Italy


Medical image segmentation is a critical field in the
domain of computer vision and with the growing acclaim of deep
learning based models, research in this field is constantly expanding.
Optical coherence tomography (OCT) is a non-invasive
method that scans the human’s retina with depth. It has been
hypothesized that the thickness of the retinal layers extracted
from OCTs could be an efficient and effective biomarker for
early diagnosis of AD. In this work, we aim to design a selftraining
model architecture for the task of segmenting the retinal
layers in OCT scans. Neural architecture search (NAS) is a
subfield of AutoML domain, which has a significant impact on
improving the accuracy of machine vision tasks. We integrate
the NAS algorithm with a Unet auto-encoder architecture as
its backbone. Then, we employ our proposed model to segment
the retinal nerve fiber layer in our preprocessed OCT images
with the aim of AD diagnosis. In this work, we trained a
super-resolution generative adversarial network on the raw OCT
scans to improve the quality of the images before the modeling
stage. In our architecture search strategy, different primitive
operations suggested to find down- &amp; up-sampling Unet cell
blocks and the binary gate method has been applied to make
the search strategy more practical. Our architecture search
method is empirically evaluated by training on the Unet and
NAS-Unet from scratch. Specifically, the proposed NAS-Unet
training significantly outperforms the baseline human-designed
architecture by achieving 95.1% in the mean Intersection over
Union metric and 79.1% in the Dice similarity coefficient.

ICPR 2020

OCT Image Segmentation Using Neural Architecture Search and SRGAN

srgan

nas-unet

oct segmentation

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. 



Medical image segmentation is a critical field in the
domain of computer vision and with the growing acclaim of deep
learning based models, research in this field is constantly expanding.
Optical coherence tomography (OCT) is a non-invasive
method that scans the human’s retina with depth. It has been
hypothesized that the thickness of the retinal layers extracted
from OCTs could be an efficient and effective biomarker for
early diagnosis of AD. In this work, we aim to design a selftraining
model architecture for the task of segmenting the retinal
layers in OCT scans. Neural architecture search (NAS) is a
subfield of AutoML domain, which has a significant impact on
improving the accuracy of machine vision tasks. We integrate
the NAS algorithm with a Unet auto-encoder architecture as
its backbone. Then, we employ our proposed model to segment
the retinal nerve fiber layer in our preprocessed OCT images
with the aim of AD diagnosis. In this work, we trained a
super-resolution generative adversarial network on the raw OCT
scans to improve the quality of the images before the modeling
stage. In our architecture search strategy, different primitive
operations suggested to find down- & up-sampling Unet cell
blocks and the binary gate method has been applied to make
the search strategy more practical. Our architecture search
method is empirically evaluated by training on the Unet and
NAS-Unet from scratch. Specifically, the proposed NAS-Unet
training significantly outperforms the baseline human-designed
architecture by achieving 95.1% in the mean Intersection over
Union metric and 79.1% in the Dice similarity coefficient.

poster

Remote sensing image retrieval (RSIR) is the process of ranking database images depending on the degree of similarity compared to the query image. As the complexity of RSIR increases due to the diversity in shooting range, angle, and location of remote sensors, there is an increasing demand for methods to address these issues and improve retrieval performance. In this work, we introduce a novel method for retrieving aerial images by merging group convolution with attention mechanism and metric learning, resulting in robustness to rotational variations.

Rotation Invariant Aerial Image Retrieval with Group Convolutional Metric Learning


For Tuberculosis (TB) detection beside the more expensive diagnosis solutions such as culture or sputum smear analysis one could consider the automatic analysis of the chest X-ray (CXR). This could mimic the lung region reading by the radiologist and it could provide an inexpensive solution to analyze and diagnose pulmonary abnormalities such as TB, a disease which often co-occurs with HIV. This software based pulmonary screening can be a reliable and affordable alternative solution for rural populations in different parts of the world such as the Indian subcontinent, Africa, etc.
The fully automatic system we are proposing is processing the incoming CXR image by applying image processing techniques to detect the region of interest (ROI) followed by a computationally cheap feature extraction involving edge detection using Laplacian of Gaussian which we enrich by counting the local distribution of the intensities. The choice to "zoom in" the ROI and look for abnormalities locally is motivated by the fact that some pulmonary abnormalities are localized in specific regions of the lungs. Later on the classifiers can decide about the normal or abnormal nature of each lung X-ray. Our goal is to find a simple feature descriptor, instead of a combination of several ones, -proposed and promoted in recent years' literature, which can properly and simply describe the different pathological alterations in the lungs. Our experiments report results on two publicly available benchmark data collections, namely the Shenzhen and the Montgomery collection.
For performance evaluation, measures such as area under the curve (AUC), and accuracy (ACC) were considered, achieving AUC = 0.81 (ACC = 83.33%) and AUC = 0.96 (ACC = 96.35%) for the Montgomery and Shenzhen collections, respectively. Several comparisons are also provided to other state-of-the-art systems reported recently in the field

Automatic Tuberculosis Detection Using Chest X-ray Analysis With Position Enhanced Structural Information


Darkness brings us uncertainty, worry and low confidence. This is a problem not only applicable to us walking in a dark evening but also for drivers driving a car on the road with very dim or even without lighting condition. To address this problem, we propose a new CNN structure named as Video Lightening Network (VLN) that regards the low-light enhancement as a residual learning task, which is useful as reference to indirectly lightening the environment, or for vision-based application systems, such as driving assistant systems. The VLN consists of several Lightening Back-Projection (LBP) and Temporal Aggregation (TA) blocks. Each LBP block enhances the low-light frame by domain transfer learning that iteratively maps the frame between the low- and normal-light domains. A TA block handles the motion among neighboring frames by investigating the spatial and temporal relationships. Several TAs work in a multi-scale way, which compensates the motions at different levels. The proposed architecture has a consistent enhancement for different levels of illuminations, which significantly increases the visual quality even in the extremely dark environment. Extensive experimental results show that the proposed approach outperforms other methods under both objective and subjective metrics.

