Timezone: »

 
Poster
DROCC: Deep Robust One-Class Classification
Sachin Goyal · Aditi Raghunathan · Moksh Jain · Harsha Vardhan Simhadri · Prateek Jain

Tue Jul 14 08:00 AM -- 08:45 AM & Tue Jul 14 09:00 PM -- 09:45 PM (PDT) @ None #None
in Poster Session 2 »

Classical approaches for one-class problems such as one-class SVM and isolation forest require careful feature engineering when applied to structured domains like images. State-of-the-art methods aim to leverage deep learning to learn appropriate features via two main approaches. The first approach based on predicting transformations (Golan & El-Yaniv, 2018; Hendrycks et al., 2019a) while successful in some domains, crucially depends on an appropriate domain-specific set of transformations that are hard to obtain in general. The second approach of minimizing a classical one-class loss on the learned final layer representations, e.g., DeepSVDD (Ruff et al., 2018) suffers from the fundamental drawback of representation collapse. In this work, we propose Deep Robust One Class Classification (DROCC) that is both applicable to most standard domains without requiring any side-information and robust to representation collapse. DROCC is based on the assumption that the points from the class of interest lie on a well-sampled, locally linear low dimensional manifold. Empirical evaluation demonstrates that DROCC is highly effective in two different one-class problem settings and on a range of real-world datasets across different domains: tabular data, images (CIFAR and ImageNet), audio, and time-series, offering up to 20% increase in accuracy over the state-of-the-art in anomaly detection.

Keywords: Representation Learning · Unsupervised and Semi-supervised Learning · Unsupervised Learning

Author Information

Sachin Goyal (Microsoft research)

Hi, I am a research fellow at Microsoft Research, India with Dr. Prateek Jain and Dr. Harsha Vardhan Simhadri. I work on anomaly detection and #EdgeML i.e. machine learning on small scale devices. Prospective pHD candidate for autumn 2021. Would love to interact with anyone :)

Aditi Raghunathan (Stanford)
Moksh Jain (MILA / NIT Karnataka, Surathkal)
Harsha Vardhan Simhadri (Microsoft Research)
Prateek Jain (Microsoft Research)

More from the Same Authors