Few-shot adversarial domain adaptation
This work provides a framework for addressing the problem of supervised domain
adaptation with deep models. The main idea is to exploit adversarial learning to learn an …
adaptation with deep models. The main idea is to exploit adversarial learning to learn an …
Dada: Depth-aware domain adaptation in semantic segmentation
Unsupervised domain adaptation (UDA) is important for applications where large scale
annotation of representative data is challenging. For semantic segmentation in particular, it …
annotation of representative data is challenging. For semantic segmentation in particular, it …
Deep imbalanced attribute classification using visual attention aggregation
N Sarafianos, X Xu… - Proceedings of the …, 2018 - openaccess.thecvf.com
For many computer vision applications, such as image description and human identification
recognizing the visual attributes of humans is an essential yet challenging problem. Its …
recognizing the visual attributes of humans is an essential yet challenging problem. Its …
Spigan: Privileged adversarial learning from simulation
Deep Learning for Computer Vision depends mainly on the source of supervision. Photo-
realistic simulators can generate large-scale automatically labeled syntheticdata, but …
realistic simulators can generate large-scale automatically labeled syntheticdata, but …
Bimal: Bijective maximum likelihood approach to domain adaptation in semantic scene segmentation
Semantic segmentation aims to predict pixel-level labels. It has become a popular task in
various computer vision applications. While fully supervised segmentation methods have …
various computer vision applications. While fully supervised segmentation methods have …
Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions
The dense network of interconnected cellular signalling responses that are quantifiable in
peripheral immune cells provides a wealth of actionable immunological insights. Although …
peripheral immune cells provides a wealth of actionable immunological insights. Although …
Not all areas are equal: Transfer learning for semantic segmentation via hierarchical region selection
The success of deep neural networks for semantic segmentation heavily relies on large-
scale and well-labeled datasets, which are hard to collect in practice. Synthetic data offers …
scale and well-labeled datasets, which are hard to collect in practice. Synthetic data offers …
Knowledge-adaptation priors
Humans and animals have a natural ability to quickly adapt to their surroundings, but
machine-learning models, when subjected to changes, often require a complete retraining …
machine-learning models, when subjected to changes, often require a complete retraining …
Multi-view feature transformation based SVM+ for computer-aided diagnosis of liver cancers with ultrasound images
It is feasible to improve the performance of B-mode ultrasound (BUS) based computer-aided
diagnosis (CAD) for liver cancers by transferring knowledge from contrast-enhanced …
diagnosis (CAD) for liver cancers by transferring knowledge from contrast-enhanced …
ML-DSVM+: A meta-learning based deep SVM+ for computer-aided diagnosis
Transfer learning (TL) can improve the performance of a single-modal medical imaging-
based computer-aided diagnosis (CAD) by transferring knowledge from related imaging …
based computer-aided diagnosis (CAD) by transferring knowledge from related imaging …