Cross-Resolution Distillation for Efficient 3D Medical Image Registration

Hu, Bo; Zhou, Shenglong; Xiong, Zhiwei; Wu, Feng

doi:10.1109/tcsvt.2022.3178178

Cited by 22 publications

(4 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To investigate the impact of various block sizes on the performance of IDwNet during DCT, experimental simulations were conducted utilizing the CIFAR-10 dataset and the ResNet-18 classification network model, and block sizes were configured with four typical combinations: (1, 1), (2, 2), (4,4), and (8,8), where (x, y) denotes the block size in the horizontal and vertical directions. Subsequently, the embedding strength was adjusted to achieve comparable image quality for these combinations.…”

Section: Effect Of Block Size On Performancementioning

confidence: 99%

“…In recent years, deep neural network (DNN) models have garnered significant success across diverse fields. For instance, within conventional computer domains, like image processing [1][2][3], video processing [4,5], and natural language processing [6,7], as well as in interdisciplinary applications, such as medical image processing [8], cross-media retrieval [9], and pedestrian detection [10], deep neural networks (DNNs) have consistently exhibited superior performance when compared to traditional methodologies. Nevertheless, the construction, optimization, and training of deep neural networks (DNNs) demand substantial expertise, extensive training data, and considerable computational resources, thereby transforming the resulting trained DNN models into crucial assets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Unique Identification-Oriented Black-Box Watermarking Scheme for Deep Classification Neural Networks

Mo,

Wang,

Bian

2024

Symmetry

View full text Add to dashboard Cite

Given the substantial value and considerable training costs associated with deep neural network models, the field of deep neural network model watermarking has come to the forefront. While black-box model watermarking has made commendable strides, the current methodology for constructing poisoned images in the existing literature is simplistic and susceptible to forgery. Notably, there is a scarcity of black-box model watermarking techniques capable of discerning a unique user in a multi-user model distribution setting. For this reason, this paper proposes a novel black-box model watermarking method for unique identity identification, which is denoted as the ID watermarking of neural networks (IDwNet). Specifically, to enhance the distinguishability of deep neural network models in multi-user scenarios and mitigate the likelihood of poisoned image counterfeiting, this study develops a discrete cosine transform (DCT) and singular value decomposition (SVD)-based symmetrical embedding method to form the poisoned image. As this ID embedding method leads to indistinguishable deep features, the study constructs a poisoned adversary training strategy by simultaneously inputting clean images, poisoned images with the correct ID, and poisoned adversary images with incorrect IDs to train a deep neural network. Extensive simulation experiments show that the proposed scheme achieves excellent invisibility for the concealed ID, surpassing remarkably the state-of-the-art. In addition, the proposed scheme obtains a validation success rate exceeding 99% for the poisoned images at the cost of a marginal classification accuracy reduction of less than 0.5%. Moreover, even though there is only a 1-bit discrepancy between IDs, the proposed scheme still results in an accurate validation of user copyright. These results indicate that the proposed scheme is promising.

show abstract

Section: Effect Of Block Size On Performancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Unique Identification-Oriented Black-Box Watermarking Scheme for Deep Classification Neural Networks

Mo,

Wang,

Bian

2024

Symmetry

View full text Add to dashboard Cite

show abstract

“…DistillFlow [43] further improves above two-stage data distillation by introducing multiple teacher models and confidence mechanism. As for a related medical image registration task, the work CRD [63] distills knowledge from a feature-shifted teacher model with high resolution input to a student model with low resolution input for more efficiency. Different from their works, our MDFlow transfers knowledge between teacher and student networks mutually, so as to decouple matching outliers in augmentation regularization and exploit recent advanced architecture as student for better final prediction, while maintaining real-time inference.…”

Section: Knowledge Distillation and Mutual Distillationmentioning

confidence: 99%

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

Kong

Yang

2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term for continual self-supervision, which has been proved to be effective on difficult matching regions. However, this method also amplify the inevitable mismatch in unsupervised setting, blocking the learning process towards optimal solution. To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement. Concretely, taking estimation of off-the-shelf unsupervised approach as pseudo labels, our insight locates at defining a confidence selection mechanism to extract relative good matches, and then add diverse data augmentation for distilling adequate and reliable knowledge from teacher to student. Thanks to the decouple nature of our method, we can choose a stronger student architecture for sufficient learning. Finally, better student prediction is adopted to transfer knowledge back to the efficient teacher without additional costs in real deployment. Rather than formulating it as a supervised task, we find that introducing an extra unsupervised term for multi-target learning achieves best final results. Extensive experiments show that our approach, termed MDFlow, achieves state-of-the-art real-time accuracy and generalization ability on challenging benchmarks. Code is available at https://github.com/ltkong218/MDFlow.

show abstract

“…Consistently aligning 3D point clouds from different views to the same view is called 3D point cloud registration. As a very important task in computer vision, 3D point cloud registration has a wide range of applications in medical science [22], robotics, and other fields.…”

Section: Introductionmentioning

confidence: 99%

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Yang

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

179

115

View full text Add to dashboard Cite

Point cloud registration is to estimate a transformation to align point clouds collected in different perspectives. In learning-based point cloud registration, a robust descriptor is vital for high-accuracy registration. However, most methods are susceptible to noise and have poor generalization ability on unseen datasets. Motivated by this, we introduce SphereNet to learn a noise-robust and unseen-general descriptor for point cloud registration. In our method, first, the spheroid generator builds a geometric domain based on spherical voxelization to encode initial features. Then, the spherical interpolation of the sphere is introduced to realize robustness against noise. Finally, a new spherical convolutional neural network with spherical integrity padding completes the extraction of descriptors, which reduces the loss of features and fully captures the geometric features. To evaluate our methods, a new benchmark 3DMatchnoise with strong noise is introduced. Extensive experiments are carried out on both indoor and outdoor datasets. Under high-intensity noise, SphereNet increases the feature matching recall by more than 25 percentage points on 3DMatch-noise. In addition, it sets a new state-of-the-art performance for the 3DMatch and 3DLoMatch benchmarks with 93.5% and 75.6% registration recall and also has the best generalization ability on unseen datasets.

show abstract

Cross-Resolution Distillation for Efficient 3D Medical Image Registration

Cited by 22 publications

References 51 publications

A Unique Identification-Oriented Black-Box Watermarking Scheme for Deep Classification Neural Networks

A Unique Identification-Oriented Black-Box Watermarking Scheme for Deep Classification Neural Networks

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Contact Info

Product

Resources

About