Recent Advances in Zero-shot Recognition

Abstract

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samples for each class remains an unsolved problem. One approach to scaling up the recognition is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/ learning. This article provides a comprehensive review of existing zero-shot recognition techniques covering various aspects ranging from representations of models, and from datasets and evaluation settings. We also overview related recognition tasks including one-shot and open set recognition which can be used as natural extensions of zero-shot recognition when limited number of class samples become available or when zero-shot recognition is implemented in a real-world setting. Importantly, we highlight the limitations of existing approaches and point out future research directions in this existing new research area.

accepted by IEEE Signal Processing Magazine

References in corpus (10)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
• Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
• A PAC-Bayesian bound for Lifelong Learning
• Inverse Graphics with Probabilistic CAD Models
• VideoStory Embeddings Recognize Events when Examples are Scarce
• Transductive Zero-Shot Action Recognition by Word-Vector Embedding

Cited by in corpus (14)

• Recent Advances in Open Set Recognition: A Survey
• AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
• Zero-Shot Detection
• RarePlanes: Synthetic Data Takes Flight
• Mix and match networks: encoder-decoder alignment for zero-pair image translation
• Adaptive Confidence Smoothing for Generalized Zero-Shot Learning
• Mix and match networks: cross-modal alignment for zero-pair image-to-image translation
• Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification
• Zero-Shot Audio Classification Based on Class Label Embeddings
• Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks
• Latent Cognizance: What Machine Really Learns
• Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition
• Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling
• Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning