Pith. sign in

REVIEW 4 cited by

Non-Parametric Outlier Synthesis

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.02966 v1 pith:SQKNSAME submitted 2023-03-06 cs.LG cs.AI

classification cs.LGcs.AI
keywords synthesisdatanposoutlierapproachassumptiondetectionframework
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Out-of-distribution (OOD) detection is indispensable for safely deploying machine learning models in the wild. 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. Recent work on outlier synthesis modeled the feature space as parametric Gaussian distribution, a strong and restrictive assumption that might not hold in reality. In this paper, we propose a novel framework, Non-Parametric Outlier Synthesis (NPOS), which generates artificial OOD training data and facilitates learning a reliable decision boundary between ID and OOD data. Importantly, our proposed synthesis approach does not make any distributional assumption on the ID embeddings, thereby offering strong flexibility and generality. We show that our synthesis approach can be mathematically interpreted as a rejection sampling framework. Extensive experiments show that NPOS can achieve superior OOD detection performance, outperforming the competitive rivals by a significant margin. Code is publicly available at https://github.com/deeplearning-wisc/npos.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

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

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    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.

  2. Segmentation Assisted Incremental Test Time Adaptation in an Open World

    cs.CV 2025-08 conditional novelty 6.0 of 10

    SegAssist uses CLIP's dense predictions to filter uncertain test images for oracle labeling, improving incremental discovery of unseen classes in test-time adaptation.

  3. Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SynOOD generates synthetic near-boundary OOD images with MLLM-guided inpainting and energy-score gradients, then fine-tunes CLIP image and text features, reporting state-of-the-art OOD detection on ImageNet benchmarks.

  4. Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    KR-NFT tunes CLIP text features with image-conditioned scaling and shifting plus a knowledge regularization loss, improving OOD detection on base and unseen classes without forgetting pre-trained knowledge.

Pith tools