A multi camera unsupervised domain adaptation pipeline for object detection in cultural sites through adversarial learning and self-training (2022-06-01T00:00:00.000000Z)

TL;DR

A new domain adaptation method which outperforms current state-of-the-art approaches combining the beneﬁts of aligning the domains at the feature and pixel level with a self-training process is presented.

Authors

Antonino Furnari

18 papers

G. Farinella

19 papers

Giovanni Pasqualino

2 papers

TL;DR

Authors

References36 items

Attention-based domain adaptation for single-stage detectors

Generative and self-supervised domain adaptation for one-stage object detection

Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation

I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors

MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection

Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites

Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation

Egocentric visitor localization and artwork detection in cultural sites using synthetic data

EGO-CH: Dataset and Fundamental Tasks for Visitors BehavioralUnderstanding using Egocentric Vision

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

Progressive Domain Adaptation for Object Detection

VEDI: Vision Exploitation for Data Interpretation

Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection

Multi-Level Domain Adaptive Learning for Cross-Domain Detection

Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

Strong-Weak Distribution Alignment for Adaptive Object Detection

Moment Matching for Multi-Source Domain Adaptation

Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach

Domain Adaptive Faster R-CNN for Object Detection in the Wild

Fully Convolutional Network and Region Proposal for Instance Identification with Egocentric Vision

Focal Loss for Dense Object Detection

Deep Artwork Detection and Retrieval for Automatic Context-Aware Audio Guides

Adversarial Discriminative Domain Adaptation

Correlation Alignment for Unsupervised Domain Adaptation

Beyond Sharing Weights for Deep Domain Adaptation

Deep Residual Learning for Image Recognition

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Unsupervised Domain Adaptation by Backpropagation

Visions for Augmented Cultural Heritage Experience

ImageNet: A large-scale hierarchical image database

A Kernel Method for the Two-Sample-Problem

Adversarial Multiple-Target Domain Adaptation for Fault Classification

GENERATIVE ADVERSARIAL NETS

Adversarial Multiple Source Domain Adaptation

Unpaired image-to-image translation using cycle-consistent adversarial networks

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names