mlsanityData to 14 Oct 2026

Open-Set Recognition with Gradient-Based Representations

arXiv 2206.08229 ↗First posted 16 Jun 2022cs.CVcited by 7

Not on the map. Why?

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.

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

20 of 23 references.

References · 20

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  7. 2016An overview of gradient descent optimization algorithmscited by 1,033
  8. 2015Towards Open Set Deep Networkscited by 538
  9. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  10. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  11. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  12. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
8 more
  1. 2020Gradients as a Measure of Uncertainty in Neural Networkscited by 55
  2. 2020Backpropagated Gradient Representations for Anomaly Detectioncited by 54
  3. 2018Classification Uncertainty of Deep Neural Networks Based on Gradient Informationcited by 43
  4. 2020Contrastive Explanations in Neural Networkscited by 26
  5. 2018CURE-OR: Challenging Unreal and Real Environments for Object Recognitioncited by 19
  6. 2019Distorted Representation Space Characterization Through Backpropagated Gradientscited by 12
  7. 2020Implicit Saliency in Deep Neural Networkscited by 9
  8. 2019Object Recognition under Multifarious Conditions: A Reliability Analysis and A Feature Similarity-based Performance Estimationcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 2.

7 papers.

  1. 2023Gaussian Switch Sampling: A Second Order Approach to Active Learningcited by 10
  2. 2023A Survey on Open-Set Image Recognitioncited by 7
  3. 2022Open-Set Automatic Target Recognitioncited by 4
  4. 2024TrajPRed: Trajectory Prediction with Region-based Relation Learningcited by 3
  5. 2022R2-AD2: Detecting Anomalies by Analysing the Raw Gradientcited by 2
  6. 2024Targeting Negative Flips in Active Learning using Validation Setscited by 1
  7. 2023Learning Trajectory-Conditioned Relations to Predict Pedestrian Crossing Behaviorcited by 0