Home /
Research
Showing 277 - 282 / 904
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
NimitS.Sohoni, JaredA.Dunnmon, GeoffreyAngus....
Published date-11/25/2020
Clustering, ImageClassification
In real-world classification tasks, each class often comprises multiple finer-grained "subclasses." As the subclass labels are frequently unavailable, models trained using only the coarser-grained class labels often exhibit highly variable …
Supercharging Imbalanced Data Learning With Causal Representation Transfer
JunyaChen, ZidiXiu, BenjaminGoldstein....
Published date-11/25/2020
TransferLearning
Dealing with severe class imbalance poses a major challenge for real-world applications, especially when the accurate classification and generalization of minority classes is of primary interest. In computer vision, learning …
The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation
BjörnBrowatzki, Jörn-PhilippLies, ChristianWallraven....
Published date-11/25/2020
RetinalVesselSegmentation
We propose an encoder-decoder framework for the segmentation of blood vessels in retinal images that relies on the extraction of large-scale patches at multiple image-scales during training. Experiments on three …
Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstruction
AnzhuYu, WenyueGuo, BingLiu....
Published date-11/25/2020
3DReconstruction
We present an efficient multi-view stereo (MVS) network for 3D reconstruction from multiview images. While previous learning based reconstruction approaches performed quite well, most of them estimate depth maps at …
Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
TianyuHan, SvenNebelung, FedericoPedersoli....
Published date-11/25/2020
DecisionMaking
Unmasking the decision-making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, we demonstrate that adversarially trained models can significantly enhance the usability …
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
PengSun, JiechaoXiong, LeiHan....
Published date-11/25/2020
Dota2, Multi-agentReinforcementLearning, Starcraft, StarcraftII
Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MARL) has shown phenomenal breakthroughs recently. Strong AIs are achieved for several benchmarks, including Dota 2, Glory of Kings, Quake III, StarCraft II, …