Italy

We talk about the novel compression method for unconditional generative models.
The key concept of our method &quot;Adversarial Knowledge Distillation for generative models (AKDG)&quot; is very simple but effective.
The key is the additional discriminator which judges a teacher or student.
We conduct the compression experiments on several datasets.
Our AKDG outperforms the conventional compression method for unconditional generative models in all experiments.

ICPR 2020

Adversarial Knowledge Distillation for a Compact Generator

gans

adversarial learning

distillation

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


We talk about the novel compression method for unconditional generative models.
The key concept of our method "Adversarial Knowledge Distillation for generative models (AKDG)" is very simple but effective.
The key is the additional discriminator which judges a teacher or student.
We conduct the compression experiments on several datasets.
Our AKDG outperforms the conventional compression method for unconditional generative models in all experiments.

poster


For 3D point cloud registration, how to improve the local feature correlation of two point clouds is a challenging problem. In this paper, we propose a cascaded mutual information attention registration network. The network improves the accuracy of point cloud registration by stacking residual structure and using lateral connection. 


3D Point Cloud Registration Based on Cascaded Mutual Information Attention Network 


Imbalance in the proportion of training samples belonging to different classes often poses performance degradation of conventional classifiers. This is primarily due to the tendency of the classifier to be biased towards the majority classes in the imbalanced dataset. In this paper, we propose a novel three step technique to address imbalanced data. As a first step we significantly oversample the minority class distribution by employing the traditional Synthetic Minority Oversampling
Technique (SMOTE) algorithm using the neighborhood of the minority class samples and in the next step we partition the generated samples using a Gaussian-Mixture Model based clustering algorithm. In the final step synthetic data samples are
chosen based on the weight associated with the cluster, the weight itself being determined by the distribution of the majority class samples. Extensive experiments on several standard datasets from diverse domains show the usefulness of the proposed technique in comparison with the original SMOTE and its state-of-the-art
variants algorithms.

A Novel Adaptive Minority Oversampling Technique for Improved Classification in Data Imbalanced Scenarios

For practical application scenes, the cosmetic contact lenses detection still facing unsolved problems, due to the low image quality and difficulty in accurately iris localization. We propose a novel framework called Weighted Region Network (WRN) to detect the cosmetic contact lenses. The WRN includes a local attention Weight Network and a global classification Region Network. With the inherent attention mechanism, the proposed network is able to find more discriminative regions, which reduces the requirement for target detection and improves the ability of classification.

Local Attention and Global Representation Collaborating for Fine-grained Classification

Mutual information (MI) is an information-theoretic measure of dependency between two random variables. Several methods to estimate MI, from samples of two random variables with unknown underlying probability distributions have been
proposed in the literature. Recent methods realize parametric probability distributions or critic as a neural network to approximate unknown density ratios. The approximated density ratios are used to estimate different variational lower bounds of MI. While these methods provide reliable estimation when the true MI is low, they produce high variance estimates in cases of high MI. We argue that the high variance characteristic is due to the uncontrolled complexity of the critic's hypothesis space. In support of this argument, we use the data-driven Rademacher complexity of the hypothesis space associated with the critic's architecture to analyse generalization error bound of variational lower bound estimates of MI. In the proposed work, we show that it is possible to negate the high variance characteristics of these estimators by constraining the critic's hypothesis space to Reproducing Hilbert Kernel Space (RKHS), which corresponds to a kernel learned using Automated Spectral Kernel Learning (ASKL). By analysing the aforementioned generalization error bounds, we augment the overall optimisation objective with effective regularisation term. We empirically demonstrate the efficacy of this regularization in enforcing proper bias variance tradeoff on four variational lower bounds, namely NWJ, MINE, JS and SMILE.

Reducing the Variance of Variational Estimates of Mutual Information by Limiting the Critic's Hypothesis Space to RKHS


In recent years, deep learning has been used extensively in the field of image fusion. In this article, we propose a new image fusion method by designing a new structure and a new loss function for a deep learning model. Our backbone network is an autoencoder, in which the encoder has a dual branch structure. We input infrared images and visible light images to the encoder to extract detailed information and semantic information respectively. The fusion layer fuses two sets of features to get fused features. The decoder reconstructs the fusion features to obtain the fused image. We design a new loss function to reconstruct the image effectively. Experiments show that our proposed method achieves state-of-the-art performance.


