Segmentation and Smoothing Affect Explanation Quality More Than the Choice of Perturbation-based XAI Method for Image Explanations

• URL: http://arxiv.org/abs/2409.04116v2
• Date: Wed, 29 Jan 2025 13:16:04 GMT
• Title: Segmentation and Smoothing Affect Explanation Quality More Than the Choice of Perturbation-based XAI Method for Image Explanations
• Authors: Gustav Grund Pihlgren, Kary Främling,
• Abstract summary: Post-hoc image explanation methods are commonly used to explain image prediction models. It remains poorly understood which parameters of the different methods are responsible for their varying performance. The results show that attribution calculation, which is frequently the focus of other works, has little impact on the results.
• Score: 1.1663475941322277
• License:
• Abstract: Perturbation-based post-hoc image explanation methods are commonly used to explain image prediction models. These methods perturb parts of the input to measure how those parts affect the output. Since the methods only require the input and output they can be applied to any model, making them a popular choice to explain black-box models. While many different models exist and have been compared with one another, it remains poorly understood which parameters of the different methods are responsible for their varying performance. This work uses the Randomized Input Sampling for Explanations (RISE) method as a baseline to evaluate many combinations of mask sampling, segmentation techniques, smoothing, attribution calculation, and per-segment or per-pixel attribution, using a proxy metric. The results show that attribution calculation, which is frequently the focus of other works, has little impact on the results. Conversely, segmentation and per-pixel attribution, rarely examined parameters, have a significant impact. The implementation of and data gathered in this work are available online: https://github.com/guspih/post-hoc-image-perturbation and https://bit.ly/smooth-mask-perturbation

Related papers

• UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation [64.01742988773745]
  An increasing privacy concern exists regarding training large-scale image segmentation models on unauthorized private data. We exploit the concept of unlearnable examples to make images unusable to model training by generating and adding unlearnable noise into the original images. We empirically verify the effectiveness of UnSeg across 6 mainstream image segmentation tasks, 10 widely used datasets, and 7 different network architectures.
  arXiv  Detail & Related papers  (2024-10-13T16:34:46Z)
• SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process [102.18226145874007]
  We propose a model-agnostic solution called SegRefiner to enhance the quality of object masks produced by different segmentation models. SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. It consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks.
  arXiv  Detail & Related papers  (2023-12-19T18:53:47Z)
• A Generalist Framework for Panoptic Segmentation of Images and Videos [61.61453194912186]
  We formulate panoptic segmentation as a discrete data generation problem, without relying on inductive bias of the task. A diffusion model is proposed to model panoptic masks, with a simple architecture and generic loss function. Our method is capable of modeling video (in a streaming setting) and thereby learns to track object instances automatically.
  arXiv  Detail & Related papers  (2022-10-12T16:18:25Z)
• Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps [85.49020931411825]
  Convolutional Neural Networks (CNNs) compression is crucial to deploying these models in edge devices with limited resources. We propose to address the channel pruning problem from a novel perspective by leveraging the interpretations of a model to steer the pruning process. We tackle this challenge by introducing a selector model that predicts real-time smooth saliency masks for pruned models.
  arXiv  Detail & Related papers  (2022-09-07T01:12:11Z)
• Estimating Appearance Models for Image Segmentation via Tensor Factorization [0.0]
  We propose a new approach to directly estimate appearance models from the image without prior information on the underlying segmentation. Our method uses local high order color statistics from the image as an input to tensor factorization-based estimator for latent variable models. This approach is able to estimate models in multiregion images and automatically output the regions proportions without prior user interaction.
  arXiv  Detail & Related papers  (2022-08-16T17:21:00Z)
• A Bhattacharyya Coefficient-Based Framework for Noise Model-Aware Random Walker Image Segmentation [3.899824115379246]
  We propose a general framework of deriving weight functions based on probabilistic modeling. This framework can be concretized to cope with virtually any well-defined noise model. We show their superior performance on synthetic data as well as different biomedical image data.
  arXiv  Detail & Related papers  (2022-06-02T09:21:52Z)
• Few-shot semantic segmentation via mask aggregation [5.886986014593717]
  Few-shot semantic segmentation aims to recognize novel classes with only very few labelled data. Previous works have typically regarded it as a pixel-wise classification problem. We introduce a mask-based classification method for addressing this problem.
  arXiv  Detail & Related papers  (2022-02-15T07:13:09Z)
• Diffusion Models for Implicit Image Segmentation Ensembles [1.444701913511243]
  We present a novel semantic segmentation method based on diffusion models. By modifying the training and sampling scheme, we show that diffusion models can perform lesion segmentation of medical images. Compared to state-of-the-art segmentation models, our approach yields good segmentation results and, additionally, meaningful uncertainty maps.
  arXiv  Detail & Related papers  (2021-12-06T16:28:15Z)
• SegDiff: Image Segmentation with Diffusion Probabilistic Models [81.16986859755038]
  Diffusion Probabilistic Methods are employed for state-of-the-art image generation. We present a method for extending such models for performing image segmentation. The method learns end-to-end, without relying on a pre-trained backbone.
  arXiv  Detail & Related papers  (2021-12-01T10:17:25Z)
• BoundarySqueeze: Image Segmentation as Boundary Squeezing [104.43159799559464]
  We propose a novel method for fine-grained high-quality image segmentation of both objects and scenes. Inspired by dilation and erosion from morphological image processing techniques, we treat the pixel level segmentation problems as squeezing object boundary. Our method yields large gains on COCO, Cityscapes, for both instance and semantic segmentation and outperforms previous state-of-the-art PointRend in both accuracy and speed under the same setting.
  arXiv  Detail & Related papers  (2021-05-25T04:58:51Z)

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.