Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Belal, Atif, Meethal, Akhil, Romero, Francisco Perdigon, Pedersoli, Marco, Granger, Eric
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.09918
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916519039991808
author Belal, Atif
Meethal, Akhil
Romero, Francisco Perdigon
Pedersoli, Marco
Granger, Eric
author_facet Belal, Atif
Meethal, Akhil
Romero, Francisco Perdigon
Pedersoli, Marco
Granger, Eric
contents Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modality information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation caused by noisy pseudo-labels that can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment method for MSDA, designed to align instances of each object category across domains. In particular, an attention module combined with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms state-of-the-art methods and exhibits robustness to class imbalance, achieved through a conceptually simple class-conditioning strategy. Our code is available at: https://github.com/imatif17/ACIA.
format Preprint
id arxiv_https___arxiv_org_abs_2403_09918
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
Belal, Atif
Meethal, Akhil
Romero, Francisco Perdigon
Pedersoli, Marco
Granger, Eric
Computer Vision and Pattern Recognition
Machine Learning
Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modality information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation caused by noisy pseudo-labels that can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment method for MSDA, designed to align instances of each object category across domains. In particular, an attention module combined with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms state-of-the-art methods and exhibits robustness to class imbalance, achieved through a conceptually simple class-conditioning strategy. Our code is available at: https://github.com/imatif17/ACIA.
title Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.09918