Matching-CNN Meets KNN: Quasi-Parametric Human Parsing

04/06/2015
by   Si Liu, et al.
0

Both parametric and non-parametric approaches have demonstrated encouraging performances in the human parsing task, namely segmenting a human image into several semantic regions (e.g., hat, bag, left arm, face). In this work, we aim to develop a new solution with the advantages of both methodologies, namely supervision from annotated data and the flexibility to use newly annotated (possibly uncommon) images, and present a quasi-parametric human parsing model. Under the classic K Nearest Neighbor (KNN)-based nonparametric framework, the parametric Matching Convolutional Neural Network (M-CNN) is proposed to predict the matching confidence and displacements of the best matched region in the testing image for a particular semantic region in one KNN image. Given a testing image, we first retrieve its KNN images from the annotated/manually-parsed human image corpus. Then each semantic region in each KNN image is matched with confidence to the testing image using M-CNN, and the matched regions from all KNN images are further fused, followed by a superpixel smoothing procedure to obtain the ultimate human parsing result. The M-CNN differs from the classic CNN in that the tailored cross image matching filters are introduced to characterize the matching between the testing image and the semantic region of a KNN image. The cross image matching filters are defined at different convolutional layers, each aiming to capture a particular range of displacements. Comprehensive evaluations over a large dataset with 7,700 annotated human images well demonstrate the significant performance gain from the quasi-parametric model over the state-of-the-arts, for the human parsing task.

READ FULL TEXT

page 1

page 4

page 8

research
03/09/2015

Deep Human Parsing with Active Template Regression

In this work, the human parsing task, namely decomposing a human image i...
research
05/07/2015

Adaptive Nonparametric Image Parsing

In this paper, we present an adaptive nonparametric solution to the imag...
research
08/12/2017

Face Parsing via a Fully-Convolutional Continuous CRF Neural Network

In this work, we address the face parsing task with a Fully-Convolutiona...
research
11/28/2018

Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints from Limited Training Data

Detecting semantic parts of an object is a challenging task in computer ...
research
12/15/2016

Design of Image Matched Non-Separable Wavelet using Convolutional Neural Network

Image-matched nonseparable wavelets can find potential use in many appli...
research
02/11/2019

Pornographic Image Recognition via Weighted Multiple Instance Learning

In the era of Internet, recognizing pornographic images is of great sign...
research
03/16/2017

Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing

Human parsing has recently attracted a lot of research interests due to ...

Please sign up or login with your details

Forgot password? Click here to reset