Keras implementation of "Densely Connected Convolutional Networks" applied to the Galaxy Zoo Kaggle competition.
-
Updated
Jan 15, 2018 - Jupyter Notebook
Keras implementation of "Densely Connected Convolutional Networks" applied to the Galaxy Zoo Kaggle competition.
Winning solution for the Kaggle TGS Salt Identification Challenge.
Creating datasets in YOLO format using pretrained YOLO model in Darknet framework which could be used to train the model further
Tensorflow based training, inference and feature engineering pipelines used in OSIC Kaggle Competition
ISWC2020 Semantic Web Challenge - Product Classification Top1 Solution
IFSS-Net: Interactive Few-Shot Siamese Network for Faster Muscle Segmentation and Propagation in Volumetric Ultrasound
Source code and data for the journal ``Dual learning for semi-supervised natural language understanding" in TASLP 2020.
Unofficial implementation of Adversarial Learning for Semi-Supervised Semantic Segmentation with tensorflow/Keras
Classify dashcam images to detect cases of distracted or safe driving.
Study project with experiments in Text MultiClassification Task Field (:
PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.
An Uncertainty-Aware Pseudo-Label Selection Framework using Regularized Conformal Prediction
Research paper-Enhancing action recognition with precondition and effect
Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
"Advanced Machine Learning" project @ Politecnico di Torino, a.y. 2021/2022.
Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training
Code and dataset for our paper "Anchored Model Transfer and Soft Instance Transfer for Cross-Task Cross-Domain Learning: A Study Through Aspect-Level Sentiment Classification", WWW2020
Labelling platform for text using weak supervision.
Semi-Supervised Hyperspectral Image Classification
[NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach'.
Add a description, image, and links to the pseudo-labeling topic page so that developers can more easily learn about it.
To associate your repository with the pseudo-labeling topic, visit your repo's landing page and select "manage topics."