# Open-Set Recognition with Gradient-Based Representations

arXiv: https://arxiv.org/abs/2206.08229 · HTML: https://mlsanity.com/paper/2206.08229/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [Classification-Reconstruction Learning for Open-Set Recognition](https://mlsanity.com/paper/1812.04246/) (2018)
- [C2AE: Class Conditioned Auto-Encoder for Open-set Recognition](https://mlsanity.com/paper/1904.01198/) (2019)
- [Conditional Gaussian Distribution Learning for Open Set Recognition](https://mlsanity.com/paper/2003.08823/) (2020)
- [Gradients as a Measure of Uncertainty in Neural Networks](https://mlsanity.com/paper/2008.08030/) (2020)
- [Backpropagated Gradient Representations for Anomaly Detection](https://mlsanity.com/paper/2007.09507/) (2020)
- [Classification Uncertainty of Deep Neural Networks Based on Gradient Information](https://mlsanity.com/paper/1805.08440/) (2018)
- [Contrastive Explanations in Neural Networks](https://mlsanity.com/paper/2008.00178/) (2020)
- [CURE-OR: Challenging Unreal and Real Environments for Object Recognition](https://mlsanity.com/paper/1810.08293/) (2018)
- [Distorted Representation Space Characterization Through Backpropagated Gradients](https://mlsanity.com/paper/1908.09998/) (2019)
- [Implicit Saliency in Deep Neural Networks](https://mlsanity.com/paper/2008.01874/) (2020)
- [Object Recognition under Multifarious Conditions: A Reliability Analysis and A Feature Similarity-based Performance Estimation](https://mlsanity.com/paper/1902.06585/) (2019)

## Built on by (most cited first, 7 of 7)

- [Gaussian Switch Sampling: A Second Order Approach to Active Learning](https://mlsanity.com/paper/2302.12018/) (2023)
- [A Survey on Open-Set Image Recognition](https://mlsanity.com/paper/2312.15571/) (2023)
- [Open-Set Automatic Target Recognition](https://mlsanity.com/paper/2211.05883/) (2022)
- [TrajPRed: Trajectory Prediction with Region-based Relation Learning](https://mlsanity.com/paper/2404.06971/) (2024)
- [R2-AD2: Detecting Anomalies by Analysing the Raw Gradient](https://mlsanity.com/paper/2206.10259/) (2022)
- [Targeting Negative Flips in Active Learning using Validation Sets](https://mlsanity.com/paper/2411.10896/) (2024)
- [Learning Trajectory-Conditioned Relations to Predict Pedestrian Crossing Behavior](https://mlsanity.com/paper/2301.05796/) (2023)

## Abstract (arXiv)

Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of unknown classes. Open-set recognition aims to solve this problem by rejecting unknown classes while classifying known classes correctly. In this paper, we propose to utilize gradient-based representations obtained from a known classifier to train an unknown detector with instances of known classes only. Gradients correspond to the amount of model updates required to properly represent a given sample, which we exploit to understand the model's capability to characterize inputs with its learned features. Our approach can be utilized with any classifier trained in a supervised manner on known classes without the need to model the distribution of unknown samples explicitly. We show that our gradient-based approach outperforms state-of-the-art methods by up to 11.6% in open-set classification.