DeepAI AI Chat
Log In Sign Up

M2IOSR: Maximal Mutual Information Open Set Recognition

by   Xin Sun, et al.
Nanyang Technological University

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.


Renormalized Mutual Information for Extraction of Continuous Features

We derive a well-defined renormalized version of mutual information that...

The Information Mutual Information Ratio for Counting Image Features and Their Matches

Feature extraction and description is an important topic of computer vis...

Learning deep representations by mutual information estimation and maximization

Many popular representation-learning algorithms use training objectives ...

Information-Bottleneck Approach to Salient Region Discovery

We propose a new method for learning image attention masks in a semi-sup...

Representation Learning for Sequence Data with Deep Autoencoding Predictive Components

We propose Deep Autoencoding Predictive Components (DAPC) – a self-super...

Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels

Although contrastive learning methods have shown prevailing performance ...

Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions

This work shows how to improve and interpret the commonly used dual enco...