• Publications
  • Influence
Rethinking the Inception Architecture for Computer Vision
TLDR
This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
TLDR
A unified implementation of the Faster R-CNN, R-FCN and SSD systems is presented and the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures is traced out.
Attention-Based Extraction of Structured Information from Street View Imagery
We present a neural network model — based on Convolutional Neural Networks, Recurrent Neural Networks and a novel attention mechanism — which achieves 84.2% accuracy on the challenging French Street
Augmentation for small object detection
TLDR
This work analyzes the current state-of-the-art model, Mask-RCNN, on a challenging dataset, MS COCO, and shows that the overlap between small ground-truth objects and the predicted anchors is much lower than the expected IoU threshold.
Semantic Instance Segmentation via Deep Metric Learning
TLDR
A new method for semantic instance segmentation is proposed, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together, based on a deep, fully convolutional embedding model.
The Devil is in the Decoder
TLDR
An extensive comparison of a variety of decoders for a range of pixel-wise prediction tasks and introduces a novel decoder: bilinear additive upsampling and introduces new residual-like connections for decoder.
The Devil is in the Decoder: Classification, Regression and GANs
TLDR
This paper presents an extensive comparison of a variety of decoders for a range of pixel-wise tasks ranging from classification, regression to synthesis and introduces new residual-like connections for decoder.
Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms
This diagnostic accuracy study evaluates whether artificial intelligence can overcome human mammography interpretation limits with a rigorous, unbiased evaluation of machine learning algorithms.
Large-Scale Mammography CAD with Deformable Conv-Nets
TLDR
This study presents a neural net architecture based on R-FCN/DCN, that has adapted from the natural image domain to suit mammograms—particularly their larger image size—without compromising resolution.
Deep Learning for Rheumatoid Arthritis: Joint Detection and Damage Scoring in X-rays
TLDR
This work presents a multi-task deep learning model that simultaneously learns to localize joints on X-ray images and diagnose two kinds of joint damage: narrowing and erosion.
...
...