Dense open-set recognition with synthetic outliers generated by Real NVP
Today's deep models are often unable to detect inputs which do not belong to the training distribution. This gives rise to confident incorrect predictions which could lead to devastating consequences in many important application fields such as healthcare and autonomous driving. Interestingly, both discriminative and generative models appear to be equally affected. Consequently, this vulnerability represents an important research challenge. We consider an outlier detection approach based on discriminative training with jointly learned synthetic outliers. We obtain the synthetic outliers by sampling an RNVP model which is jointly trained to generate datapoints at the border of the training distribution. We show that this approach can be adapted for simultaneous semantic segmentation and dense outlier detection. We present image classification experiments on CIFAR-10, as well as semantic segmentation experiments on three existing datasets (StreetHazards, WD-Pascal, Fishyscapes Lost & Found), and one contributed dataset. Our models perform competitively with respect to the state of the art despite producing predictions with only one forward pass.
Code (1)
Tasks
Autonomous Drivingimage-classificationImage ClassificationOpen Set LearningOutlier DetectionSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Dense outlier detection and open-set recognition based on training with noisy negative images
Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution. Consequently, the problem of detecting outlier images has recently been receiving a lot of attention. Unlike…
Open Set LearningOutlier DetectionRobust Bayesian Method for Simultaneous Block Sparse Signal Recovery with Applications to Face Recognition
In this paper, we present a novel Bayesian approach to recover simultaneously block sparse signals in the presence of outliers. The key advantage of our proposed method is the ability to handle non-stationary outliers, i…
Face RecognitionSynthetic Captions for Open-Vocabulary Zero-Shot Segmentation
Generative vision-language models (VLMs) exhibit strong high-level image understanding but lack spatially dense alignment between vision and language modalities, as our findings indicate. Orthogonal to advancements in ge…
Representation LearningzGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation
The phenomenon of "black swans" has posed a fundamental challenge to performance of classical machine learning models. The perceived rise in frequency of outlier conditions, especially in post-pandemic environment, has n…
Binary ClassificationGenerative Adversarial NetworkSynthetic Data EvaluationSynthetic Data Generation+1Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors
We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers. Motivated by the difficulty of curating suitable calibration data…
Data AugmentationOpen Set LearningOut-of-Distribution DetectionOut of Distribution (OOD) Detection+1