arXiv subjects

Khoi Nguyen

Publications and source records attributed to Khoi Nguyen.

41 records · Page 3Linked to original sources

arXiv2021

FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter

This paper is about few-shot instance segmentation, where training and test image sets do not share the same object classes. We specify and evaluate a new few-shot anchor-free part-based instance segmenter FAPIS. Our key novelty is in explicit modeling of latent object parts shared across training object classes, which is expected to facilitate our few-shot learning on new classes in testing. We specify a new anchor-free object detector aimed at scoring and regressing locations of foreground bounding boxes, as well as estimating relative importance of latent parts within each box. Also, we specify a new network for delineating and weighting latent parts for the final instance segmentation within every detected bounding box. Our evaluation on the benchmark COCO-20i dataset demonstrates that we significantly outperform the state of the art.

cs.CV↗

arXiv2020

A Self-supervised GAN for Unsupervised Few-shot Object Recognition

This paper addresses unsupervised few-shot object recognition, where all training images are unlabeled, and test images are divided into queries and a few labeled support images per object class of interest. The training and test images do not share object classes. We extend the vanilla GAN with two loss functions, both aimed at self-supervised learning. The first is a reconstruction loss that enforces the discriminator to reconstruct the probabilistically sampled latent code which has been used for generating the "fake" image. The second is a triplet loss that enforces the discriminator to output image encodings that are closer for more similar images. Evaluation, comparisons, and detailed ablation studies are done in the context of few-shot classification. Our approach significantly outperforms the state of the art on the Mini-Imagenet and Tiered-Imagenet datasets.

cs.CV↗

arXiv2019

Feature Weighting and Boosting for Few-Shot Segmentation

This paper is about few-shot segmentation of foreground objects in images. We train a CNN on small subsets of training images, each mimicking the few-shot setting. In each subset, one image serves as the query and the other(s) as support image(s) with ground-truth segmentation. The CNN first extracts feature maps from the query and support images. Then, a class feature vector is computed as an average of the support's feature maps over the known foreground. Finally, the target object is segmented in the query image by using a cosine similarity between the class feature vector and the query's feature map. We make two contributions by: (1) Improving discriminativeness of features so their activations are high on the foreground and low elsewhere; and (2) Boosting inference with an ensemble of experts guided with the gradient of loss incurred when segmenting the support images in testing. Our evaluations on the PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that we significantly outperform existing approaches.

cs.CV↗

arXiv2019

Causal Mediation Analysis Leveraging Multiple Types of Summary Statistics Data

Summary statistics of genome-wide association studies (GWAS) teach causal relationship between millions of genetic markers and tens and thousands of phenotypes. However, underlying biological mechanisms are yet to be elucidated. We can achieve necessary interpretation of GWAS in a causal mediation framework, looking to establish a sparse set of mediators between genetic and downstream variables, but there are several challenges. Unlike existing methods rely on strong and unrealistic assumptions, we tackle practical challenges within a principled summary-based causal inference framework. We analyzed the proposed methods in extensive simulations generated from real-world genetic data. We demonstrated only our approach can accurately redeem causal genes, even without knowing actual individual-level data, despite the presence of competing non-causal trails.

stat.ML↗

arXiv2017

Curvature-induced stiffening of a fish fin

How fish modulate their fin stiffness during locomotive manoeuvres remains unknown. We show that changing the fin's curvature modulates its stiffness. Modelling the fin as bendable bony rays held together by a membrane, we deduce that fin curvature is manifested as a misalignment of the principal bending axes between neighbouring rays. An external force causes neighbouring rays to bend and splay apart, and thus stretches the membrane. This coupling between bending the rays and stretching the membrane underlies the increase in stiffness. Using analysis of a 3D reconstruction of a Mackerel (Scomber japonicus) pectoral fin, we calculate the range of stiffnesses this fin is expected to span by changing curvature. The 3D reconstruction shows that, even in its geometrically flat state, a functional curvature is embedded within the fin microstructure owing to the morphology of individual rays. Since the ability of a propulsive surface to transmit force to the surrounding fluid is limited by its stiffness, the fin curvature controls the coupling between the fish and its surrounding fluid. Thereby, our results provide mechanical underpinnings and morphological predictions for the hypothesis that the spanned range of fin stiffnesses correlates with the behaviour and the ecological niche of the fish.

physics.flu-dyn↗