GitHub

Cut and Learn for Unsupervised Image & Video Object Detection and Instance Segmentation

We propose MaskCut approach to generate pseudo-masks for multiple objects in an image. CutLER can learn unsupervised object detectors and instance segmentors solely on ImageNet-1K. CutLER exhibits ...
GitHub

Rotated Mask R-CNN

Due to bounding box ambiguity, Mask R-CNN fails in relatively dense scenes with objects of the same class, particularly if those objects have high bounding box overlap. In these scenes, both recall ...
Scientific Research Publishing

A Multi-Modal Approach for Arabic Sign Language Gesture Recognition Using Deep Learning ()

This paper proposes a multi-modal deep learning framework for Arabic Sign Language (ArSL) recognition, addressing the challenges of both static and dynamic gesture recognition. The framework ...
Frontiers

Contrastive self-supervised learning for neurodegenerative disorder classification

Neurodegenerative diseases such as Alzheimer's disease (AD) or frontotemporal lobar degeneration (FTLD) involve specific loss of brain volume, detectable in vivo using T1-weighted MRI scans.
Frontiers

End-to-end 3D instance segmentation of synthetic data and embryo microscopy images with a 3D Mask R-CNN

In recent years, the exploitation of three-dimensional (3D) data in deep learning has gained momentum despite its inherent challenges. The necessity of 3D approaches arises from the limitations of two ...
Analytics Insight

How to Build AI Models with TensorFlow

TensorFlow has emerged as one of the most popular frameworks for building machine learning models. Whether you are a beginner or an experienced data scientist, understanding how to build AI models ...
C&EN

Fault Diagnosis of the Dynamic Chemical Process Based on the Optimized CNN-LSTM Network

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Deep learning provides new ideas for chemical process fault diagnosis, reducing ...