Italy

Synthetic image generation provides the ability to efficiently produce large quantities of labeled data, which addresses both the data volume requirements of state-of-the-art vision systems and the expense of manually labeling data. However, systems trained on synthetic data typically under-perform systems trained on realistic data due to mismatch between the synthetic and realistic data distributions. Domain Randomization (DR) is a method of broadening a synthetic data distribution to encompass a realistic data distribution and provides better performance when the exact characteristics of the realistic data distribution are not known or cannot be simulated. However, there is no consensus in the literature on the best method of performing DR. We propose a novel method of ranking DR methods by directly measuring the difference between realistic and DR data distributions. This avoids the need to measure task-specific performance and the associated expense of training and evaluation. We compare different methods for measuring distribution differences, including the Wasserstein and Fréchet Inception distances. We also examine the effect of performing this evaluation directly on images and features generated by an image classification backbone. Finally, we show that the ranking generated by our method is reflected in actual task performance.

ICPR 2020

Quantifying the Use of Domain Randomization

object localization

domain randomization

sim-to-real

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. 


poster

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various techniques have been proposed since the original formulation, which mimics different aspects of the teacher such as the representation space, decision boundary, or intra-data relationship. Some methods replace the one-way knowledge distillation from a static teacher with collaborative learning between a cohort of students. Despite the recent advances, a clear understanding of where knowledge resides in a deep neural network and an optimal method for capturing knowledge from teacher and transferring it to student remains an open question. In this study, we provide an extensive study on nine different KD methods which covers a broad spectrum of approaches to capture and transfer knowledge. We demonstrate the versatility of the KD framework on different datasets and network architectures under varying capacity gaps between the teacher and student. The study provides intuition for the effects of mimicking different aspects of the teacher and derives insights from the performance of the different distillation approaches to guide the design of more effective KD methods. Furthermore, our study shows the effectiveness of the KD framework in learning efficiently under varying severity levels of label noise and class imbalance, consistently providing generalization gains over standard training. We emphasize that the efficacy of KD goes much beyond a model compression technique and it should be considered as a general-purpose training paradigm which offers more robustness to common challenges in the real-world datasets compared to the standard training procedure.

Knowledge Distillation Beyond Model Compression


Objective: In the last years, Robot-assisted partial nephrectomy (RAPN) is establishing as elected treatment for renal cell carcinoma (RCC). Reduced field of view, field occlusions by surgical tools, and reduced maneuverability may potentially cause accidents, such as unwanted vessel resection with conse- quent bleeding. Surgical Data Science (SDS) can provide effective context-aware tools for supporting surgeons. However, currently no tools have been exploited for automatic vessels segmentation from nephrectomy laparoscopic videos. Herein, we propose a new approach based on adversarial Fully Convolutional Neural Net- works (FCNNs) to kidney vessel segmentation from nephrectomy laparoscopic vision. Methods: The proposed approach enhances existing segmentation framework by (i) encoding 3D kernels for spatio-temporal features extraction to enforce pixel connectivity in time, and (ii) perform training in adversarial fashion, which constrains vessels shape. Results: We performed a preliminary study using 8 different RAPN videos (1871 frames), the first in the field, achieving a median Dice Similarity Coefficient of 71.76%. Conclusions: Results showed that the proposed approach could be a valuable solution with a view to assist surgeon during RAPN.

NephCNN: A Deep-Learning Framework for Vessel Segmentation in Nephrectomy Laparoscopic Videos


One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has yet to be solved completely is lane detection. Since methods for this task have to work in real-time (+30 FPS), they not only have to be effective (i.e., have high accuracy) but they also have to be efficient (i.e., fast). In this work, we present a novel method for lane detection that uses as input an image from a forward-looking camera mounted in the vehicle and outputs polynomials representing each lane marking in the image, via deep polynomial regression. The proposed method is shown to be competitive with existing state-of-the-art methods in the TuSimple dataset while maintaining its efficiency (115 FPS). Additionally, extensive qualitative results on two additional public datasets are presented, alongside with limitations in the evaluation metrics used by recent works for lane detection. Finally, we provide source code and trained models that allow others to replicate all the results shown in this paper, which is surprisingly rare in state-of-the-art lane detection methods.

PolyLaneNet: Lane Estimation via Deep Polynomial Regression

In the recognition problem, a canonical form that
expresses the spatio-temporal relation of concepts for a given
class can potentially increase accuracy. Concepts are defined as
attributes that can be recognized using a soft matching paradigm.
We consider the specific case study of American Sign Language
(ASL) to show that canonical forms of classes can be used to
recognize unseen gestures. There are several advantages of a
canonical form of gestures including translation between gestures,
gesture-based searching, and automated transcription of gestures
into any spoken language. We applied our technique to two
independently collected datasets: a) IMPACT Lab dataset: 23
ASL gestures each executed three times from 130 first time ASL
learners as training data and b) ASLTEXT dataset: 190 gestures
each executed six times on an average. Our technique was able to
recognize 19 arbitrarily chosen previously unseen gestures in the
IMPACT dataset from seven individuals who are not a part of 130
and 34 unseen gestures from the ASLTEXT dataset without any
retraining. Our normalized accuracy on the ASLTEXT dataset
is 66% which is 13.6 % higher than the state-of-art technique.

