Search Results for author:
Found 13 papers, 6 papers with code
M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice.
Problems and shortcuts in deep learning for screening mammography
The original model trained on both datasets achieved a 0. 945 AUC on the combined US+UK dataset but paradoxically only 0. 838 and 0. 892 on the US and UK datasets, respectively.
Deep is a Luxury We Don't Have
In this paper, we tackle this complexity by leveraging a linear self-attention approximation.
Knowledge Evolution in Neural Networks
We evaluate KE using relatively small datasets (e. g., CUB-200) and randomly initialized deep networks.
SVMax: A Feature Embedding Regularizer
The SVMax regularizer supports both supervised and unsupervised learning.
A Generic Visualization Approach for Convolutional Neural Networks
Compared to classification networks, attention visualization for retrieval networks is hardly studied.
Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
We introduce an unsupervised formulation to estimate heteroscedastic uncertainty in retrieval systems.
Boosting Standard Classification Architectures Through a Ranking Regularizer
We employ triplet loss as a feature embedding regularizer to boost classification performance.
Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
We cast visual retrieval as a regression problem by posing triplet loss as a regression loss.
Kid-Net: Convolution Networks for Kidney Vessels Segmentation from CT-Volumes
We propose a convolution neural network, called Kid-Net, along with a training schema to segment kidney vessels: artery, vein and collecting system.
Two Stream Self-Supervised Learning for Action Recognition
The self-supervised pre-trained weights effectiveness is validated on the action recognition task.
Texture Synthesis with Recurrent Variational Auto-Encoder
A novel loss function, FLTBNK, is used for training the texture synthesizer.
Seeded Laplaican: An Eigenfunction Solution for Scribble Based Interactive Image Segmentation
In our experiments, we evaluate our approach using both human scribble and "robot user" annotations to guide the foreground/background segmentation.
