Semantic Novelty Detection via Relational Reasoning
Not on the map. Why?
Abstract (arXiv)
Semantic novelty detection aims at discovering unknown categories in the test data. This task is particularly relevant in safety-critical applications, such as autonomous driving or healthcare, where it is crucial to recognize unknown objects at deployment time and issue a warning to the user accordingly. Despite the impressive advancements of deep learning research, existing models still need a finetuning stage on the known categories in order to recognize the unknown ones. This could be prohibitive when privacy rules limit data access, or in case of strict memory and computational constraints (e.g. edge computing). We claim that a tailored representation learning strategy may be the right solution for effective and efficient semantic novelty detection. Besides extensively testing state-of-the-art approaches for this task, we propose a novel representation learning paradigm based on relational reasoning. It focuses on learning how to measure semantic similarity rather than recognizing known categories. Our experiments show that this knowledge is directly transferable to a wide range of scenarios, and it can be exploited as a plug-and-play module to convert closed-set recognition models into reliable open-set ones.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 67 of its 87 references that are in the map. First posted on arXiv 18 Jul 2022.
Builds on
67 of 87 references.
References · 67
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2022Generative Adversarial Networkscited by 5,603
- 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2020Exploring Simple Siamese Representation Learningcited by 2,853
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
- 2020Supervised Contrastive Learningcited by 2,803
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
38 more
- 2013Describing Textures in the Wildcited by 2,110
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
- 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
- 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
- 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
- 2020Energy-based Out-of-distribution Detectioncited by 1,296
- 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
- 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2017Deeper, Broader and Artier Domain Generalizationcited by 983
- 2018Deep Anomaly Detection with Outlier Exposurecited by 939
- 2017Large Batch Training of Convolutional Networkscited by 529
- 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
- 2018Do Deep Generative Models Know What They Don't Know?cited by 443
- 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
- 2017VisDA: The Visual Domain Adaptation Challengecited by 432
- 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
- 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
- 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
- 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
- 2017A simple neural network module for relational reasoningcited by 345
- 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
- 2017Relation Networks for Object Detectioncited by 305
- 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
- 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
- 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
- 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
- 2019Revisiting Self-Supervised Visual Representation Learningcited by 250
- 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
- 2020How Well Do Self-Supervised Models Transfer?cited by 213
- 2020Classification-Based Anomaly Detection for General Datacited by 210
- 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
- 2021Learning to Diversify for Single Domain Generalizationcited by 170
- 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
50 most cited of 67 All 67 (JSON)
Built on by
Citing papers per year: 2023: 2.
2 papers.