pith. sign in

arxiv: 2202.01197 · v4 · pith:6CMOZU4Wnew · submitted 2022-02-02 · 💻 cs.LG · cs.CV

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

classification 💻 cs.LG cs.CV
keywords datadetectionoutliervirtualmodelmodelsnovelobject
0
0 comments X
read the original abstract

Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Previous approaches rely on real outlier datasets for model regularization, which can be costly and sometimes infeasible to obtain in practice. In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision boundary during training. Specifically, VOS samples virtual outliers from the low-likelihood region of the class-conditional distribution estimated in the feature space. Alongside, we introduce a novel unknown-aware training objective, which contrastively shapes the uncertainty space between the ID data and synthesized outlier data. VOS achieves competitive performance on both object detection and image classification models, reducing the FPR95 by up to 9.36% compared to the previous best method on object detectors. Code is available at https://github.com/deeplearning-wisc/vos.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 7.0

    NegAS uses negative labels for attention guidance and sigmoid scoring to improve OOD detection in VLM-based object detectors while preserving ID performance.

  2. Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models

    cs.LG 2026-05 unverdicted novelty 6.0

    Debiased negative mining via Monte-Carlo sampling from ID labels and unlabeled wild data improves OOD detection with VLMs and achieves new state-of-the-art results.

  3. GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels

    cs.CV 2026-05 unverdicted novelty 6.0

    GAMR introduces geometric-aware manifold regularization via virtual outlier synthesis to enhance intra-class compactness and inter-class separation, improving robustness to noisy labels beyond passive sample filtering.

  4. HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels

    cs.CV 2026-05 unverdicted novelty 6.0

    HamBR uses Spherical HMC to probe ambiguous regions and synthesize virtual outliers with energy-based repulsion to restore decision boundaries degraded by noisy labels, achieving SOTA on CIFAR and real-world benchmarks.

  5. Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing

    cs.LG 2026-04 unverdicted novelty 6.0

    A framework unifies runtime monitoring for safety-critical ML into ODD, OOD, and OMS categories and demonstrates them on vision-based runway detection for landing.

  6. Uncertainty Quantification in Detection Transformers: Object-Level Calibration and Image-Level Reliability

    cs.CV 2024-12 unverdicted novelty 6.0

    DETRs learn an optimal specialist strategy via the Hungarian loss, motivating the new Object-level Calibration Error (OCE) metric and an image-level post-hoc uncertainty quantification framework.

  7. ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

    cs.LG 2024-02 unverdicted novelty 6.0

    ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and I...