SSD: A Unified Framework for Self-Supervised Outlier Detection

• URL: http://arxiv.org/abs/2103.12051v1
• Date: Mon, 22 Mar 2021 17:51:35 GMT
• Title: SSD: A Unified Framework for Self-Supervised Outlier Detection
• Authors: Vikash Sehwag, Mung Chiang, Prateek Mittal
• Abstract summary: We propose an outlier detector based on only unlabeled in-distribution data. We use self-supervised representation learning followed by a Mahalanobis distance based detection. We extend our framework to incorporate training data labels, if available.
• Score: 37.254114112911786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We ask the following question: what training information is required to design an effective outlier/out-of-distribution (OOD) detector, i.e., detecting samples that lie far away from the training distribution? Since unlabeled data is easily accessible for many applications, the most compelling approach is to develop detectors based on only unlabeled in-distribution data. However, we observe that most existing detectors based on unlabeled data perform poorly, often equivalent to a random prediction. In contrast, existing state-of-the-art OOD detectors achieve impressive performance but require access to fine-grained data labels for supervised training. We propose SSD, an outlier detector based on only unlabeled in-distribution data. We use self-supervised representation learning followed by a Mahalanobis distance based detection in the feature space. We demonstrate that SSD outperforms most existing detectors based on unlabeled data by a large margin. Additionally, SSD even achieves performance on par, and sometimes even better, with supervised training based detectors. Finally, we expand our detection framework with two key extensions. First, we formulate few-shot OOD detection, in which the detector has access to only one to five samples from each class of the targeted OOD dataset. Second, we extend our framework to incorporate training data labels, if available. We find that our novel detection framework based on SSD displays enhanced performance with these extensions, and achieves state-of-the-art performance. Our code is publicly available at https://github.com/inspire-group/SSD.

Related papers

• Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation [4.457854503856095]
  Out-of-distribution (OOD) detection addresses the challenge of identifying inputs that differ from in-distribution (ID) data. We propose TARDIS, a post-hoc OOD detection method for scalable geospatial deployments. Our method takes a pre-trained model, ID data WILD samples, and WILD samples, disentangling the latter into surrogate ID and surrogate OOD labels. To demonstrate scalability, we deploy TARDIS on the Fields of the World dataset, offering actionable insights into pre-trained model behavior for large-scale deployments.
  arXiv  Detail & Related papers  (2024-12-18T00:10:44Z)
• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• EAT: Towards Long-Tailed Out-of-Distribution Detection [55.380390767978554]
  This paper addresses the challenging task of long-tailed OOD detection. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes. We propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes, and (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data.
  arXiv  Detail & Related papers  (2023-12-14T13:47:13Z)
• Label-Efficient Object Detection via Region Proposal Network Pre-Training [58.50615557874024]
  We propose a simple pretext task that provides an effective pre-training for the region proposal network (RPN) In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance.
  arXiv  Detail & Related papers  (2022-11-16T16:28:18Z)
• TDT: Teaching Detectors to Track without Fully Annotated Videos [2.8292841621378844]
  One-stage trackers that predict both detections and appearance embeddings in one forward pass received much attention. Our proposed one-stage solution matches the two-stage counterpart in quality but is 3 times faster.
  arXiv  Detail & Related papers  (2022-05-11T15:56:17Z)
• Logit Normalization for Long-tail Object Detection [32.18963619434191]
  Real-world data exhibiting skewed distributions pose a serious challenge to existing object detectors. We propose Logit Normalization (LogN), a technique to self-calibrate the classified logits of detectors in a similar way to batch normalization. In general, our LogN is training- and tuning-free (i.e. require no extra training and tuning process), model- and label distribution-agnostic, and also plug-and-play.
  arXiv  Detail & Related papers  (2022-03-31T13:28:51Z)
• Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera [83.31666463259849]
  We propose a method to automatically generate training labels (called pseudo-labels) for 2D LiDAR-based person detectors. We show that self-supervised detectors, trained or fine-tuned with pseudo-labels, outperform detectors trained using manual annotations. Our method is an effective way to improve person detectors during deployment without any additional labeling effort.
  arXiv  Detail & Related papers  (2020-12-16T12:10:04Z)
• Stance Detection Benchmark: How Robust Is Your Stance Detection? [65.91772010586605]
  Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim. We introduce a StD benchmark that learns from ten StD datasets of various domains in a multi-dataset learning setting. Within this benchmark setup, we are able to present new state-of-the-art results on five of the datasets.
  arXiv  Detail & Related papers  (2020-01-06T13:37:51Z)

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.