Generalized Zero-Shot Learning Via Over-Complete Distribution

2020-04-01 · CVPR 2020 6 · Rohit Keshari, Richa Singh, Mayank Vatsa

A well trained and generalized deep neural network (DNN) should be robust to both seen and unseen classes. However, the performance of most of the existing supervised DNN algorithms degrade for classes which are unseen in the training set. To learn a discriminative classifier which yields good performance in Zero-Shot Learning (ZSL) settings, we propose to generate an Over-Complete Distribution (OCD) using Conditional Variational Autoencoder (CVAE) of both seen and unseen classes. In order to enforce the separability between classes and reduce the class scatter, we propose the use of Online Batch Triplet Loss (OBTL) and Center Loss (CL) on the generated OCD. The effectiveness of the framework is evaluated using both Zero-Shot Learning and Generalized Zero-Shot Learning protocols on three publicly available benchmark databases, SUN, CUB and AWA2. The results show that generating over-complete distributions and enforcing the classifier to learn a transform function from overlapping to non-overlapping distributions can improve the performance on both seen and unseen classes.

📄 PDF Abstract BibTeX arXiv:2004.00666

Code (1)

0shimax/Easy-Over-Complete-Distribution pytorch

Tasks

Generalized Zero-Shot LearningTripletZero-Shot Learning

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Solana Customer Service Number +1-833-534-1729 설명 없음

Model Selection for Generalized Zero-shot Learning

2018-11-08 · Hongguang Zhang, Piotr Koniusz

In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which mak…

Generalized Zero-Shot Learning Generative Adversarial Network model Model Selection+1

Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition

2019-04-18 · CVPR 2019 6 · Devraj Mandal, Sanath Narayan, Saikumar Dwivedi, Vikram Gupta 외

Generalized zero-shot action recognition is a challenging problem, where the task is to recognize new action categories that are unavailable during the training stage, in addition to the seen action categories. Existing …

Action Recognition Action Recognition In Videos Out-of-Distribution Detection Temporal Action Localization+1

Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition

2024-02-18 · Yijie Wang, Mingjian Hong, Luwen Huangfu, Sheng Huang

In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to-end generative GZSL framework called D$^3$GZSL. …

Generalized Zero-Shot Learning Zero-Shot Learning

RevCD -- Reversed Conditional Diffusion for Generalized Zero-Shot Learning

2024-08-31 · William Heyden, Habib Ullah, M. Salman Siddiqui, Fadi Al Machot

In Generalized Zero-Shot Learning (GZSL), we aim to recognize both seen and unseen categories using a model trained only on seen categories. In computer vision, this translates into a classification problem, where knowle…

Generalized Zero-Shot Learning Transfer Learning Zero-Shot Learning

Feature Generating Networks for Zero-Shot Learning

2017-12-04 · CVPR 2018 6 · Yongqin Xian, Tobias Lorenz, Bernt Schiele, Zeynep Akata

Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging generalized zero-shot learning tas…

Generalized Zero-Shot Learning Generative Adversarial Network Zero-Shot Learning