Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2211.06660v2
• Date: Thu, 14 Sep 2023 13:13:25 GMT
• Title: Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
• Authors: Silvio Galesso, Max Argus, Thomas Brox
• Abstract summary: Nearest-Neighbors approaches have been shown to work well in object-centric data domains. We show that nearest-neighbor approaches also yield state-of-the-art results on dense novelty detection in complex driving scenes.
• Score: 33.78080060234557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The key to out-of-distribution detection is density estimation of the in-distribution data or of its feature representations. This is particularly challenging for dense anomaly detection in domains where the in-distribution data has a complex underlying structure. Nearest-Neighbors approaches have been shown to work well in object-centric data domains, such as industrial inspection and image classification. In this paper, we show that nearest-neighbor approaches also yield state-of-the-art results on dense novelty detection in complex driving scenes when working with an appropriate feature representation. In particular, we find that transformer-based architectures produce representations that yield much better similarity metrics for the task. We identify the multi-head structure of these models as one of the reasons, and demonstrate a way to transfer some of the improvements to CNNs. Ultimately, the approach is simple and non-invasive, i.e., it does not affect the primary segmentation performance, refrains from training on examples of anomalies, and achieves state-of-the-art results on RoadAnomaly, StreetHazards, and SegmentMeIfYouCan-Anomaly.

Related papers

• GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [68.14842693208465]
  GeneralAD is an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining.
  arXiv  Detail & Related papers  (2024-07-17T09:27:41Z)
• Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning [24.701170582359104]
  Existing works assume that neighbors' information offers the basis for estimating the attributes of the unobserved target. We propose Contrastive-Prototypical'' self-supervised learning for Kriging to refine valuable information from neighbors and recycle the one from non-neighbors.
  arXiv  Detail & Related papers  (2024-01-23T11:46:31Z)
• Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection [57.646582245834324]
  We propose a simple yet effective deepfake detector called LSDA. It is based on a idea: representations with a wider variety of forgeries should be able to learn a more generalizable decision boundary. We show that our proposed method is surprisingly effective and transcends state-of-the-art detectors across several widely used benchmarks.
  arXiv  Detail & Related papers  (2023-11-19T09:41:10Z)
• Weakly-supervised deepfake localization in diffusion-generated images [4.548755617115687]
  We propose a weakly-supervised localization problem based on the Xception network as the backbone architecture. We show that the best performing detection method (based on local scores) is less sensitive to the looser supervision than to the mismatch in terms of dataset or generator.
  arXiv  Detail & Related papers  (2023-11-08T10:27:36Z)
• Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training [17.6179873429447]
  State-of-the-art semi-supervised semantic segmentation networks with consistency training can help to deal with this issue. We propose to integrate the consistency of both features and outputs in the end-to-end network training of unlabeled samples. Experimental results show that the proposed approach can well extract more complete building structures.
  arXiv  Detail & Related papers  (2022-05-17T14:55:13Z)
• Pretrained equivariant features improve unsupervised landmark discovery [69.02115180674885]
  We formulate a two-step unsupervised approach that overcomes this challenge by first learning powerful pixel-based features. Our method produces state-of-the-art results in several challenging landmark detection datasets.
  arXiv  Detail & Related papers  (2021-04-07T05:42:11Z)
• Pixel-wise Anomaly Detection in Complex Driving Scenes [30.884375526254836]
  We present a pixel-wise anomaly detection framework that uses uncertainty maps to improve anomaly detection. Our approach works as a general framework around already trained segmentation networks. Top-2 performance across a range of different anomaly datasets shows the robustness of our approach to handling different anomaly instances.
  arXiv  Detail & Related papers  (2021-03-09T14:26:20Z)
• Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection [60.88952532574564]
  This paper conducts a thorough comparison of out-of-domain intent detection methods. We evaluate multiple contextual encoders and methods, proven to be efficient, on three standard datasets for intent classification. Our main findings show that fine-tuning Transformer-based encoders on in-domain data leads to superior results.
  arXiv  Detail & Related papers  (2021-01-11T09:10:58Z)
• Video Anomaly Detection by Estimating Likelihood of Representations [21.879366166261228]
  Video anomaly is a challenging task because it involves solving many sub-tasks such as motion representation, object localization and action recognition. Traditionally, solutions to this task have focused on the mapping between video frames and their low-dimensional features, while ignoring the spatial connections of those features. Recent solutions focus on analyzing these spatial connections by using hard clustering techniques, such as K-Means, or applying neural networks to map latent features to a general understanding. In order to solve video anomaly in the latent feature space, we propose a deep probabilistic model to transfer this task into a density estimation problem.
  arXiv  Detail & Related papers  (2020-12-02T19:16:22Z)
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation [62.29076080124199]
  This paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains.
  arXiv  Detail & Related papers  (2020-03-23T13:40:06Z)
• Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection [86.69077525494106]
  Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. Existing UDA methods largely ignore the instantaneous data distribution during model learning, which could deteriorate the feature representation given large domain shift. We propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains.
  arXiv  Detail & Related papers  (2020-03-19T13:30:45Z)

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.