Log In Sign Up

Opening Deep Neural Networks with Generative Models

by   Marcos Vendramini, et al.

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.


page 1

page 2

page 3

page 4


Open Set Recognition with Conditional Probabilistic Generative Models

Deep neural networks have made breakthroughs in a wide range of visual u...

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

The current generation of deep neural networks has achieved close-to-hum...

Open Set Recognition using Vision Transformer with an Additional Detection Head

Deep neural networks have demonstrated prominent capacities for image cl...

Denoising Autoencoders for Overgeneralization in Neural Networks

Despite the recent developments that allowed neural networks to achieve ...

Deep Open-Set Recognition for Silicon Wafer Production Monitoring

The chips contained in any electronic device are manufactured over circu...

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

Unknown examples that are unseen during training often appear in real-wo...

Measuring Human Perception to Improve Open Set Recognition

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