Odd-One-Out: Anomaly Detection by Comparing with Neighbors

• URL: http://arxiv.org/abs/2406.20099v4
• Date: Sat, 22 Mar 2025 08:52:52 GMT
• Title: Odd-One-Out: Anomaly Detection by Comparing with Neighbors
• Authors: Ankan Bhunia, Changjian Li, Hakan Bilen,
• Abstract summary: This paper introduces a novel anomaly detection (AD) problem aimed at identifying odd-looking' objects within a scene by comparing them to other objects present.<n>Unlike traditional AD benchmarks with fixed anomaly criteria, our task detects anomalies specific to each scene by inferring a reference group of regular objects.
• Score: 27.474201071615187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces a novel anomaly detection (AD) problem aimed at identifying `odd-looking' objects within a scene by comparing them to other objects present. Unlike traditional AD benchmarks with fixed anomaly criteria, our task detects anomalies specific to each scene by inferring a reference group of regular objects. To address occlusions, we use multiple views of each scene as input, construct 3D object-centric models for each instance from 2D views, enhancing these models with geometrically consistent part-aware representations. Anomalous objects are then detected through cross-instance comparison. We also introduce two new benchmarks, ToysAD-8K and PartsAD-15K as testbeds for future research in this task. We provide a comprehensive analysis of our method quantitatively and qualitatively on these benchmarks.

