Generalized Zero-Shot Learning via Synthesized Examples

By Gundeep Arora, Vinay Kumar Verma, Ashish Mishra, Piyush Rai. 2017

488 citations recorded by the source corpus.

We present a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a probabilistic conditional decoder, our model can generate novel exemplars from seen/unseen classes, given their respective class attributes. These exemplars can subsequently be used to train any off-the-shelf classification model. One of the key aspects of our encoder-decoder architecture is a feedback-driven mechanism in which a discriminator (a multivariate regressor) learns to map the generated exemplars to the corresponding class attribute vectors, leading to an improved generator. Our model's ability to generate and leverage examples from unseen classes to train the classification model naturally helps to mitigate the bias towards predicting seen classes in generalized zero-shot learning settings. Through a comprehensive set of experiments, we show that our model outperforms several state-of-the-art methods, on several benchmark datasets, for both standard as well as generalized zero-shot learning.

Subfields: Artificial Intelligence, Cancer Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cancer Research

Citations in the corpus

PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, background): “Further works should investigate how to exploit the already present future information with Zeroshot [42, 41] as already done in semantic segmentation [36, 5] and explored for continual classification [72, 19].”
Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders (2018, methodology): “After individual VAEs learn to encode features of only their specific datatype for some epochs, we also start to compute cross- and distribution alignment losses. δ is increased from epoch 6 to epoch 22 by a rate of 0.54 per epoch, while γ is increased from epoch 21 to 75 by 0.044 per epoch.”
Learning Transferable Knowledge Through Embedding Spaces (2019, background): “For this reason, recently, a new learning setting has been suggested to generalize ZSL, call generalized zero-shot learning (GZSL) [81; 263].”
Small Sample Learning in Big Data Era (2018, methodology): “Similarly, Arora et al. (2018) proposed a method able to generate semantically rich CNN feature distributions via the conditional VAE with discriminator-driven feedback mechanism improving the reconstruction capability.”
F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning (2019, methodology): “Among those, [5] uses GMMN [33], [63, 58] use GANs[17] and [28] em-”
Don’t Even Look Once: Synthesizing Features for Zero-Shot Detection (2019, background): “Motivated by these concerns, recent works have proposed to synthesize unseen examples by means of generative models such as autoencoders [4, 19], GANs and adversarial methods [49, 20, 42, 16, 23, 36] that take semantic vectors as input, and output images.”
A Survey of Zero-Shot Learning (2019, background): “The generative moment matching network (GMMN) [11], denoising autoencoder [11], adversarial autoencoder [11], conditional variational autoencoder-based architecture [141], and generative adversarial networks (GANs) [11, 156, 179] are examples.”
Zero-Shot Semantic Segmentation (2019, background): “Recently, [7, 25, 45] proposed to generate synthetic instances of unseen classes by training a conditional generator from the seen classes.”
Generalized Zero-Shot Learning with Deep Calibration Network (2018, background): “[31] explored approaches that synthesize images for unseen classes using GANs [22] or VAE [26].”
Insights from the Future for Continual Learning (2020, background): “Although several approaches exist for zero-shot learning, we will focus on generating a representation for the future classes [3, 22, 39].”
Attribute Prototype Network for Zero-Shot Learning (2020, background): “Recent advances in zero-shot learning mainly focus on learning better visual-semantic embeddings [26, 50, 17, 5] or training generative models to synthesize features [44, 45, 57, 56, 19, 33].”
Zero Shot Detection (2018, background): “There already exists various efforts to bridge such a gap, e.g. [47]– [49].”
Classifier and Exemplar Synthesis for Zero-Shot Learning (2018, methodology): “est in exploiting them for generating labeled data from corresponding semantic representations. Once those examples are generated, one can employ any supervised learning technique to learn classiﬁers [36,90,77,7]. Note that all these methods focus on directly generating features rather than image pi”
Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration (2019, unknown): “Some of these methods include [24], [25].”
A Meta-Learning Framework for Generalized Zero-Shot Learning (2019, methodology): “This setting is popularly known as Zero-Shot Learning (ZSL), and has drawn a considerable interest recently [44, 32, 47, 5, 38, 53, 46, 27, 39, 7, 29, 4, 33, 10, 62, 41, 23].”
Leveraging the Invariant Side of Generative Zero-Shot Learning (2019, background): “To summarize, the main contributions of this paper are: 1) We propose a novel ZSL method LisGAN which takes advantage of generative adversarial networks.”
Adaptive and Generative Zero-Shot Learning (2021, background): “Generative approaches (Chen et al., 2018; Felix et al., 2018; Kumar Verma et al., 2018; Mishra et al., 2018; Schonfeld et al., 2019; Paul et al., 2019; Xian et al., 2019) tackle the problem by synthesizing visual features of unseen classes from their semantic features with generative models like…”