A Dual-branch Network for Infrared and Visible Image Fusion


With the increasing popularity of augmented and virtual reality, retailers are now focusing more towards customer satisfaction to increase the amount of sales. Although augmented reality is not a new concept but it has gained much needed attention over the past few years. Our present work is targeted towards this direction which may be used to enhance user experience in various virtual and augmented reality based applications. We propose a model to change skin tone of a person. Given any input image of a person or a group of persons with some value indicating the desired change of skin color towards fairness or darkness, this method can change the skin tone of the persons in the image. This is an unsupervised method and also unconstrained in terms of pose, illumination, number of persons in the image etc. The goal of this work is to reduce the time and effort which is generally required for changing the skin tone using existing applications (e.g., Photoshop) by professionals or novice. To establish the efficacy of this method we have compared our result with that of some popular photo editor and also with the result of some existing benchmark method related to human attribute manipulation. Rigorous experiments on different datasets show the effectiveness of this method in terms of synthesizing perceptually convincing outputs.

An Unsupervised Approach towards Varying Human Skin Tone Using Generative Adversarial Networks


Structural reconstruction of plant roots from MRI
is challenging, because of low resolution and low signal-to-noise
ratio of the 3D measurements which may lead to disconnectivities
and wrongly connected roots. We propose a two-stage approach
for this task. The first stage is based on semantic root vs.
soil segmentation and finds lowest-cost paths from any root
voxel to the shoot. The second stage takes the largest fully
connected component generated in the first stage and uses
3D skeletonization to extract a graph structure. We evaluate
our method on 22 MRI scans and compare to human expert
reconstructions.

Robust Skeletonization for Plant Root Structure Reconstruction from MRI


Fractal Dimension (FD) is widely used for image
segmentation because of its successful approach toward
quantifying texture information. In this paper, we present a FD-based multi-focus image fusion method that utilizes FD to identify
focused regions, as the primary step for the multi-focus image
fusion process. The algorithm aims to extract the local FD features
of each multi-focus pair estimated using the differential box-counting method. A guided filter is employed to further specify the
spatial information and increase the robustness of the FD features
to noise. The outcome would be analyzed to achieve a focus map
that identifies sharp regions in each partially focused image.
Afterwards, the detected regions are combined into a single all-focused image. The experiments, along with the objective
assessments, demonstrate the competitive performance of the
proposed method compared to several state-of-the-art multi-focus
image fusion methods.

A Multi-Focus Image Fusion Method based on Fractal Dimension and Guided Filtering

The success of deep neural networks in the traditional keypoint detection task encourages researchers to solve new problems and collect more complex datasets. The size of the DeepFashion2 dataset poses a new challenge on the keypoint detection task, as it comprises 13 clothing categories that span a wide range of keypoints (294 in total). The direct prediction of all keypoints leads to huge memory consumption, slow training, and a slow inference time. This paper studies the keypoint grouping approach and how it affects the performance of the CenterNet architecture. We propose a simple and efficient automatic grouping technique with a powerful post-processing method and apply it to the DeepFashion2 fashion landmark task and the MS COCO pose estimation task. This reduces memory consumption and processing time during inference by up to 19% and 30% respectively, and during the training stage by 28% and 26% respectively, without compromising accuracy.

Efficient grouping for keypoint detection

In cataract surgery, the operation is performed with the help of a microscope. Since the microscope enables watching real-time surgery by up to two people only, a major part of surgical training is conducted using the recorded videos. To optimize the training procedure with the video content, the surgeons require an automatic relevance detection approach. In addition to relevance-based retrieval, these results can be further used for skill assessment and irregularity detection in cataract surgery videos. In this paper, a three-module framework is proposed to detect and classify the relevant phase segments in cataract videos. Taking advantage of an idle frame recognition network, the video is divided into idle and action segments. To boost the performance in relevance detection, the cornea where the relevant surgical actions are conducted is detected in all frames using Mask R-CNN. The spatiotemporally localized segments containing higher-resolution information about the pupil texture and actions, and complementary temporal information from the same phase are fed into the relevance detection module. This module consists of four parallel recurrent CNNs being responsible to detect four relevant phases that have been defined with medical experts. The results will then be integrated to classify the action phases as irrelevant or one of four relevant phases. Experimental results reveal that the proposed approach outperforms static CNNs and different configurations of feature-based and end-to-end recurrent networks.

Downloads

Next from ICPR 2020

3D Point Cloud Registration Based on Cascaded Mutual Information Attention Network

Similar lecture

Text Recognition in Real Scenarios with a Few Labeled Samples