Technology
LearningImbalancedDatasetswith Label-Distribution-AwareMarginLoss
First, we propose a theoretically-principled label-distribution-aware margin (LDAM) loss motivated by minimizing a margin-based generalization bound.
Generalizing to Unseen Domains via Adversarial Data Augmentation
Riccardo Volpi, Hongseok Namkoong, Ozan Sener, John C. Duchi, Vittorio Murino, Silvio Savarese
Neural Information Processing Systems http://nips.cc/
Modelling and unsupervised learning of symmetric deformable object categories
James Thewlis, Hakan Bilen, Andrea Vedaldi
Top: inputimageswiththeaxisof symmetry superimposed (showningreen). Infact,ourmethodbuildson[38]and also learns a dense geometric embedding for objects, however, by using a different supervision principle,symmetry.
SolvingInterpretableKernelDimensionReduction
Kernel dimensionality reduction (KDR) algorithms find a low dimensional representation of the original data by optimizing kernel dependency measures that are capable ofcapturing nonlinear relationships.
Supplementary Material 481 We provide details omitted in the main paper
To achieve this, auxiliary information (e.g., texts or attributes) is usually needed