Asia
Automated Classification of Model Errors on ImageNet
While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress.
Deep Homogeneous Mixture Models: Representation, Separation, and Approximation
Priyank Jaini, Pascal Poupart, Yaoliang Yu
Neural Information Processing Systems http://nips.cc/
5c186016d0844767209dc36e9e61441b-Paper-Conference.pdf
DeMa's focus on sequences diminishes approximately exponentially.
Graphical Generative Adversarial Networks
Chongxuan LI, Max Welling, Jun Zhu, Bo Zhang
Neural Information Processing Systems http://nips.cc/
Doubly Mild Generalization for Offline Reinforcement Learning Yixiu Mao 1, Qi Wang 1, Y un Qu
Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards out-of-distribution (OOD) actions.
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, hongsheng Li
Neural Information Processing Systems http://nips.cc/
Emergent Communication in Interactive Sketch Question Answering
Ironically, previous works neglect multi-round interaction, which is indispensable in human communication.
Approximating the Permanent by Sampling from Adaptive Partitions
Jonathan Kuck, Tri Dao, Hamid Rezatofighi, Ashish Sabharwal, Stefano Ermon
Neural Information Processing Systems http://nips.cc/
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
Bruno Korbar, Du Tran, Lorenzo Torresani
Toeasethelearning, wedemonstrate thatitisbeneficial toadoptacurriculum learning strategy [23], where harder negatives are introduced after an initial stage of learning on easiernegatives.