Paper presented at ICCV 2019.
This paper targets the task with discrete and periodic
class labels (e.g., pose/orientation estimation) in the context of deep learning. The commonly used cross-entropy or
regression loss is not well matched to this problem as they
ignore the periodic nature of the labels and the class similarity, or assume labels are continuous value. We propose to
incorporate inter-class correlations in a Wasserstein training framework by pre-defining (i.e., using arc length of a
circle) or adaptively learning the ground metric. We extend
the ground metric as a linear, convex or concave increasing
function w.r.t. arc length from an optimization perspective.
We also propose to construct the conservative target labels
which model the inlier and outlier noises using a wrapped
unimodal-uniform mixture distribution. Unlike the one-hot
setting, the conservative label makes the computation of
Wasserstein distance more challenging. We systematically
conclude the practical closed-form solution of Wasserstein
distance for pose data with either one-hot or conservative
target label. We evaluate our method on head, body, vehicle and 3D object pose benchmarks with exhaustive ablation studies. The Wasserstein loss obtaining superior performance over the current methods, especially using convex mapping function for ground metric, conservative label,
and closed-form solution.
Xiaofeng Liu, Yang Zou, Tong Che, Peng Ding, Ping Jia, Jane You, B.V.K. Vijaya Kumar
In this paper, we evaluate a baseline word embedding model for a set of clinical notes derived from patient records. For our baseline, we extract features for this embedding using the Word2Vec module from the gensim package. We also build two models, a word2vec skipgram model with negative sampling and a positive point-wise mutual information (PPMI) model by training on the processed clinical notes. Our evaluation shows that both the PPMI and the skipgram models show improved results for medically-related terms when compared with the baseline model. PPMI shows the best result out of all three models.