DeepAI AI Chat
Log In Sign Up

C2AE: Class Conditioned Auto-Encoder for Open-set Recognition

04/02/2019
by   Poojan Oza, et al.
Johns Hopkins University
12

Models trained for classification often assume that all testing classes are known while training. As a result, when presented with an unknown class during testing, such closed-set assumption forces the model to classify it as one of the known classes. However, in a real world scenario, classification models are likely to encounter such examples. Hence, identifying those examples as unknown becomes critical to model performance. A potential solution to overcome this problem lies in a class of learning problems known as open-set recognition. It refers to the problem of identifying the unknown classes during testing, while maintaining performance on the known classes. In this paper, we propose an open-set recognition algorithm using class conditioned auto-encoders with novel training and testing methodology. In contrast to previous methods, training procedure is divided in two sub-tasks, 1. closed-set classification and, 2. open-set identification (i.e. identifying a class as known or unknown). Encoder learns the first task following the closed-set classification training pipeline, whereas decoder learns the second task by reconstructing conditioned on class identity. Furthermore, we model reconstruction errors using the Extreme Value Theory of statistical modeling to find the threshold for identifying known/unknown class samples. Experiments performed on multiple image classification datasets show proposed method performs significantly better than state of the art.

READ FULL TEXT

page 3

page 11

03/28/2021

Learning Placeholders for Open-Set Recognition

Traditional classifiers are deployed under closed-set setting, with both...
05/06/2017

Sparse Representation-based Open Set Recognition

We propose a generalized Sparse Representation- based Classification (SR...
09/23/2022

Understanding Open-Set Recognition by Jacobian Norm of Representation

In contrast to conventional closed-set recognition, open-set recognition...
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...
03/09/2023

R-Tuning: Regularized Prompt Tuning in Open-Set Scenarios

In realistic open-set scenarios where labels of a part of testing data a...
03/16/2022

Open Set Recognition using Vision Transformer with an Additional Detection Head

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