Sanity checks and improvements for patch visualisation in prototype-based image classification

• URL: http://arxiv.org/abs/2302.08508v2
• Date: Mon, 15 May 2023 09:09:19 GMT
• Title: Sanity checks and improvements for patch visualisation in prototype-based image classification
• Authors: Romain Xu-Darme (LSL, MRIM), Georges Qu\'enot (MRIM), Zakaria Chihani (LSL), Marie-Christine Rousset (SLIDE)
• Abstract summary: We perform an in-depth analysis of the visualisation methods implemented in two popular self-explaining models for visual classification based on prototypes. We first show that such methods do not correctly identify the regions of interest inside of the images, and therefore do not reflect the model behaviour. We discuss the implications of our findings for other prototype-based models sharing the same visualisation method.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we perform an in-depth analysis of the visualisation methods implemented in two popular self-explaining models for visual classification based on prototypes - ProtoPNet and ProtoTree. Using two fine-grained datasets (CUB-200-2011 and Stanford Cars), we first show that such methods do not correctly identify the regions of interest inside of the images, and therefore do not reflect the model behaviour. Secondly, using a deletion metric, we demonstrate quantitatively that saliency methods such as Smoothgrads or PRP provide more faithful image patches. We also propose a new relevance metric based on the segmentation of the object provided in some datasets (e.g. CUB-200-2011) and show that the imprecise patch visualisations generated by ProtoPNet and ProtoTree can create a false sense of bias that can be mitigated by the use of more faithful methods. Finally, we discuss the implications of our findings for other prototype-based models sharing the same visualisation method.

Related papers

• Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images [12.365801596593936]
  Medical image segmentation is one of the domains where sufficient annotated data is not available. We propose a prototype-based self-supervised one-way one-shot learning framework using pseudo-labels generated from superpixels. We show that the proposed simple but potent framework performs at par with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-12T15:38:51Z)
• Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery [17.156864650143678]
  We develop a few-shot object detector based on a traditional two-stage architecture. A large-scale pre-trained model is used to build class-reference embeddings or prototypes. We perform evaluations on two remote sensing datasets containing challenging and rare objects.
  arXiv  Detail & Related papers  (2024-03-08T15:20:27Z)
• Sanity checks for patch visualisation in prototype-based image classification [0.0]
  We show that the visualisation methods implemented in ProtoPNet and ProtoTree do not correctly identify the regions of interest inside of the images. We also demonstrate quantitatively that this issue can be mitigated by using other saliency methods that provide more faithful image patches.
  arXiv  Detail & Related papers  (2023-10-25T08:13:02Z)
• COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification [21.3855970055692]
  We present a set of metrics that utilize vision priors to assess the performance of saliency methods on image classification tasks. We show that although saliency methods are thought to be architecture-independent, most methods could better explain transformer-based models over convolutional-based models.
  arXiv  Detail & Related papers  (2023-09-20T01:06:44Z)
• PDiscoNet: Semantically consistent part discovery for fine-grained recognition [62.12602920807109]
  We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods.
  arXiv  Detail & Related papers  (2023-09-06T17:19:29Z)
• DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulation [83.51882381294357]
  DisPositioNet is a model that learns a disentangled representation for each object for the task of image manipulation using scene graphs. Our framework enables the disentanglement of the variational latent embeddings as well as the feature representation in the graph.
  arXiv  Detail & Related papers  (2022-11-10T11:47:37Z)
• Rethinking Semantic Segmentation: A Prototype View [126.59244185849838]
  We present a nonparametric semantic segmentation model based on non-learnable prototypes. Our framework yields compelling results over several datasets. We expect this work will provoke a rethink of the current de facto semantic segmentation model design.
  arXiv  Detail & Related papers  (2022-03-28T21:15:32Z)
• Attentional Prototype Inference for Few-Shot Segmentation [128.45753577331422]
  We propose attentional prototype inference (API), a probabilistic latent variable framework for few-shot segmentation. We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution. We conduct extensive experiments on four benchmarks, where our proposal obtains at least competitive and often better performance than state-of-the-art prototype-based methods.
  arXiv  Detail & Related papers  (2021-05-14T06:58:44Z)
• ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery [9.36640530008137]
  We introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions. The main novelty of the ProtoPShare is its ability to efficiently share prototypical parts between the classes thanks to our data-dependent merge-pruning. We verify our findings on two datasets, the CUB-200-2011 and the Stanford Cars.
  arXiv  Detail & Related papers  (2020-11-29T11:23:05Z)
• Synthesizing the Unseen for Zero-shot Object Detection [72.38031440014463]
  We propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain. We use a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them.
  arXiv  Detail & Related papers  (2020-10-19T12:36:11Z)
• Part-aware Prototype Network for Few-shot Semantic Segmentation [50.581647306020095]
  We propose a novel few-shot semantic segmentation framework based on the prototype representation. Our key idea is to decompose the holistic class representation into a set of part-aware prototypes. We develop a novel graph neural network model to generate and enhance the proposed part-aware prototypes.
  arXiv  Detail & Related papers  (2020-07-13T11:03:09Z)

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.