Detecting Anomalies in Semantic Segmentation with Prototypes

• URL: http://arxiv.org/abs/2106.00472v1
• Date: Tue, 1 Jun 2021 13:22:33 GMT
• Title: Detecting Anomalies in Semantic Segmentation with Prototypes
• Authors: Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Barbara Caputo
• Abstract summary: We propose to address anomaly segmentation through prototype learning. Our approach achieves the new state of the art, with a significant margin over previous works.
• Score: 23.999211737485812
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional semantic segmentation methods can recognize at test time only the classes that are present in the training set. This is a significant limitation, especially for semantic segmentation algorithms mounted on intelligent autonomous systems, deployed in realistic settings. Regardless of how many classes the system has seen at training time, it is inevitable that unexpected, unknown objects will appear at test time. The failure in identifying such anomalies may lead to incorrect, even dangerous behaviors of the autonomous agent equipped with such segmentation model when deployed in the real world. Current state of the art of anomaly segmentation uses generative models, exploiting their incapability to reconstruct patterns unseen during training. However, training these models is expensive, and their generated artifacts may create false anomalies. In this paper we take a different route and we propose to address anomaly segmentation through prototype learning. Our intuition is that anomalous pixels are those that are dissimilar to all class prototypes known by the model. We extract class prototypes from the training data in a lightweight manner using a cosine similarity-based classifier. Experiments on StreetHazards show that our approach achieves the new state of the art, with a significant margin over previous works, despite the reduced computational overhead. Code is available at https://github.com/DarioFontanel/PAnS.

Related papers

• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• Placing Objects in Context via Inpainting for Out-of-distribution Segmentation [59.00092709848619]
  Placing Objects in Context (POC) is a pipeline to realistically add objects to an image. POC can be used to extend any dataset with an arbitrary number of objects. We present different anomaly segmentation datasets based on POC-generated data and show that POC can improve the performance of recent state-of-the-art anomaly fine-tuning methods.
  arXiv  Detail & Related papers  (2024-02-26T08:32:41Z)
• UGainS: Uncertainty Guided Anomaly Instance Segmentation [80.12253291709673]
  A single unexpected object on the road can cause an accident or lead to injuries. Current approaches tackle anomaly segmentation by assigning an anomaly score to each pixel. We propose an approach that produces accurate anomaly instance masks.
  arXiv  Detail & Related papers  (2023-08-03T20:55:37Z)
• Anomaly Detection via Multi-Scale Contrasted Memory [3.0170109896527086]
  We introduce a new two-stage anomaly detector which memorizes during training multi-scale normal prototypes to compute an anomaly deviation score. Our model highly improves the state-of-the-art performance on a wide range of object, style and local anomalies with up to 35% error relative improvement on CIFAR-10.
  arXiv  Detail & Related papers  (2022-11-16T16:58:04Z)
• 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)
• Simulated Adversarial Testing of Face Recognition Models [53.10078734154151]
  We propose a framework for learning how to test machine learning algorithms using simulators in an adversarial manner. We are the first to show that weaknesses of models trained on real data can be discovered using simulated samples.
  arXiv  Detail & Related papers  (2021-06-08T17:58:10Z)
• Prototype Memory for Large-scale Face Representation Learning [0.5524804393257919]
  Softmax-based approach is not suitable for datasets with millions of persons. We propose a novel face representation learning model called Prototype Memory. We prove the effectiveness of the proposed model by extensive experiments on popular face recognition benchmarks.
  arXiv  Detail & Related papers  (2021-05-05T15:08:34Z)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)

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.