Search Results for author:
Found 15 papers, 2 papers with code
Adaptive Texture Filtering for Single-Domain Generalized Segmentation
Domain generalization in semantic segmentation aims to alleviate the performance degradation on unseen domains through learning domain-invariant features.
MOT: Masked Optimal Transport for Partial Domain Adaptation
A novel masked OT (MOT) methodology on conditional distributions is proposed by defining a mask operation with label information.
Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation
Specifically, we propose a novel alignment loss term that minimizes the kernel Bures-Wasserstein distance between the joint distributions.
Generalized Label Shift Correction via Minimum Uncertainty Principle: Theory and Algorithm
As a fundamental problem in machine learning, dataset shift induces a paradigm to learn and transfer knowledge under changing environment.
SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss
Also, to strengthen characterization on the capillaries and the edges of blood vessels, we define a residual pyramid architecture which decomposes the spatial information in the decoding phase.
Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation
Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.
Conditional Bures Metric for Domain Adaptation
A conditional distribution matching network is proposed to learn the conditional invariant and discriminative features for UDA.
Learning Target Domain Specific Classifier for Partial Domain Adaptation
Previous UDA methods assume that the source and target domains share an identical label space, which is unrealistic in practice since the label information of the target domain is agnostic.
Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification
KLN can simultaneously learn a more expressive kernel and label prediction distribution, thus, it can be used to improve the classification performance in both supervised and semi-supervised learning scenarios.
Dual Adversarial Auto-Encoders for Clustering
By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of Auto-encoders.
Unsupervised Domain Adaptation via Discriminative Manifold Propagation
Second, batch-wise training of deep learning limits the characterization of the global structure.
Discriminative Residual Analysis for Image Set Classification with Posture and Age Variations
Consequently, the crucial point of image set recognition is to mine the intrinsic connection or structural information from the image batches with variations.
Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
In this paper, we consider a more general application scenario where the label distributions of the source and target domains are not the same.
Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment
Second, the batch-wise training manner in deep learning limits the description of the global structure.
Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation
We derive a camera style adaptation framework to learn the style-based mappings between different camera views, from the target domain to the source domain, and then we can transfer the identity-based distribution from the source domain to the target domain on the camera level.
Domain Adaptive Person Re-Identification
Person Re-Identification
+1
