [22.04114134677181]
  We present a novel method for the unsupervised domain adaptation for histological image analysis. It is based on a backbone for embedding images into a feature space, and a graph neural layer for propa-gating the supervision signals of images with labels. In experiments, our methodachieves state-of-the-art performance on four public datasets.
  arXiv  Detail & Related papers  (2020-08-21T04:53:44Z)
• Usefulness of interpretability methods to explain deep learning based plant stress phenotyping [8.786924604224101]
  We train a DenseNet-121 network for the classification of eight different soybean stresses (biotic and abiotic) For a diverse subset of the test data, we compared the important features with those identified by a human expert. Most interpretability methods identify the infected regions of the leaf as important features for some -- but not all -- of the correctly classified images.
  arXiv  Detail & Related papers  (2020-07-11T09:28:50Z)
• Learning Representations by Predicting Bags of Visual Words [55.332200948110895]
  Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions.
  arXiv  Detail & Related papers  (2020-02-27T16:45:25Z)
• 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.