# M2IOSR: Maximal Mutual Information Open Set Recognition arXiv: https://arxiv.org/abs/2108.02373 ยท HTML: https://mlsanity.com/paper/2108.02373/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 29 of its 56 references that are in the map. - First posted on arXiv 5 Aug 2021. ## Builds on (most cited first, 29 of 29) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014) - [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014) - [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018) - [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016) - [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015) - [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016) - [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015) - [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018) - [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019) - [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019) - [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015) - [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016) - [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018) - [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020) - [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020) - [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014) - [Formal Limitations on the Measurement of Mutual Information](https://mlsanity.com/paper/1811.04251/) (2018) - [Input complexity and out-of-distribution detection with likelihood-based generative models](https://mlsanity.com/paper/1909.11480/) (2019) - [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017) - [Learning Discrete Representations via Information Maximizing Self-Augmented Training](https://mlsanity.com/paper/1702.08720/) (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) - [Learning Open Set Network with Discriminative Reciprocal Points](https://mlsanity.com/paper/2011.00178/) (2020) - [Hybrid Models for Open Set Recognition](https://mlsanity.com/paper/2003.12506/) (2020) - [Boundary-Aware Feature Propagation for Scene Segmentation](https://mlsanity.com/paper/1909.00179/) (2019) - [Conditional Gaussian Distribution Learning for Open Set Recognition](https://mlsanity.com/paper/2003.08823/) (2020) - [Semantic Correlation Promoted Shape-Variant Context for Segmentation](https://mlsanity.com/paper/1909.02651/) (2019) - [Sparse Representation-based Open Set Recognition](https://mlsanity.com/paper/1705.02431/) (2017) ## Built on by (most cited first, 12 of 12) - [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021) - [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023) - [Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning](https://mlsanity.com/paper/2109.05749/) (2021) - [Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2210.16829/) (2022) - [A Survey on Open-Set Image Recognition](https://mlsanity.com/paper/2312.15571/) (2023) - [Few-shot Open-set Recognition Using Background as Unknowns](https://mlsanity.com/paper/2207.09059/) (2022) - [Spatial Feature Mapping for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2206.01831/) (2022) - [M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios](https://mlsanity.com/paper/2303.05122/) (2023) - [A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution](https://mlsanity.com/paper/2305.05079/) (2023) - [Calibrating Class Activation Maps for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2108.12757/) (2021) - [OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning](https://mlsanity.com/paper/2310.03848/) (2023) - [Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Direction](https://mlsanity.com/paper/2510.15422/) (2025) ## Abstract (arXiv) In this work, we aim to address the challenging task of open set recognition (OSR). Many recent OSR methods rely on auto-encoders to extract class-specific features by a reconstruction strategy, requiring the network to restore the input image on pixel-level. This strategy is commonly over-demanding for OSR since class-specific features are generally contained in target objects, not in all pixels. To address this shortcoming, here we discard the pixel-level reconstruction strategy and pay more attention to improving the effectiveness of class-specific feature extraction. We propose a mutual information-based method with a streamlined architecture, Maximal Mutual Information Open Set Recognition (M2IOSR). The proposed M2IOSR only uses an encoder to extract class-specific features by maximizing the mutual information between the given input and its latent features across multiple scales. Meanwhile, to further reduce the open space risk, latent features are constrained to class conditional Gaussian distributions by a KL-divergence loss function. In this way, a strong function is learned to prevent the network from mapping different observations to similar latent features and help the network extract class-specific features with desired statistical characteristics. The proposed method significantly improves the performance of baselines and achieves new state-of-the-art results on several benchmarks consistently.