Self Supervised Paradigm

Self-supervised learning aims to train machine learning models on vast amounts of unlabeled data by leveraging inherent data structures and relationships, reducing reliance on expensive human annotation. Current research focuses on improving the robustness and efficiency of self-supervised methods, exploring techniques like contrastive learning, masked autoencoders, and the integration of foundation models for tasks such as depth estimation, pose estimation, and active learning initialization. These advancements are significant because they enable the development of more generalizable and data-efficient models across various computer vision applications, impacting fields ranging from medical image analysis to autonomous driving.

Papers

September 23, 2024

GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth
Aurélien Cecille, Stefan Duffner, Franck Davoine, Thibault Neveu, Rémi Agier
Monocular Depth Estimation Depth Prediction Geometric Constraint Metric Depth Self Supervised Paradigm

April 3, 2024

A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
Jie Zhu, Jirong Zha, Ding Li, Leye Wang
Self Supervised Learning Self Supervised Self Supervised Model Membership Inference Part Aware Self Supervised Paradigm

February 4, 2024

Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning
Han Yuan, Chuan Hong
Foundation Model Active Learning Self Supervised Paradigm Better Initialization Start Active Learning

November 16, 2023

From Pretext to Purpose: Batch-Adaptive Self-Supervised Learning
Jiansong Zhang, Linlin Shen, Peizhong Liu
Contrastive Learning Self Supervised Contrastive Learning Self Supervised Learning Method Pretext Task Self Supervised Paradigm

November 6, 2023

Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning
Nobline Yoo, Olga Russakovsky
Self Supervised High Efficiency Self Supervised Method 2 Dimensional Human Pose Estimation Self Supervised Paradigm Inductive Prior

August 21, 2023

Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Data
Patrick Ruhkamp, Daoyi Gao, HyunJun Jung, Nassir Navab, Benjamin Busam
Pose Estimation Limited Data Shape Prior Object Pose Estimation RGB D Data Photometric Broad Band Image Self Supervised Paradigm Polarization Information

July 31, 2023

Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?
Prakash Chandra Chhipa, Johan Rodahl Holmgren, Kanjar De, Rajkumar Saini, Marcus Liwicki
Self Supervised Learning Self Supervised Self Supervised Representation Learning Self Supervised Learning Method Self Supervised Representation Corruption Level Self Supervised Paradigm

May 19, 2023

SurgMAE: Masked Autoencoders for Long Surgical Video Analysis
Muhammad Abdullah Jamal, Omid Mohareri
Supervised Autoencoder Masked Autoencoders Surgical Video Self Supervised Paradigm

February 1, 2023

Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms
Shihan Ma, Jidong J. Yang
Self Supervised Feature Wise Self Supervised Learning Method Vehicle Image Self Supervised Paradigm Vehicle Type Classification

March 14, 2022

Physical Neural Cellular Automata for 2D Shape Classification
Kathryn Walker, Rasmus Berg Palm, Rodrigo Moreno Garcia, Andres Faina, Kasper Stoy, Sebastian Risi
Neural Cellular Automaton Modular Robot Self Reconfiguration Self Supervised Paradigm Shape Classification

December 15, 2021

Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration
Yu Wang, Jingyang Lin, Jingjing Zou, Yingwei Pan, Ting Yao, Tao Mei
Self Supervised Learning Self Supervised Learning Method Self Supervised Framework Unsupervised Outlier Detection Self Supervised Paradigm

November 3, 2021

Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
Mrinal Anand, Aditya Garg
Supervised Learning Recent Advance Self Supervision Feature Representation Self Supervised Method Self Supervised Paradigm

Self Supervised Paradigm

Papers

GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth

A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability

Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning

From Pretext to Purpose: Batch-Adaptive Self-Supervised Learning

Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning

Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Data

Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?

SurgMAE: Masked Autoencoders for Long Surgical Video Analysis

Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms

Physical Neural Cellular Automata for 2D Shape Classification

Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration

Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation