Asia
AMOS: ALarge-ScaleAbdominalMulti-Organ BenchmarkforVersatileMedicalImageSegmentation
The significant heterogeneity poses higher requirements foralgorithm robustness.
Characterizing Bias in Classifiers using Generative Models
Daniel McDuff, Shuang Ma, Yale Song, Ashish Kapoor
Models that are learned from real-world data are often biased because the data usedtotrainthemisbiased.
Low-Rank Tucker Decomposition of Large Tensors Using TensorSketch
Osman Asif Malik, Stephen Becker
Neural Information Processing Systems http://nips.cc/
Neural Voice Cloning with a Few Samples
Sercan Arik, Jitong Chen, Kainan Peng, Wei Ping, Yanqi Zhou
Neural Information Processing Systems http://nips.cc/
Approximate Feature Collisions in Neural Nets
Ke Li, Tianhao Zhang, Jitendra Malik
Neural Information Processing Systems http://nips.cc/
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
We revisit data selection in a modern context of finetuning from a fundamental perspective.
eda9523faa5e7191aee1c2eaff669716-Supplemental-Conference.pdf
Though promising results have been reported on some RL application domains, policies learned with such representations usually fail to generalize well in a complex environment because minimizing a reconstruction loss may potentially introduce local (visual) features with task-irrelevant information.