Salvato in:
Dettagli Bibliografici
Autori principali: Cao, Haozhi, Xu, Yuecong, Yin, Pengyu, Ji, Xingyu, Yuan, Shenghai, Yang, Jianfei, Xie, Lihua
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.06461
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915532831195136
author Cao, Haozhi
Xu, Yuecong
Yin, Pengyu
Ji, Xingyu
Yuan, Shenghai
Yang, Jianfei
Xie, Lihua
author_facet Cao, Haozhi
Xu, Yuecong
Yin, Pengyu
Ji, Xingyu
Yuan, Shenghai
Yang, Jianfei
Xie, Lihua
contents Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. While previous MM-TTA methods for 3D segmentation offer a promising solution by leveraging self-refinement per frame, they suffer from two major limitations: 1) unstable frame-wise predictions caused by temporal inconsistency, and 2) consistently incorrect predictions that violate the assumption of reliable modality guidance. To address these limitations, this work introduces a comprehensive two-fold framework. Firstly, building upon our previous work ReLiable Spatial-temporal Voxels (Latte), we propose Latte++ that better suppresses the unstable frame-wise predictions with more informative geometric correspondences. Instead of utilizing a universal sliding window, Latte++ employs multi-window aggregation to capture more reliable correspondences to better evaluate the local prediction consistency of different semantic categories. Secondly, to tackle the consistently incorrect predictions, we propose Interactive Test-Time Adaptation (ITTA), a flexible add-on to empower effortless human feedback with existing MM-TTA methods. ITTA introduces a novel human-in-the-loop approach that efficiently integrates minimal human feedback through interactive segmentation, requiring only simple point clicks and bounding box annotations. Instead of using independent interactive networks, ITTA employs a lightweight promptable branch with a momentum gradient module to capture and reuse knowledge from scarce human feedback during online inference. Extensive experiments across five MM-TTA benchmarks demonstrate that ITTA achieves consistent and notable improvements with robust performance gains for target classes of interest in challenging imbalanced scenarios, while Latte++ provides complementary benefits for temporal stability.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06461
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interactive Test-Time Adaptation with Reliable Spatial-Temporal Voxels for Multi-Modal Segmentation
Cao, Haozhi
Xu, Yuecong
Yin, Pengyu
Ji, Xingyu
Yuan, Shenghai
Yang, Jianfei
Xie, Lihua
Computer Vision and Pattern Recognition
Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. While previous MM-TTA methods for 3D segmentation offer a promising solution by leveraging self-refinement per frame, they suffer from two major limitations: 1) unstable frame-wise predictions caused by temporal inconsistency, and 2) consistently incorrect predictions that violate the assumption of reliable modality guidance. To address these limitations, this work introduces a comprehensive two-fold framework. Firstly, building upon our previous work ReLiable Spatial-temporal Voxels (Latte), we propose Latte++ that better suppresses the unstable frame-wise predictions with more informative geometric correspondences. Instead of utilizing a universal sliding window, Latte++ employs multi-window aggregation to capture more reliable correspondences to better evaluate the local prediction consistency of different semantic categories. Secondly, to tackle the consistently incorrect predictions, we propose Interactive Test-Time Adaptation (ITTA), a flexible add-on to empower effortless human feedback with existing MM-TTA methods. ITTA introduces a novel human-in-the-loop approach that efficiently integrates minimal human feedback through interactive segmentation, requiring only simple point clicks and bounding box annotations. Instead of using independent interactive networks, ITTA employs a lightweight promptable branch with a momentum gradient module to capture and reuse knowledge from scarce human feedback during online inference. Extensive experiments across five MM-TTA benchmarks demonstrate that ITTA achieves consistent and notable improvements with robust performance gains for target classes of interest in challenging imbalanced scenarios, while Latte++ provides complementary benefits for temporal stability.
title Interactive Test-Time Adaptation with Reliable Spatial-Temporal Voxels for Multi-Modal Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.06461