7 citations · 29 across the 11 of their papers we have counts for
13 papers
M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
Yen Nhi Truong Vu, Dan Guo, Ahmed Taha +2
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
Trevor Tsue, Brent Mombourquette, Ahmed Taha +3
This work reveals undiscovered challenges in the performance and generalizability of deep learning models. We (1) identify spurious shortcuts and evaluation issues that can inflate…
Deep is a Luxury We Don't Have
Ahmed Taha, Yen Nhi Truong Vu, Brent Mombourquette +3
Medical images come in high resolutions. A high resolution is vital for finding malignant tissues at an early stage. Yet, this resolution presents a challenge in terms of modeling…
Knowledge Evolution in Neural Networks
Ahmed Taha, Abhinav Shrivastava, Larry Davis
Deep learning relies on the availability of a large corpus of data (labeled or unlabeled). Thus, one challenging unsettled question is: how to train a deep network on a relatively…
SVMax: A Feature Embedding Regularizer
Ahmed Taha, Alex Hanson, Abhinav Shrivastava +1
A neural network regularizer (e.g., weight decay) boosts performance by explicitly penalizing the complexity of a network. In this paper, we penalize inferior network activations -…
A Generic Visualization Approach for Convolutional Neural Networks
Ahmed Taha, Xitong Yang, Abhinav Shrivastava +1
Retrieval networks are essential for searching and indexing. Compared to classification networks, attention visualization for retrieval networks is hardly studied. We formulate att…
Unsupervised Data Uncertainty Learning in Visual Retrieval Systems
Ahmed Taha, Yi-Ting Chen, Teruhisa Misu +2
We introduce an unsupervised formulation to estimate heteroscedastic uncertainty in retrieval systems. We propose an extension to triplet loss that models data uncertainty for each…
Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
Ahmed Taha, Yi-Ting Chen, Xitong Yang +2
We cast visual retrieval as a regression problem by posing triplet loss as a regression loss. This enables epistemic uncertainty estimation using dropout as a Bayesian approximatio…
Boosting Standard Classification Architectures Through a Ranking Regularizer
Ahmed Taha, Yi-Ting Chen, Teruhisa Misu +2
We employ triplet loss as a feature embedding regularizer to boost classification performance. Standard architectures, like ResNet and Inception, are extended to support both losse…
Kid-Net: Convolution Networks for Kidney Vessels Segmentation from CT-Volumes
Ahmed Taha, Pechin Lo, Junning Li +1
Semantic image segmentation plays an important role in modeling patient-specific anatomy. We propose a convolution neural network, called Kid-Net, along with a training schema to s…
Two Stream Self-Supervised Learning for Action Recognition
Ahmed Taha, Moustafa Meshry, Xitong Yang +2
We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and tempor…
Texture Synthesis with Recurrent Variational Auto-Encoder
Rohan Chandra, Sachin Grover, Kyungjun Lee +2
We propose a recurrent variational auto-encoder for texture synthesis. A novel loss function, FLTBNK, is used for training the texture synthesizer. It is rotational and partially c…
Seeded Laplaican: An Eigenfunction Solution for Scribble Based Interactive Image Segmentation
Ahmed Taha, Marwan Torki
In this paper, we cast the scribble-based interactive image segmentation as a semi-supervised learning problem. Our novel approach alleviates the need to solve an expensive general…