Timezone: »

 
Poster
SIREN: Shaping Representations for Detecting Out-of-Distribution Objects
Xuefeng Du · Gabriel Gozum · Yifei Ming · Yixuan Li

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #137
in Poster Session 2 »

Detecting out-of-distribution (OOD) objects is indispensable for safely deploying object detectors in the wild. Although distance-based OOD detection methods have demonstrated promise in image classification, they remain largely unexplored in object-level OOD detection. This paper bridges the gap by proposing a distance-based framework for detecting OOD objects, which relies on the model-agnostic representation space and provides strong generality across different neural architectures. Our proposed framework SIREN contributes two novel components: (1) a representation learning component that uses a trainable loss function to shape the representations into a mixture of von Mises-Fisher (vMF) distributions on the unit hypersphere, and (2) a test-time OOD detection score leveraging the learned vMF distributions in a parametric or non-parametric way. SIREN achieves competitive performance on both the recent detection transformers and CNN-based models, improving the AUROC by a large margin compared to the previous best method. Code is publicly available at https://github.com/deeplearning-wisc/siren.

[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Xuefeng Du (UW-Madison)
Gabriel Gozum (Department of Computer Science, University of Wisconsin - Madison)
Yifei Ming (University of Wisconsin-Madison)

I'm a Ph.D. student at the University of Wisconsin-Madison. I’m broadly interested in trustworthy machine learning and representation learning. Research topics that I am currently focusing on include: out-of-distribution detection, domain generalization, supervised and self-supervised (multi-modal) representation learning. My prior research involves designing efficient algorithms and promoting fundamental understandings to enable reliable open-world learning. (e.g., impact of spurious correlation, sample efficiency, and multi-modality).

Yixuan Li (University of Wisconsin-Madison)

More from the Same Authors