Search
Search Results
-
Multi-scale constraints and perturbation consistency for semi-supervised sonar image segmentation
Emerging semi-supervised learning methods have enabled great progress in segmentation tasks. However, popular semi-supervised segmentation models use...
-
Perturbation consistency and mutual information regularization for semi-supervised semantic segmentation
Recent semi-supervised learning has attracted much attention by leveraging the hidden structures learned from unlabeled data to reduce the number of...
-
Spatiotemporal Perturbation Based Dynamic Consistency for Semi-supervised Temporal Action Detection
Temporal action detection usually relies on huge tagging costs to achieve significant performance. Semi-supervised learning, where only a small... -
Multi-Consistency Training for Semi-Supervised Medical Image Segmentation
Medical image segmentation is a crucial task in clinical applications. However, obtaining labeled data for medical images is often challenging. This...
-
Semi-supervised Retinal Vessel Segmentation Through Point Consistency
Retinal vessels usually serve as biomarkers for early diagnosis and treatment of ophthalmic and systemic diseases. However, collecting and labeling... -
Normal Magnetizing-Based Eddy Current Testing Method for Multidirectional Cracks on Steel Plate Surface Based on Permeability Perturbation
Conventional-magnetizing-based eddy current testing (CMB-ECT) typically applies a direct current (DC) tangential magnetization field parallel to the...
-
Analytical solution for ginzburg–landau equation in discrete solitons laser arrays lattices via non-perturbation methods
The Ginzburg–Landau equation (GLE) plays an important role in discrete solitons laser array lattices. In this manuscript, the analytical solution for...
-
On Robust Cross-view Consistency in Self-supervised Monocular Depth Estimation
Remarkable progress has been made in self-supervised monocular depth estimation (SS-MDE) by exploring cross-view consistency, e.g., photometric...
-
Degenerate perturbation theory to quantum search
We utilize degenerate perturbation theory to investigate continuous-time quantum search on second-order truncated simplex lattices. In this work, we...
-
Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely...
-
An Initial Perturbation Method for the Multiscale Singular Vector in Global Ensemble Prediction
Ensemble prediction is widely used to represent the uncertainty of single deterministic Numerical Weather Prediction (NWP) caused by errors in...
-
Improving explainable AI with patch perturbation-based evaluation pipeline: a COVID-19 X-ray image analysis case study
Recent advances in artificial intelligence (AI) have sparked interest in develo** explainable AI (XAI) methods for clinical decision support...
-
Neuron-Level Inverse Perturbation Against Adversarial Attacks
Although deep learning models have achieved unprecedented success, their vulnerabilities towards adversarial attacks have attracted increasing... -
Exploring Epipolar Consistency Conditions
Intravital X-ray microscopy (XRM) in preclinical mouse models is of vital importance for the identification of microscopic structural pathological... -
AP-GCL: Adversarial Perturbation on Graph Contrastive Learning
A serious ecological hazard of illegal transactions (money laundering, financial fraud, etc.) on the Bitcoin trading network. Anti-money laundering... -
Towards continuous consistency axiom
It is shown for the first time in this paper, that Kleinberg’s (
2002 ) (self-contradictory) axiomatic system for distance-based clustering fails (that... -
A spatial perturbation framework to validate implantation of the epileptogenic zone
Stereo-electroencephalography (SEEG) is the gold standard to delineate surgical targets in focal drug-resistant epilepsy. SEEG uses electrodes placed...
-
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain...
-
Semi-supervised 3D shape segmentation with multilevel consistency and part substitution
The lack of fine-grained 3D shape segmentation data is the main obstacle to develo** learning-based 3D segmentation techniques. We propose an...
-
Improving cross-lingual language understanding with consistency regularization-based fine-tuning
Fine-tuning pre-trained cross-lingual language models alleviates the need for annotated data in different languages, as it allows the models to...