Related papers

• Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline [63.96226274616927]
  A new framework called Track Any Anomalous Object (TAO) introduces a granular video anomaly detection pipeline.<n>Unlike methods that assign anomaly scores to every pixel, our approach transforms the problem into pixel-level tracking of anomalous objects.<n>Experiments demonstrate that TAO sets new benchmarks in accuracy and robustness.
  arXiv  Detail & Related papers  (2025-06-05T15:49:39Z)
• Believing is Seeing: Unobserved Object Detection using Generative Models [17.883297093049787]
  This study introduces the novel tasks of 2D, 2.5D and 3D unobserved object detection. We adapt several state-of-the-art pre-trained generative models to address this task. We show that they can be used to infer the presence of objects that are not directly observed.
  arXiv  Detail & Related papers  (2024-10-08T09:57:14Z)
• Looking 3D: Anomaly Detection with 2D-3D Alignment [27.474201071615187]
  This paper introduces a new conditional anomaly detection problem, which involves identifying anomalies in a query image by comparing it to a reference shape. We have created a large dataset, BrokenChairs-180K, consisting of around 180K images, with diverse anomalies, geometries, and textures paired with 8,143 reference 3D shapes. Our approach has been rigorously evaluated through comprehensive experiments, serving as a benchmark for future research in this domain.
  arXiv  Detail & Related papers  (2024-06-27T17:59:46Z)
• View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesis [0.0]
  Inspection and monitoring of infrastructure assets requires identifying visual anomalies in scenes periodically photographed over time. Images collected manually or with robots such as unmanned aerial vehicles from the same scene at different instances in time are typically not perfectly aligned. Current unsupervised pixel-level anomaly detection methods have mainly been developed for industrial settings. We present a novel network termed OmniAD to address the Scene AD problem posed.
  arXiv  Detail & Related papers  (2024-06-26T01:54:10Z)
• S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection [21.96072831561483]
  This paper proposes a novel Supervised Shape&Scale-perceptive Deformable Attention'' (S$3$-DA) module for monocular 3D object detection. Benefiting from this, S$3$-DA effectively estimates receptive fields for query points belonging to any category, enabling them to generate robust query features. Experiments on KITTI and Open datasets demonstrate that S$3$-DA significantly improves the detection accuracy.
  arXiv  Detail & Related papers  (2023-09-02T12:36:38Z)
• Object-Centric Multiple Object Tracking [124.30650395969126]
  This paper proposes a video object-centric model for multiple-object tracking pipelines. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module. Benefited from object-centric learning, we only require sparse detection labels for object localization and feature binding.
  arXiv  Detail & Related papers  (2023-09-01T03:34:12Z)
• When Super-Resolution Meets Camouflaged Object Detection: A Comparison Study [135.19004496785408]
  Super Resolution (SR) and Camouflaged Object Detection (COD) are two hot topics in computer vision with various joint applications. We benchmark different super-resolution methods on commonly used COD datasets. We evaluate the robustness of different COD models by using COD data processed by SR methods.
  arXiv  Detail & Related papers  (2023-08-08T16:17:46Z)
• 3DMODT: Attention-Guided Affinities for Joint Detection & Tracking in 3D Point Clouds [95.54285993019843]
  We propose a method for joint detection and tracking of multiple objects in 3D point clouds. Our model exploits temporal information employing multiple frames to detect objects and track them in a single network.
  arXiv  Detail & Related papers  (2022-11-01T20:59:38Z)
• Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision [63.429704654271475]
  We propose a novel weakly supervised method RWSeg that only requires labeling one object with one point. With these sparse weak labels, we introduce a unified framework with two branches to propagate semantic and instance information. Specifically, we propose a Cross-graph Competing Random Walks (CRW) algorithm that encourages competition among different instance graphs.
  arXiv  Detail & Related papers  (2022-08-10T02:14:39Z)
• Benchmarking Deep Models for Salient Object Detection [67.07247772280212]
  We construct a general SALient Object Detection (SALOD) benchmark to conduct a comprehensive comparison among several representative SOD methods. In the above experiments, we find that existing loss functions usually specialized in some metrics but reported inferior results on the others. We propose a novel Edge-Aware (EA) loss that promotes deep networks to learn more discriminative features by integrating both pixel- and image-level supervision signals.
  arXiv  Detail & Related papers  (2022-02-07T03:43:16Z)
• MVM3Det: A Novel Method for Multi-view Monocular 3D Detection [0.0]
  MVM3Det simultaneously estimates the 3D position and orientation of the object according to the multi-view monocular information. We present a first dataset for multi-view 3D object detection named MVM3D.
  arXiv  Detail & Related papers  (2021-09-22T01:31:00Z)
• ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects [0.0]
  ODDObjects is designed to detect anomalies of various categories using unsupervised autoencoders trained on COCO-style datasets. The framework extends previous work on anomaly detection with autoencoders, comparing state-of-the-art models trained on object recognition datasets.
  arXiv  Detail & Related papers  (2021-04-26T01:13:28Z)
• Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation [79.6596425920849]
  This paper addresses the task of unsupervised video multi-object segmentation. We introduce a novel approach for more accurate and efficient unseen-temporal segmentation. We evaluate the proposed approach on DAVIS$_17$ and YouTube-VIS, and the results demonstrate that it outperforms state-of-the-art methods both in segmentation accuracy and inference speed.
  arXiv  Detail & Related papers  (2021-04-10T14:39:44Z)
• 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)
• Attention-based Joint Detection of Object and Semantic Part [4.389917490809522]
  Our model is created on top of two Faster-RCNN models that share their features to get enhanced representations of both. Experiments on the PASCAL-Part 2010 dataset show that joint detection can simultaneously improve both object detection and part detection.
  arXiv  Detail & Related papers  (2020-07-05T18:54:10Z)
• Frustratingly Simple Few-Shot Object Detection [98.42824677627581]
  We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 220 points on current benchmarks.
  arXiv  Detail & Related papers  (2020-03-16T00:29:14Z)
• OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features [14.115782214599015]
  One-shot object detection consists in detecting objects defined by a single demonstration. We build the one-stage system that performs localization and recognition jointly. Experimental evaluation on several challenging domains shows that our method can detect unseen classes.
  arXiv  Detail & Related papers  (2020-03-15T11:39:47Z)
• BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View [117.44028458220427]
  On-board 3D object detection in autonomous vehicles often relies on geometry information captured by LiDAR devices. We present a fully end-to-end 3D object detection framework that can infer oriented 3D boxes solely from BEV images.
  arXiv  Detail & Related papers  (2020-03-09T15:08:40Z)
• OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning [23.48763375455514]
  We propose a One-for-all Image Anomaly Detection system based on disentangled learning using only clean samples. Our experiments with three datasets show that OIAD can detect over $90%$ of anomalies while maintaining a low false alarm rate.
  arXiv  Detail & Related papers  (2020-01-18T09:57:37Z)

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.