Article

Unsupervised Few-shot Object Recognition by Self-Supervised Training

2022-09-07

Abstract excerpt

<title>Abstract</title> <p>Humans can easily spot people, objects, scenes, and visual details in photographs and videos. The main goal is to make a computer capable of what humans can do with learning a level of understanding of actual image/video content. Object recognition is one of the computer vision techniques for identifying objects in images or videos, and it is a key learning point. The proposed research...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 0b4418da-5d28-541a-9b10-f52ed31272a1
DOI: 10.21203/rs.3.rs-1573937/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Unsupervised Few-shot Object Recognition by Self-Supervised TrainingDOI 10.21203/rs.3.rs-1573937/v1Read

Abstracted Gaussian Prototypes for One-Shot Concept LearningSemantic proximity Read

Contextual Feature Expansion with Superordinate Concept for Compositional Zero-Shot LearningSemantic proximity Read

A self-supervised domain-general learning framework for human ventral stream representationSemantic proximity Read

One Shot Cluster Based Approach for the Detection of COVID-19 from Chest X-Ray ImagesSemantic proximity Read

Detecting and Learning from Unknown by Extremely Weak Supervision: eXploratory Classifier (xClass)Semantic proximity Read

Transfer Learning Model forAnomalous Event Recognition in Big Video DataSemantic proximity Read

DiscoverNet: Unsupervised Video Object Discovery through Discrete Visual Tokenization and Language Model-Inspired ReconstructionSemantic proximity Read

Attention Inspiring Receptive-Fields Multi-Task Network via Self- supervised Learning for Violence RecognitionSemantic proximity Read

Optimised ARG based Group Activity Recognition for Video UnderstandingSemantic proximity Read

A Two-Stream Deep Learning Approach for Enhanced Two-Person Human Interaction Recognition in VideosSemantic proximity Read

Towards Trustworthy Human Suspicious Activity Detection from Surveillance Videos Using Deep LearningSemantic proximity Read

Self-Supervised Learning Principles Challenges and Emerging DirectionsSemantic proximity Read