This repository contains implementations of 5 classical zero-shot algorithms in the usual as well as the generalized zero-shot settings using the Proposed Split and evaluation protocols outlined in Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly (ZSLGBU) by Yongqin Xian, Christoph H. Lampert, Bernt Schiele, Zeynep Akata (TPAMI 2018).

The original papers corressponding to the 5 algorithms are:

• [1] SAE - Semantic Autoencoder for Zero-Shot Learning. Elyor Kodirov, Tao Xiang, Shaogang Gong. CVPR, 2017.

• [2] ALE - Label-Embedding for Image Classification. Zeynep Akata, Florent Perronnin, Zaid Harchaoui, Cordelia Schmid. PAMI, 2016.

• [3] SJE - Evaluation of Output Embeddings for Fine-Grained Image Classification. Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, Bernt Schiele. CVPR, 2015.

• [4] ESZSL - An embarrassingly simple approach to zero-shot learning. Bernardino Romera-Paredes, Philip H. S. Torr. ICML, 2015.

• [5] DeViSE - DeViSE: A Deep Visual-Semantic Embedding Model. Andrea Frome*, Greg S. Corrado*, Jonathon Shlens*, Samy Bengio, Jeffrey Dean, Marc’Aurelio Ranzato, Tomas Mikolov. NIPS, 2013.

To the best of my knowledge, this is the first public implementation of SAE, ALE, SJE and DeViSE under the ZSLGBU protocol. An existing implementation of ESZSL can be found here. To this, I have also added the generalized ZSL functionality.

Each code folder has its own README with running instructions, results and their comparisons with those found in the ZSLGBU paper.

git clone https://github.com/mvp18/Popular-ZSL-Algorithms.git
cd Popular-ZSL-Algorithms
bash setup.sh

This downloads data corressponding to the Proposed Split for AWA1, AWA2, CUB, SUN and aPY.