A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning (2020-08-09T00:00:00.000000Z)

TL;DR

This paper proposes a boundary based Out-of-Distribution (OOD) classifier which classifies the unseen and seen domains by only using seen samples for training and extensively validate the approach on five popular benchmark datasets including AWA1, AWA2, CUB, FLO and SUN.

Abstract

Generalized Zero-Shot Learning (GZSL) is a challenging topic that has promising prospects in many realistic scenarios. Using a gating mechanism that discriminates the unseen samples from the seen samples can decompose the GZSL problem to a conventional Zero-Shot Learning (ZSL) problem and a supervised classification problem. However, training the gate is usually challenging due to the lack of data in the unseen domain. To resolve this problem, in this paper, we propose a boundary based Out-of-Distribution (OOD) classifier which classifies the unseen and seen domains by only using seen samples for training. First, we learn a shared latent space on a unit hyper-sphere where the latent distributions of visual features and semantic attributes are aligned class-wisely. Then we find the boundary and the center of the manifold for each class. By leveraging the class centers and boundaries, the unseen samples can be separated from the seen samples. After that, we use two experts to classify the seen and unseen samples separately. We extensively validate our approach on five popular benchmark datasets including AWA1, AWA2, CUB, FLO and SUN. The experimental results show that our approach surpasses state-of-the-art approaches by a significant margin.

Authors

Xuguang Lan

3 papers

Nanning Zheng

3 papers

Xingyu Chen

1 papers

TL;DR

Abstract

Authors

References37 items

A Joint Label Space for Generalized Zero-Shot Classification

Alleviating Feature Confusion for Generative Zero-shot Learning

Co-Representation Network for Generalized Zero-Shot Learning

F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning

Adaptive Confidence Smoothing for Generalized Zero-Shot Learning

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders

Multi-modal Cycle-consistent Generalized Zero-Shot Learning

Zero Shot Learning via Low-rank Embedded Semantic AutoEncoder

Hyperspherical Variational Auto-Encoders

Preserving Semantic Relations for Zero-Shot Learning

Zero-Shot Kernel Learning

Generalized Zero-Shot Learning via Synthesized Examples

Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks

Feature Generating Networks for Zero-Shot Learning

A Generative Model for Zero Shot Learning Using Conditional Variational Autoencoders

Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly

Matrix Tri-Factorization with Manifold Regularizations for Zero-Shot Learning

From Zero-Shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis

Semantic Autoencoder for Zero-Shot Learning

Learning Robust Visual-Semantic Embeddings

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

Learning Deep Representations of Fine-Grained Visual Descriptions

Synthesized Classifiers for Zero-Shot Learning

Zero-Shot Learning via Semantic Similarity Embedding

An embarrassingly simple approach to zero-shot learning

Label-Embedding for Image Classification

Evaluation of output embeddings for fine-grained image classification

Generative Adversarial Nets

The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding

Auto-Encoding Variational Bayes

DeViSE: A Deep Visual-Semantic Embedding Model

Distributed Representations of Words and Phrases and their Compositionality

Sinkhorn Distances: Lightspeed Computation of Optimal Transport

Zero-Shot Learning Through Cross-Modal Transfer

The Caltech-UCSD Birds-200-2011 Dataset

Automated Flower Classification over a Large Number of Classes

Attribute-Based Classification for Zero-Shot Visual Object Categorization

Field of Study

Venue Information

Name

Type

URL

Alternate Names