DROCC: Deep Robust One Class Classification
Jul 12, 2020
Speakers
Sachin Goyal
Speaker · 0 followers
Aditi Raghunathan
Speaker · 0 followers
Moksh Jain
Speaker · 1 follower
Harsha Vardhan Simhadri
Speaker · 0 followers
Prateek Jain
Speaker · 0 followers
About
Classical approaches for one-class problems such as one-class SVM (Schölkopf et al., 1999) and isolation forest (Liu et al., 2008) require careful feature engineering when applied to structured domains like images. To alleviate this concern, state-of-the-art methods like DeepSVDD (Ruff et al., 2018) consider the natural alternative of minimizing a classical one -class loss applied to the learned final layer representations. However, such an approach suffers from the fundamental drawback that a representation that simply collapses all the inputs minimizes the one class loss; heuristics to mitigate collapsed representations provide limited benefits. In this work, we propose Deep Robust One Class Classification (DROCC) method that is robust to such a collapse by training the network to distinguish the training points from their perturbations, generated adversarially. DROCC is motivated by the assumption that the interesting class lies on a locally linear low dimensional manifold. Empirical evaluation demonstrates DROCC’s effectiveness on two different one-class problem settings and on a range of real-world datasets across different domains—images (CIFAR and ImageNet), audio and timeseries, offering up to 20 over the state-of-the-art in anomaly detection.Classical approaches for one-class problems such as one-class SVM (Schölkopf et al., 1999) and isolation forest (Liu et al., 2008) require careful feature engineering when applied to structured domains like images. To alleviate this concern, state-of-the-art methods like DeepSVDD (Ruff et al., 2018) consider the natural alternative of minimizing a classical one -class loss applied to the learned final layer representations. However, such an approach suffers from the fundamental drawback that a r…
Categories
Education & Teaching
Category · 357 presentations
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters
Watch later
Sulin Liu, …
Leveraging Procedural Generation to Benchmark Reinforcement Learning
Watch later
Karl Cobbe, …
Learning Object-Centric Representations for High-Level PLanning in Minecraft
Watch later
Steven James, …
Encoding Musical Style with Transformer Autoencoders
Watch later
Kristy Choi, …
Spotlight Talk 1.25 (1min)
Watch later
Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances
Watch later
Csaba Toth, …