Home /
Research
Showing 37 - 42 / 904
Attention-gating for improved radio galaxy classification
MicahBowles, AnnaM.M.Scaife, FionaPorter....
Published date-12/02/2020
In this work we introduce attention as a state of the art mechanism for classification of radio galaxies using convolutional neural networks. We present an attention-based model that performs on …
Chair Segments: A Compact Benchmark for the Study of Object Segmentation
LeticiaPinto-Alva, IanK.Torres, RosangelGarcia....
Published date-12/02/2020
ImageClassification, ObjectDiscovery, SemanticSegmentation, TransferLearning
Over the years, datasets and benchmarks have had an outsized influence on the design of novel algorithms. In this paper, we introduce ChairSegments, a novel and compact semi-synthetic dataset for …
Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training
AndreiMargeloiu, NikolaSimidjievski, MatejaJamnik....
Published date-12/02/2020
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer. We show that gradient-based saliency maps of adversarially trained …
PlueckerNet: Learn to Register 3D Line Reconstructions
LiuLiu, HongdongLi, HaodongYao....
Published date-12/02/2020
Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions. This paper proposes a neural network …
How Robust are Randomized Smoothing based Defenses to Data Poisoning?
AkshayMehra, BhavyaKailkhura, Pin-YuChen....
Published date-12/02/2020
bileveloptimization, DataAugmentation, DataPoisoning
The prediction of certifiably robust classifiers remains constant around a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously …
PatchmatchNet: Learned Multi-View Patchmatch Stereo
FangjinhuaWang, SilvanoGalliani, ChristophVogel....
Published date-12/02/2020
We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for high-resolution multi-view stereo. With high computation speed and low memory requirement, PatchmatchNet can process higher resolution imagery and …