DeepAI
Log In Sign Up

Opening Deep Neural Networks with Generative Models

05/20/2021
by   Marcos Vendramini, et al.
0

Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes. Real-world problems, however, may not allow for a full knowledge of the input and label spaces, making failures in recognition a hazard to deep visual learning. Open set recognition methods are characterized by the ability to correctly identifying inputs of known and unknown classes. In this context, we propose GeMOS: simple and plug-and-play open set recognition modules that can be attached to pretrained Deep Neural Networks for visual recognition. The GeMOS framework pairs pre-trained Convolutional Neural Networks with generative models for open set recognition to extract open set scores for each sample, allowing for failure recognition in object recognition tasks. We conduct a thorough evaluation of the proposed method in comparison with state-of-the-art open set algorithms, finding that GeMOS either outperforms or is statistically indistinguishable from more complex and costly models.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/12/2020

Open Set Recognition with Conditional Probabilistic Generative Models

Deep neural networks have made breakthroughs in a wide range of visual u...
10/21/2021

Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networks

The current generation of deep neural networks has achieved close-to-hum...
03/16/2022

Open Set Recognition using Vision Transformer with an Additional Detection Head

Deep neural networks have demonstrated prominent capacities for image cl...
09/14/2017

Denoising Autoencoders for Overgeneralization in Neural Networks

Despite the recent developments that allowed neural networks to achieve ...
08/30/2022

Deep Open-Set Recognition for Silicon Wafer Production Monitoring

The chips contained in any electronic device are manufactured over circu...
03/18/2021

Collective Decision of One-vs-Rest Networks for Open Set Recognition

Unknown examples that are unseen during training often appear in real-wo...
09/08/2022

Measuring Human Perception to Improve Open Set Recognition

The human ability to recognize when an object is known or novel currentl...