In this work, we propose a novel scale-aware progressive training mechanism to address large scale variations across faces.
We observe that these proposed schemes are capable of facilitating the learning of discriminative feature representations.
To this end, we comprehensively investigate three types of ranking constraints, i. e., global ranking, class-specific ranking and IoU-guided ranking losses.
Particularly, with the same architecture of PSPNet (ResNet-18), our method outperforms the single-dataset baseline by 5. 65\%, 6. 57\%, and 5. 79\% of mIoU on the validation sets of Cityscapes, BDD100K, CamVid, respectively.
Such bin regularization (BR) mechanism encourages the weight distribution of each quantization bin to be sharp and approximate to a Dirac delta distribution ideally.
In step II, we augment the initial imputations to ensure the consistency of the resulting estimators regardless of the specification of the prediction model or the imputation model.
Motivated by the need of modeling the number of relapses in multiple sclerosis patients, where the ratio of relapse rates is a natural choice of the treatment effect, we propose to estimate the conditional average treatment effect (CATE) as the ratio of expected potential outcomes, and derive a doubly robust estimator of this CATE in a semiparametric model of treatment-covariate interactions.
1 code implementation • 22 Sep 2019 • Zhigang Li, Lu Tian, A. James O'Malley, Margaret R. Karagas, Anne G. Hoen, Brock C. Christensen, Juliette C. Madan, Quran Wu, Raad Z. Gharaibeh, Christian Jobin, Hongzhe Li
The target of inference in microbiome analyses is usually relative abundance (RA) because RA in a sample (e. g., stool) can be considered as an approximation of RA in an entire ecosystem (e. g., gut).
Person re-identification is generally divided into two part: first how to represent a pedestrian by discriminative visual descriptors and second how to compare them by suitable distance metrics.
In detail, the proposed method distributes the $d$-dimensional data of size $N$ generated from a transelliptical graphical model into $m$ worker machines, and estimates the latent precision matrix on each worker machine based on the data of size $n=N/m$.
We propose a communication-efficient distributed estimation method for sparse linear discriminant analysis (LDA) in the high dimensional regime.
As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor.
Ranked #76 on Person Re-Identification on DukeMTMC-reID
However, in a more realistic situation, one does not know in advance whether a feature is effective or not for a given query.
In the light of recent advances in image search, this paper proposes to treat person re-identification as an image search problem.