Italy


Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large number of use scenarios in the real-world, remains a challenge because documents not only have textual features extracting from OCR systems but also have semantic visual features that are not fully exploited and play a critical role in KIE. Too little work has been devoted to efficiently make full use of both textual and visual features of the documents. In this paper, we introduce PICK, a framework that is effective and robust in handling complex document layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features and global layout without ambiguity. Extensive experiments on real-world datasets have been conducted to show that our method outperforms baseline methods by significant margins. Our code is available at https://github.com/wenwenyu/PICK-pytorch.

ICPR 2020

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks

graph convolutional networks

key information extraction

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

Video saliency detection is an important low-level task that has been used in a large range of high-level applications. In this paper, we proposed a three-stream multi-scale attentive network (TSMSAN) for saliency detection in dynamic scenes. TSMSAN integrates motion vector (MV) representation, static saliency map, and RGB information in multi-scales together into one framework on the basis of Fully Convolutional Network (FCN) and spatial attention mechanism. On the one hand, the respective motion features, spatial features, as well as scene features can provide abundant information for video saliency detection. On the other hand, spatial attention mechanism can combine features with multi-scales to focus on key information in dynamic scenes. In this manner, the proposed TSMSAN can encode the spatiotemporal features of the dynamic scene comprehensively.
We evaluate the proposed approach on two public dynamic saliency datasets. The experimental results demonstrate TSMSAN is able to achieve the state-of-the-art performance as well as excellent generalization ability. Furthermore, the proposed TSMSAN can provide more convincing video saliency information, in line with human perception.

TSMSAN: A Three-Stream Multi-Scale Attentive Network for Video Saliency Detection

Recent machine learning methods use increasingly large deep neural networks to achieve state-of-the-art results in various tasks. Network quantization can effectively reduce computation and memory costs without modifying network
structures, facilitating the deployment of deep neural networks (DNNs) on cloud and edge devices. However, most of the existing methods usually need time-consuming training or fine-tuning and access to the original training dataset that may be unavailable due to privacy or security concerns. In this paper, we present a novel
method to achieve low-precision quantization with limited data. Firstly, to reduce the complexity of per-channel quantization and degeneration of per-layer quantization, we introduce group quantization that separates the output channels into groups and processes each group independently. Secondly, to better distill
knowledge from the pre-trained FP32 model with limited data, we introduce a two-stage knowledge distillation method that divides the optimization process into blockwise optimization and joint optimization to address the limitation of layer-wise supervision and global supervision. Extensive experiments on ImageNet2012
(ResNet18/50, ShuffleNetV2, and MobileNetV2) demonstrate that the proposed approach can significantly improve the quantization model’s accuracy when only a few training samples are available. We further show that the method also extends to other computer vision architectures and tasks such as object detection.

Towards Low-bit Quantization of Deep Neural Networks with Limited Data

With the development of cheap image sensors, the amount of available image data have increased enormously, and the possibility of using crowdsourced collection methods has emerged. This calls for development of ways to handle all these data. In this paper, we present new tools that will enable efficient, flexible and robust map merging. Assuming that separate optimisations have been performed for the individual maps, we show how only relevant data can be stored in a low memory footprint representation. We use these representations to perform map merging so that the algorithm is invariant to the merging order and independent of the choice of coordinate system. The result is a robust algorithm that can be applied to several maps simultaneously. The result of a merge can also be represented with the same type of low-memory footprint format, which enables further merging and updating of the map in a hierarchical way. Furthermore, the method can perform loop closing and also detect changes in the scene between the capture of the different image sequences. Using both simulated and real data — from both a hand held mobile phone and from a drone — we verify the performance of the proposed method.

Generic Merging of Structure from Motion Maps with a Low Memory Footprint




Deep learning frameworks have been successfully applied to tackle many challenging tasks in pattern recognition and computer vision thanks to its ability to automatically extract representative features from the training data. Such type of data- driven approach, however, is subject to the criticism of too much dependency on the training set. In this research, we attempt to investigate the validity of this statement: ‘deep learning is only as good as its data’ by evaluating the performance of deep learning models using heterogeneous data sets, in which distinct representations of the same source data are employed for training/testing. We have examined three cases: low-resolution image, severely compressed input and halftone image in this work. Our preliminary results indicate that such dependency indeed exists. Classifier performance drops considerably when the model is tested with modified or transformed input. The best outcomes are obtained when the model is trained with hybrid input.

