Decoupled unbiased teacher for source-free domain adaptive medical object detection

X Liu, W Li, Y Yuan - IEEE Transactions on Neural Networks …, 2023 - ieeexplore.ieee.org
… medical object detection, we propose decoupled unbiased teacher (DUT), a decoupled
mean-… ] proposed a reversed flow method to transforms real images to synthetic and performed …

Decoupling features for fault detection and diagnosis on centrifugal chillers (1486-RP)

X Zhao, M Yang, H Li - HVAC&R Research, 2011 - Taylor & Francis
… of some decoupling features, which are the basis of a decoupling-based … flow rate will be
used for the other decoupling features. Once a reduced condenser water flow fault is detected, …

Generalized pose decoupled network for unsupervised 3d skeleton sequence-based action representation learning

M Liu, F Meng, Y Liang - Cyborg and Bionic Systems, 2022 - spj.science.org
… of the autoencoder, whose midlevel feature is expected to describe … features from pose flow
where direction and norm are mixed. To this end, we present an explicit pose decoupled flow

Actual bearing compound fault diagnosis based on active learning and decoupling attentional residual network

Y Jin, C Qin, Y Huang, C Liu - Measurement, 2021 - Elsevier
… This paper presents a novel decoupling attentional residual network for compound fault …
overall flow chart of the proposed method, in which active learning technique and decoupling

Enhancing unsupervised video representation learning by decoupling the scene and the motion

J Wang, Y Gao, K Li, J Hu, X Jiang, X Guo… - Proceedings of the …, 2021 - ojs.aaai.org
… In order to tackle this problem, we propose to decouple the scene and the motion (DSM) with
… It should be noted that given a video frame at time t and the corresponding optical flow, we …

Did-m3d: Decoupling instance depth for monocular 3d object detection

L Peng, X Wu, Z Yang, H Liu, D Cai - European Conference on Computer …, 2022 - Springer
… Due to the entangled features, the previous way of directly predicting instance depth is
suboptimal. Therefore, we propose to decouple the … We illustrate the depth flow process in Fig. 4. …

Dual Spatial-Temporal Feature Pyramid With Decoupled Temporal Mining for Video Semantic Segmentation

Y Hong, H Pan, W Sun, Y Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
feature pyramid from multiple reference frames. Building on the dual feature pyramid, we
further propose to decouple … optical flow-based method [34] obtained the aligned feature by …

Unveiling the Unknown: Conditional Evidence Decoupling for Unknown Rejection

Z Wu, B Su, H Zhang, Z Zhou - arXiv preprint arXiv:2406.18443, 2024 - arxiv.org
… For these pseudo-unknown samples, we decouple training in the form of Evidential Deep …
Normalizing flow based feature synthesis for outlier-aware object detection. In Proceedings …

BD-MSA: Body decouple VHR Remote Sensing Image Change Detection method guided by multi-scale feature information aggregation

Y Tan, X Li, Y Chen, J Ai - IEEE Journal of Selected Topics in …, 2024 - ieeexplore.ieee.org
Decoupling edge and body is feasible using the previously described flow, as well as the …
As a result, we use the flow field concept and add the decouple module after feature decoding …

HD-Net: High-resolution decoupled network for building footprint extraction via deeply supervised body and boundary decomposition

Y Li, D Hong, C Li, J Yao, J Chanussot - ISPRS Journal of Photogrammetry …, 2024 - Elsevier
… Notably, our flow-based decoupling strategy, as expected, … of feature coupling, we introduced
the feature decoupling–recoupling (FDR) module. Within this module, the coupled feature