Pith. sign in

REVIEW 5 cited by

How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2203.04450 v3 pith:4QL3CPXD submitted 2022-03-08 cs.CV cs.LG

Yifei Ming , Yiyou Sun , Ousmane Dia , Yixuan Li This is my paper
classification cs.CVcs.LG
keywords detectioncidersampleshypersphericallearningprototypesclasscompactness
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Out-of-distribution (OOD) detection is a critical task for reliable machine learning. Recent advances in representation learning give rise to distance-based OOD detection, where testing samples are detected as OOD if they are relatively far away from the centroids or prototypes of in-distribution (ID) classes. However, prior methods directly take off-the-shelf contrastive losses that suffice for classifying ID samples, but are not optimally designed when test inputs contain OOD samples. In this work, we propose CIDER, a novel representation learning framework that exploits hyperspherical embeddings for OOD detection. CIDER jointly optimizes two losses to promote strong ID-OOD separability: a dispersion loss that promotes large angular distances among different class prototypes, and a compactness loss that encourages samples to be close to their class prototypes. We analyze and establish the unexplored relationship between OOD detection performance and the embedding properties in the hyperspherical space, and demonstrate the importance of dispersion and compactness. CIDER establishes superior performance, outperforming the latest rival by 19.36% in FPR95. Code is available at https://github.com/deeplearning-wisc/cider.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. VAE with Hyperspherical Coordinates: Improving Anomaly Detection from Hypervolume-Compressed Latent Space

    cs.LG 2026-01 unverdicted novelty 7.0 of 10

    VAEs using hyperspherical latent coordinates compress the hypervolume to achieve superior unconditional and conditional anomaly detection on complex image datasets.

  2. ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    Under cold-start scarcity, ArcAD's Sinkhorn-balanced hyperspherical clustering plus anomaly-guided repulsion lifts reconstruction-based anomaly detection, with the clearest gains (+3.7 to +11.2 I-AUROC) on large multi...

  3. Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Norm-balanced, hierarchy-aware hyperbolic prototypes as the classification head improve out-of-distribution detection across many scoring functions and 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.

  5. Task-Driven Discrete Representation Learning

    cs.LG 2025-06 reject novelty 3.0 of 10

    A task-conditioned discrete representation objective with a Wasserstein regularizer, claiming an accuracy versus sample-complexity trade-off, with applications to RL state abstraction and domain generalization.

Pith tools