Investigation of DNN Model Robustness Using Heterogeneous Datasets


This paper presents a multi-channel Extended Depth of Field (EDF) method for digital cytology based on the stationary wavelet transform. With a coefficient selection rule adapted to a precise color recovery, a sharp image can be reconstructed even on images with transparent overlapping cells. The precision and the color fidelity of the proposed method is analyzed. Moreover, an experiment demonstrating the necessity of volume analysis in cytology to achieve precise segmentation on cell clumps is conducted, and the importance of color fidelity in this context is asserted. The proposed method was tested on pap-stained urothelial cells and gray-scale cervical cells with important overlapping.

Extended Depth of Field Preserving Color Fidelity For Automated Digital Cytology

Accurate and fine-grained information about the extent of damage to buildings is essential for directing Humanitarian Aid and Disaster Response (HADR) operations in the immediate aftermath of any natural calamity. In recent years, satellite and UAV (drone) imagery has been used for this purpose, sometimes aided by computer vision algorithms. Existing Computer Vision approaches for building damage assessment
typically rely on a two stage approach, consisting of building detection using an object detection model, followed by damage assessment through classification of the detected building tiles. These multi-stage methods are not end-to-end trainable, and
suffer from poor overall results. We propose RescueNet, a unified model that can simultaneously segment buildings and assess the damage levels to individual buildings and can be trained end-toend. In order to to model the composite nature of this problem, we propose a novel localization aware loss function, which consists
of a Binary Cross Entropy loss for building segmentation, and a foreground only selective Categorical Cross-Entropy loss for damage classification, and show significant improvement over the widely used Cross-Entropy loss. RescueNet is tested on the large scale and diverse xBD dataset and achieves significantly better building segmentation and damage classification performance than previous methods and achieves generalization across varied geographical regions and disaster types.

RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery

Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between different tasks, which may lead to task interference when training the multi-task networks. To address this problem, we propose a novel selective feature-sharing method, and establish a multi-task network for facial expression recognition and facial expression synthesis. The proposed method can effectively transfer beneficial features between different tasks, while filtering out useless and harmful information. Moreover, we employ the facial expression synthesis task to enlarge and balance the training dataset to further enhance the generalization ability of the proposed method. Experimental results show that the proposed method achieves state-of-the-art performance on those commonly used facial expression recognition benchmarks, which makes it a potential solution to real-world facial expression recognition problems.

Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing


Image inpainting faces the challenging issue of the requirements on structure reasonableness and texture coherence. In this paper, we propose a two-stage inpainting framework to address this issue. The basic idea is to address the two requirements in two separate stages. Completed segmentation of the corrupted image is firstly predicted through segmentation reconstruction network, while fine-grained image details are restored in the second stage through an image generator. The two stages are connected in series as the image details are generated under the guidance of completed segmentation map that predicted in the first stage. Specifically, in the second stage, we propose a novel graph-based relation network to model the relationship existed in corrupted image. In relation network, both intra-relationship for pixels in the same semantic region and inter-relationship between different semantic parts are considered, improving the consistency and compatibility of image textures. Besides, contrastive loss is designed to facilitate the relation network training. Such a framework not only simplifies the inpainting problem directly, but also exploits the relationship in corrupted image explicitly. Extensive experiments on various public datasets quantitatively and qualitatively demonstrate the superiority of our approach compared with the state-of-the-art.

Image Inpainting with Contrastive Relation Network

We propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning and adversarial learning. Since target data is distributed across different camera viewpoints, we propose to model each camera as an independent domain, and aim to learn domain-independent features. Straightforward adversarial learning yields negative transfer, we thus introduce a conditioning strategy to mitigate this undesirable effect. We evaluate the proposed architecture on two state-of-the-art clustering-based unsupervised person re-identification (re-ID) methods and three different data sets and set the new state-of-the-art performance on all three of them.

CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification

Deep reinforcement learning (DRL) has achieved great success in processing vision-based driving tasks. However, the end-to-end training manner makes DRL agents suffer from overfitting training scenes. The agents easily fail to generalize to unseen environments. In this paper, we propose a deep reinforcement learning for autonomous driving by transferring visual features. We formulate the DRL training as a perception and control module and introduce adversarial training mechanism for autonomous driving. The perception module is able to extract invariant features between different domains through adversarial training. While the DRL agent can then be trained on the basis of low dimensional states. In this manner, the proposed approach enables trained agents to adapt to unseen environments by learning robust features invariant across various scenes. We evaluate the proposed approach by transferring visual features between different simulators. The experimental results demonstrate the driving policy trained in the source domain can be directly applied in the target domain, and achieve great efficient and effective performance for autonomous driving.

Downloads

Next from ICPR 2020

TSMSAN: A Three-Stream Multi-Scale Attentive Network for Video Saliency Detection

Similar lecture

On-Device Text Image Super Resolution