Concept Embedding through Canonical Forms: A Case Study on Zero-Shot American Sign Language Recognition

In this paper, we propose the use of Optical Coherence
Tomography (OCT) imaging for the problem of iris
presentation attack (PA) detection. We assess its viability by
comparing its performance with respect to traditional iris imaging
modalities, viz., near-infrared (NIR) and visible spectrum.
OCT imaging provides a cross-sectional view of an eye, whereas
traditional imaging provides 2D iris textural information. PA
detection is performed using three state-of-the-art deep architectures
(VGG19, ResNet50 and DenseNet121) to differentiate
between bonafide and PA samples for each of the three imaging
modalities. Experiments are performed on a dataset of 2,169
bonafide, 177 Van Dyke eyes and 360 cosmetic contact images
acquired using all three imaging modalities under intra-attack
(known PAs) and cross-attack (unknown PAs) scenarios. We
observe promising results demonstrating OCT as a viable solution
for iris presentation attack detection.

Viability of Optical Coherence Tomography for Iris Presentation Attack Detection


In this work, we tackle the problem of estimating a camera capability to preserve fine texture details at a given lighting condition. Importantly, our texture preservation measurement should coincide with human perception. Consequently, we formulate our problem as a regression one and we introduce a deep convolutional network to estimate texture quality score. At training time, we use ground-truth quality scores provided by expert human annotators in order to obtain a subjective quality measure. In addition, we propose a region selection method to identify the image regions that are better suited at measuring perceptual quality. Finally, our experimental evaluation shows that our learning-based approach outperforms existing methods and that our region selection algorithm consistently improves the quality estimation.

DR2S: Deep Regression with Region Selection for Camera Quality Evaluation

Class imbalance limits the performance of most learning algorithms, resulting in a low recognition rate for samples belonging to the minority class. Although there are different strategies to address this problem, methods that generate ensemble of classifiers have proven to be effective in several applications. This paper presents a new strategy to construct the training set of each classifier in the ensemble by exploiting information in the feature space that can give rise to unreliable classifications, which are determined by a novel algorithm here introduced. The performance of our proposal is compared against multiple standard ensemble approaches on 25 publicly available datasets, showing promising results.

Categorizing the feature space for two-class imbalance learning


Medical image segmentation has played an important
role in medical analysis and widely developed for many clinical
applications. Deep learning-based approaches have achieved
high performance in semantic segmentation but they are limited
to pixel-wise setting and imbalanced classes data problem. In
this paper, we tackle those limitations by developing a new
deep learning-based model which takes into account both higher
feature level i.e. region inside contour, intermediate feature level
i.e. offset curves around the contour and lower feature level i.e.
contour. Our proposed Offset Curves (OsC) loss consists of three
main fitting terms. The first fitting term focuses on pixel-wise level
segmentation whereas the second fitting term acts as attention
model which pays attention to the area around the boundaries
(offset curves). The third terms plays a role as regularization
term which takes the length of boundaries into account. We
evaluate our proposed OsC loss on both 2D network and 3D
network. Two common medical datasets, i.e. retina DRIVE and
brain tumor BRATS 2018 datasets are used to benchmark our
proposed loss performance. The experiments have shown that
our proposed OsC loss function outperforms other mainstream
loss functions such as Cross-Entropy, Dice, Focal on the most
common segmentation networks Unet, FCN.

Offset Curves Loss for Imbalanced Problem in Medical Segmentation

Anomaly detection in complex data structures is one of the most challenging problems in computer vision. In many real-world problems, for example in the quality control in modern manufacturing, the anomalous samples are usually rare, resulting in (highly) imbalanced datasets. However, in current research practice, these scenarios are rarely modeled, and as a consequence, evaluation of anomaly detection algorithms often do not reproduce results that are useful for practical applications. First, even in case of highly unbalanced input data, anomaly detection algorithms are expected to significantly reduce the proportion of anomalous samples, detecting ”almost all” anomalous samples (with exact specifications depending on the target customer). This places high importance on only the small part of the ROC curve, possibly rendering the standard metrics such as AUC (Area Under Curve) and AP (Average Precision) useless. Second, the target of automatic anomaly detection in practical applications is the significant reduction in manual work required, and standard metrics are poor predictor of this feature. Finally, the evaluation may produce erratic results for different randomly initialized training runs of the neural network, producing evaluation results that may not reproduce well in practice. In our presentation, we present an evaluation methodology that avoids these pitfalls.

Evaluation of Anomaly Detection Algorithms for the Real-world Applications

One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge computing makes us look for ways to reduce its time for mobile and embedded devices. One way to decrease the neural network inference time is to modify a neuron model to make it more efficient for computations on a specific device. The example of such a model is a bipolar morphological neuron model. The bipolar morphological neuron is based on the idea of replacing multiplication with addition and maximum operations. This model has been demonstrated for simple image classification with LeNet-like architectures [1]. In the paper, we introduce a bipolar morphological ResNet (BM-ResNet) model obtained from a much more complex ResNet architecture by converting its layers to bipolar morphological ones. We apply BM-ResNet to image classification on MNIST and CIFAR-10 datasets with only a moderate accuracy decrease from 99.3% to 99.1% and from 85.3% to 85.1%. We also estimate the computational complexity of the resulting model. We show that for the majority of ResNet layers, the considered model requires 2.1-2.9 times fewer logic gates for implementation and 15-30% lower latency.

Premium content

Quantifying the Use of Domain Randomization

Downloads

Next from ICPR 2020

Knowledge Distillation Beyond Model Compression

Similar lecture

Convolutional STN for Weakly Supervised Object Localization