DeepAI AI Chat
Log In Sign Up

A Weak Supervision Approach to Detecting Visual Anomalies for Automated Testing of Graphics Units

by   Adi Szeskin, et al.

We present a deep learning system for testing graphics units by detecting novel visual corruptions in videos. Unlike previous work in which manual tagging was required to collect labeled training data, our weak supervision method is fully automatic and needs no human labelling. This is achieved by reproducing driver bugs that increase the probability of generating corruptions, and by making use of ideas and methods from the Multiple Instance Learning (MIL) setting. In our experiments, we significantly outperform unsupervised methods such as GAN-based models and discover novel corruptions undetected by baselines, while adhering to strict requirements on accuracy and efficiency of our real-time system.


page 2

page 5


Meta Label Correction for Learning with Weak Supervision

Leveraging weak or noisy supervision for building effective machine lear...

LogLAB: Attention-Based Labeling of Log Data Anomalies via Weak Supervision

With increasing scale and complexity of cloud operations, automated dete...

Novelty Detection and Learning from Extremely Weak Supervision

In this paper we offer a method and algorithm, which make possible fully...

Automatically Detecting Visual Bugs in HTML5 <canvas> Games

The HTML5 <canvas> is used to display high quality graphics in web appli...

Modular Representations for Weak Disentanglement

The recently introduced weakly disentangled representations proposed to ...

DATE: Detecting Anomalies in Text via Self-Supervision of Transformers

Leveraging deep learning models for Anomaly Detection (AD) has seen wide...

Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach

The proliferation of massive open online courses (MOOCs) demands an effe...