Test-time adaptation (TTA) has been proven to effectively improve the adaptability of deep learning semantic segmentation models facing continuous changeable scenes. However, most of the existing TTA algorithms lack an explicit exploration of domain gaps, especially those based on visual dom...
没有用到混合域、在进行快慢模型更新的时候没用到源域数据 2022/12/23
The goal of the challenge is to develop a test-time adaptation (TTA) method, which could adapt the model to gradually changing domains in video sequences for semantic segmentation task. It is based on a synthetic driving video dataset - SHIFT. The source model is trained on images taken dur...
To solve this problem, we propose a simple yet effective method named Multi-source fUlly Test-timE adaptation (MUTE). Firstly, considering that different models contribute differently to the test samples, we assign a weight to each model and adopt the weight aggregation strategy (Ahmed et al.,...
In this paper, we propose a test-time adaptation method for event- based VFI to address the gap between the source and target domains. Our approach enables sequential learning in an online manner on the target domain, which only provides low-frame-r...
Continual Test-Time Domain Adaptation Qin Wang1 Olga Fink1,3* Luc Van Gool1,4 Dengxin Dai2 1ETH Zurich, Switzerland 2MPI for Informatics, Germany 3EPFL, Switzerland 4KU Lueven, Belgium {qin.wang,vangool,dai}@vision.ee.ethz.ch olga.fink@epfl.ch Abstract Test-time domain adaptation aims ...
These approaches are semantic segmentation based on the U-Net, and instance segmentation based on the Mask R-CNN models. Our findings show that even if only simple test-time augmentations (such as rotation or flipping and proper merging methods) are applied, TTA can significantly improve ...
test-time domain adaptation, test-time batch adaptation, and online test-time adaptation. For each category, we provide a comprehensive taxonomy of advanced algorithms and discuss various learning scenarios. Furthermore, we analyze relevant applications of TTA and discuss open challenges and promising ...
Welcome to the official code repository forATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentationby Zhitong Gao, Shipeng Yan, and Xuming He (NeurIPS 2023). This work introduces a novel framework to enhance the robustness of dense out-of-distribution (OOD) detec...
The official implementation of our work "HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation".Introduction3D point cloud segmentation has received significant interest for its growing applications. However, the generalization ability of models suffers in dynamic scenar...