Video Lightening with Dedicated CNN Architecture

We present a novel approach to developing an end-to-end learning framework to segment and classify major regions of a scientific document. We consider scientific document layout analysis as an object detection task over digital images, without any additional text features that need to be added into the network during the training process. Our technical objective is to implement transfer learning via fine-tuning of pre-trained networks and thereby demonstrate that this deep learning architecture is suitable for tasks that lack very large document corpora for training ab initio. As part of the experimental test bed for empirical evaluation of this approach, we created a merged multi-corpus data set for scientific publication layout detection tasks. Our results show good improvement with fine-tuning of a pre-trained base network using this merged data set, compared to the baseline convolutional neural network architecture.

Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks

Recently, various material recognition methods have
been introduced that uses a single color or light field camera. In
prior methods, color and texture information of an object are
used as key features. However, there exists fundamental limitation
in using color features for material recognition in that material
type can be characterized better by surface reflectance, visual
appearance rather than its color and textures. In this work, we
propose IR surface reflectance based material type recognition
method. We use off-the-shelf ToF camera to estimate the IR
reflectance of arbitrary surface. Material type recognition is
performed on both color and surface IR reflectance features. Several
network structures including gradual convolutional neural
network are proposed and verified for our material recognition
within our own 3D data sets.

Surface IR Reflectance Estimation and Material Recognition using ToF Camera

Although supervised person re-identification (RE-ID) has achieved great progress with deep learning, it requires time-consuming annotation of a large number of pedestrian identities. To reduce labeling cost, we attempt to reduce cross-camera identity annotations and exploit pedestrian attribute annotations as auxiliary information instead. The pedestrian attributes, such as outfit styles, contain coarse semantic knowledge. Although pedestrian attributes are annotated without exhaustive searching in a camera network, which is much easier than cross-camera identity annotation, ambiguity exists in attributes when different persons have similar outfits. To solve this problem, we propose an Attribute Similarity Guidance loss (ASG) to guide appearance feature learning for RE-ID by selective attribute similarity preservation to avoid the impact of such ambiguity. Finally, we develop an attribute-guided self training framework to jointly utilize attribute annotations, unlabeled data and limited labeled data for semi-supervised learning. Extensive experiments on Market-1501 and DukeMTMC-ReID show the superiority of our method for semi-supervised RE-ID.

Semi-supervised Person Re-identification by Attribute Similarity Guidance

We look at robustness in terms of reproducibility, which is challenging to improve and quantify in the context of dimensionality reduction for data visualization. We identify potential building blocks for achieving this kind of robustness and support these findings with a novel similarity measure for scatter plots. The building blocks are a restricted Boltzmann machine (RBM) pre-training for deep neural network (DNN) initilization and a deep autoencoder based regularization method.

Dimensionality Reduction for Data Visualization and Linear Classification - Robustness vs. Accuracy


This paper studies the problem of Person Re-Identification (ReID)
for large-scale applications. Recent research efforts have been devoted
to building complicated part models, which introduce considerably
high computational cost and memory consumption, inhibiting its practicability
in large-scale applications. This paper aims to develop a novel learning
strategy to find efficient feature embeddings while maintaining the
balance of accuracy and model complexity. More specifically, we find
by enhancing the classical triplet loss together with cross-entropy
loss, our method can explore the hard examples and build a discriminant
feature embedding yet compact enough for large-scale applications.
Our method is carried out progressively using Bayesian optimization,
and we call it the Progressive Learning Algorithm (PLA). Extensive
experiments on three large-scale datasets show that our PLA is comparable
or better than the state-of-the-arts. Especially, on the challenging
Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving
at least 30\% parameters than strong part models.

Supervised Classification Using Graph-based Space Partitioning for Multiclass Problems

Significant advances have been achieved in face recognition in the last decade thanks to the development of deep learning methods. However, recognizing faces captured in uncontrolled environments is still a challenging problem for the scientific community. In these scenarios, the performance of most of existing deep learning based methods abruptly falls, due to the bad quality of the face images. In this work, we propose to use an activation map to represent the quality information in a face image. Different face regions are analyzed to determine their quality and then only those regions with good quality are used to perform the recognition using a given deep face model. For experimental evaluation, in order to simulate unconstrained environments, three challenging databases, with different variations in appearance, were selected: the Labeled Faces in the Wild Database, the Celebrities in Frontal-Profile in the Wild Database, and the AR Database. Three deep face models were used to evaluate the proposal on these databases and in all cases, the use of the proposed activation map allows the improvement of the recognition rates obtained by the original models in a range from 0.3 up to 31%. The obtained results experimentally demonstrated that the proposal is able to select those face areas with higher discriminative power and enough identifying information,

Premium content

OCT Image Segmentation Using Neural Architecture Search and SRGAN

Downloads

Next from ICPR 2020

Rotation Invariant Aerial Image Retrieval with Group Convolutional Metric Learning

Similar lecture

Automatic Tuberculosis Detection Using Chest X-ray Analysis With Position Enhanced Structural Information