GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → fnbalves → zero_shot_learning

fnbalves / zero_shot_learning

Licence: other
A Visual-semantic embedding model using word2vec and CNNs

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningconvolutional-neural-networkszero-shot-learning

Projects that are alternatives of or similar to zero shot learning

Zero-shot-Fact-Verification
Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"
Stars: ✭ 39 (+200%)
Mutual labels:  zero-shot-learning
ZS SDL
Official Pytorch Implementation of: "Semantic Diversity Learning for Zero-Shot Multi-label Classification"(ICCV, 2021) paper
Stars: ✭ 22 (+69.23%)
Mutual labels:  zero-shot-learning
few shot dialogue generation
Dialogue Knowledge Transfer Networks (DiKTNet)
Stars: ✭ 24 (+84.62%)
Mutual labels:  zero-shot-learning
Awesome-Weak-Shot-Learning
A curated list of papers, code and resources pertaining to weak-shot classification, detection, and segmentation.
Stars: ✭ 142 (+992.31%)
Mutual labels:  zero-shot-learning
domain-adaptation-capls
Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
Stars: ✭ 43 (+230.77%)
Mutual labels:  zero-shot-learning
Awesome Domain Adaptation
A collection of AWESOME things about domian adaptation
Stars: ✭ 3,357 (+25723.08%)
Mutual labels:  zero-shot-learning
synse-zsl
Official PyTorch code for the ICIP 2021 paper 'Syntactically Guided Generative Embeddings For Zero Shot Skeleton Action Recognition'
Stars: ✭ 14 (+7.69%)
Mutual labels:  zero-shot-learning
tfvaegan
[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL
Stars: ✭ 107 (+723.08%)
Mutual labels:  zero-shot-learning
hierse
Zero-shot image tagging by hierarchical semantic embedding
Stars: ✭ 77 (+492.31%)
Mutual labels:  zero-shot-learning
CE-GZSL
Codes for the CVPR 2021 paper: Contrastive Embedding for Generalized Zero-Shot Learning
Stars: ✭ 73 (+461.54%)
Mutual labels:  zero-shot-learning
FREE
Codes for the ICCV'21 paper "FREE: Feature Refinement for Generalized Zero-Shot Learning"
Stars: ✭ 28 (+115.38%)
Mutual labels:  zero-shot-learning
Awesome-Zero-Shot-Object-Detection
No description or website provided.
Stars: ✭ 89 (+584.62%)
Mutual labels:  zero-shot-learning
class-norm
Class Normalization for Continual Zero-Shot Learning
Stars: ✭ 34 (+161.54%)
Mutual labels:  zero-shot-learning
deep-eos
General-Purpose Neural Networks for Sentence Boundary Detection
Stars: ✭ 66 (+407.69%)
Mutual labels:  zero-shot-learning
Zero-Shot-Learning
A python ZSL system which makes it easy to run Zero-Shot Learning on new datasets, by giving it features and attributes. Used for the paper "Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features", published in ICFHR2018.
Stars: ✭ 21 (+61.54%)
Mutual labels:  zero-shot-learning
Feature-Generating-Networks
Zero Shot Learning with Feature Generating Networks
Stars: ✭ 31 (+138.46%)
Mutual labels:  zero-shot-learning
adapt
Awesome Domain Adaptation Python Toolbox
Stars: ✭ 46 (+253.85%)
Mutual labels:  zero-shot-learning
gzsl-od
Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
Stars: ✭ 47 (+261.54%)
Mutual labels:  zero-shot-learning
Zero-Shot-TTS
Unofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Stars: ✭ 33 (+153.85%)
Mutual labels:  zero-shot-learning
good robot
"Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer
Stars: ✭ 84 (+546.15%)
Mutual labels:  zero-shot-learning
View All Similar Projects ➔

This project's objective is to reproduce the results from

https://static.googleusercontent.com/media/research.google.com/pt-BR//pubs/archive/41473.pdf

However, we use a smaller dataset (CIFAR-100) with lower resolution images. In order to do so, new cost functions needed to be created.

To use this code

  1. Get CIFAR-10 and CIFAR-100 from:

https://www.cs.toronto.edu/~kriz/cifar.html

Put cifar-100 test, train and meta files inside a folder called cifar-100-python/ (read_cifar100 conde uses them)

  1. Download the glove model from

http://nlp.stanford.edu/data/glove.6B.zip

And extract the files into a folder called glove.6B

  1. Install python dependencies by using pip and the requirements.txt file:

sudo pip install requirements.txt

  1. Create a folder called pickle files and run read_cifar100 to create all datasets

  2. To train the composite model, run the train_composite file

  3. To visualize the TSNE plots, run the visualize_results file (Change the indicated vars on the code)

  4. To compute quantitative results, run the compute_quantitative_results file and use the functions (Change the indicated vars on the code)

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].