Open-Set Recognition: A Good Closed-Set Classifier is All You Need

by   Sagar Vaze, et al.

The ability to identify whether or not a test sample belongs to one of the semantic classes in a classifier's training set is critical to practical deployment of the model. This task is termed open-set recognition (OSR) and has received significant attention in recent years. In this paper, we first demonstrate that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes. We find that this relationship holds across loss objectives and architectures, and further demonstrate the trend both on the standard OSR benchmarks as well as on a large-scale ImageNet evaluation. Second, we use this correlation to boost the performance of the cross-entropy OSR 'baseline' by improving its closed-set accuracy, and with this strong baseline achieve a new state-of-the-art on the most challenging OSR benchmark. Similarly, we boost the performance of the existing state-of-the-art method by improving its closed-set accuracy, but this does not surpass the strong baseline on the most challenging dataset. Our third contribution is to reappraise the datasets used for OSR evaluation, and construct new benchmarks which better respect the task of detecting semantic novelty, as opposed to low-level distributional shifts as tackled by neighbouring machine learning fields. In this new setting, we again demonstrate that there is negligible difference between the strong baseline and the existing state-of-the-art.


page 2

page 8

page 21

page 22

∙ 08/10/2023

𝒢^2Pxy: Generative Open-Set Node Classification on Graphs with Proxy Unknowns

Node classification is the task of predicting the labels of unlabeled no...
∙ 01/09/2023

On advantages of Mask-level Recognition for Open-set Segmentation in the Wild

Most dense recognition methods bring a separate decision in each particu...
∙ 04/20/2020

Boosting Deep Open World Recognition by Clustering

While convolutional neural networks have brought significant advances in...
∙ 09/07/2018

Open Set Adversarial Examples

Adversarial examples in recent works target at closed set recognition sy...
∙ 01/19/2023

Hybrid Open-set Segmentation with Synthetic Negative Data

Open-set segmentation is often conceived by complementing closed-set cla...
∙ 08/24/2023

LORD: Leveraging Open-Set Recognition with Unknown Data

Handling entirely unknown data is a challenge for any deployed classifie...
∙ 11/18/2019

Large Scale Open-Set Deep Logo Detection

We present an open-set logo detection (OSLD) system, which can detect (l...

Please sign up or login with your details

Forgot password? Click here to reset