Multi-task self-supervised visual learning

Multi-task self-supervised visual learning

We investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling-in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very dee...

Podrobná bibliografie
Hlavní autoři:	Doersch, C, Zisserman, A
Médium:	Conference item
Vydáno:	IEEE Explore 2017

Podobné jednotky

Self-supervised learning of audio-visual objects from video
Autor: Afouras, T, a další
Vydáno: (2020)

Multi-Task Collaborative Network: Bridge the Supervised and Self-Supervised Learning for EEG Classification in RSVP Tasks
Autor: Hongxin Li, a další
Vydáno: (2024-01-01)

Sim2real transfer learning for 3D human pose estimation: motion to the rescue
Autor: Doersch, C, a další
Vydáno: (2020)

Self-supervised learning for spinal MRIs
Autor: Jamaludin, A, a další
Vydáno: (2017)

Self-supervised multi-task representation learning for sequential medical images
Autor: Dong, N, a další
Vydáno: (2021)

Multi-task multi-sample learning
Autor: Aytar, Y, a další
Vydáno: (2015)

Self-supervised co-training for video representation learning
Autor: Han, T, a další
Vydáno: (2020)

Weakly supervised scale-invariant learning of models for visual recognition
Autor: Fergus, R, a další
Vydáno: (2006)

Mixup Feature: A Pretext Task Self-Supervised Learning Method for Enhanced Visual Feature Learning
Autor: Jiashu Xu, a další
Vydáno: (2023-01-01)

Self-supervised learning of class embeddings from video
Autor: Wiles, O, a další
Vydáno: (2020)

A Self-Supervised Learning Solution With Momentum-Based Siamese Network for Robotic Visual Task
Autor: Yuehong Huang, a další
Vydáno: (2023-01-01)

Self-Supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning
Autor: Tianshu Xie, a další
Vydáno: (2023-01-01)

Separating the “chirp” from the “chat”: self-supervised visual grounding of sound and language
Autor: Hamilton, M, a další
Vydáno: (2024)

Self-supervised multi-modal alignment for whole body medical imaging
Autor: Windsor, R, a další
Vydáno: (2021)

Self-supervised multi-task learning framework for safety and health-oriented road environment surveillance based on connected vehicle visual perception
Autor: Shaocheng Jia, a další
Vydáno: (2024-04-01)

Multi-Task Simultaneous Supervision
Autor: Afifah Rizka, a další
Vydáno: (2024-08-01)

Multiple Self-Supervised Auxiliary Tasks for Target-Driven Visual Navigation Using Deep Reinforcement Learning
Autor: Wenzhi Zhang, a další
Vydáno: (2023-06-01)

Self-supervised learning of a facial attribute embedding from video
Autor: Wiles, O, a další
Vydáno: (2018)

EMS2L: Enhanced Multi-Task Self-Supervised Learning for 3D Skeleton Representation Learning
Autor: Lilang Lin, a další
Vydáno: (2023-01-01)

Exploiting temporal context for 3D human pose estimation in the wild
Autor: Arnab, A, a další
Vydáno: (2020)

Multi-Tasking for Aspect-Based Sentiment Analysis via Constructing Auxiliary Self-Supervision ACOP Task
Autor: Zhaozhen Wu, a další
Vydáno: (2023-01-01)

Self-supervised learning of structural representations of visual objects
Autor: Jakab, T
Vydáno: (2021)

ProteinGLUE multi-task benchmark suite for self-supervised protein modeling
Autor: Henriette Capel, a další
Vydáno: (2022-09-01)

Survey on Self-Supervised Learning: Auxiliary Pretext Tasks and Contrastive Learning Methods in Imaging
Autor: Saleh Albelwi
Vydáno: (2022-04-01)

Comparing Learning Methodologies for Self-Supervised Audio-Visual Representation Learning
Autor: Hacene Terbouche, a další
Vydáno: (2022-01-01)

Dysarthric Speech Recognition Using Pseudo-Labeling, Self-Supervised Feature Learning, and a Joint Multi-Task Learning Approach
Autor: Ryoichi Takashima, a další
Vydáno: (2024-01-01)

Self-Supervised Visual Representation Learning via Residual Momentum
Autor: Trung Xuan Pham, a další
Vydáno: (2023-01-01)

Self-supervised learning using motion and visualizing convolutional neural networks
Autor: Mahendran, A
Vydáno: (2018)

Semi-Supervised Learning for Multi-View Data Classification and Visualization
Autor: Najmeh Ziraki, a další
Vydáno: (2024-07-01)

A Self-Supervised Few-Shot Semantic Segmentation Method Based on Multi-Task Learning and Dense Attention Computation
Autor: Kai Yi , a další
Vydáno: (2024-07-01)

Semi-supervised Histopathological Image Segmentation Method Based on Multi-task Learning
Autor: ZENG Li, a další
Vydáno: (2023-03-01)

Self-supervised video object segmentation by motion grouping
Autor: Yang, C, a další
Vydáno: (2021)

Self-supervised and supervised contrastive learning
Autor: Tan, Alvin De Jun
Vydáno: (2023)

Of gods and goats: weakly supervised learning of figurative art
Autor: Crowley, E, a další
Vydáno: (2013)

Mining visual collocation patterns via self-supervised subspace learning
Autor: Yuan, Junsong, a další
Vydáno: (2013)

GAN-Based Image Colorization for Self-Supervised Visual Feature Learning
Autor: Sandra Treneska, a další
Vydáno: (2022-02-01)

Self-Supervised Learning for Audio-Visual Relationships of Videos With Stereo Sounds
Autor: Tomoya Sato, a další
Vydáno: (2022-01-01)

Surgical Gesture Recognition in Laparoscopic Tasks Based on the Transformer Network and Self-Supervised Learning
Autor: Athanasios Gazis, a další
Vydáno: (2022-11-01)

PASS: An ImageNet replacement for self-supervised pretraining without humans
Autor: Asano, YM, a další
Vydáno: (2021)

Disentangled Speech Embeddings Using Cross-Modal Self-Supervision
Autor: Nagrani, A, a další
Vydáno: (2020)