Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learning
Not on the map. Why?
Abstract (arXiv)
Open set recognition (OSR) and continual learning are two critical challenges in machine learning, focusing respectively on detecting novel classes at inference time and updating models to incorporate the new classes. While many recent approaches have addressed these problems, particularly OSR, by heuristically promoting feature diversity, few studies have directly examined the role that feature diversity plays in tackling them. In this work, we provide empirical evidence that enhancing feature diversity improves the recognition of open set samples. Moreover, increased feature diversity also facilitates both the retention of previously learned data and the integration of new data in continual learning. We hope our findings can inspire further research into both practical methods and theoretical understanding in these domains.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 18 Aug 2025.
Builds on
34 of 50 references.
References · 34
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
- 2016Learning without Forgettingcited by 2,496
- 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
- 2019Similarity of Neural Network Representations Revisitedcited by 1,755
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
- 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
- 2021Learning to Prompt for Continual Learningcited by 944
- 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
- 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
- 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
22 more
- 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
- 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
- 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
- 2018Reducing Network Agnostophobiacited by 165
- 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
- 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
- 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
- 2018Deep Learning for Sentiment Analysis : A Surveycited by 139
- 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
- 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
- 2020Hybrid Models for Open Set Recognitioncited by 109
- 2020Few-Shot Open-Set Recognition using Meta-Learningcited by 50
- 2018Learning a Neural-network-based Representation for Open Set Recognitioncited by 40
- 2024Make Continual Learning Stronger via C-Flatcited by 35
- 2017Open-Category Classification by Adversarial Sample Generationcited by 24
- 2023Is forgetting less a good inductive bias for forward transfer?cited by 18
- 2020Open-Set Recognition with Gaussian Mixture Variational Autoencoderscited by 15
- 2022Provable and Efficient Continual Representation Learningcited by 14
- 2024Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillationcited by 11
- 2021Novelty Detection via Contrastive Learning with Negative Data Augmentationcited by 10
- 2023Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspectivecited by 10
- 2020Assessing The Importance Of Colours For CNNs In Object Recognitioncited by 8
Built on by
Not cited yet.