Italy


The cross-media hash retrieval method is to encode multimedia data into a common binary hash space, which can effectively measure the correlation between samples from different modalities. In order to further improve the retrieval accuracy, this paper proposes an unsupervised cross-media hash retrieval method based on multi-head attention network. First of all, we use a multi-head attention network to make better matching images and texts, which contains rich semantic information. At the same time, an auxiliary similarity matrix is constructed to integrate the original neighborhood information from different modalities. Therefore, this method can capture the potential correlations between different modalities and within the same modality, so as to make up for the differences between different modalities and within the same modality. Secondly, the method is unsupervised and does not require additional semantic labels, so it has the potential to achieve large-scale cross-media retrieval.In addition, batch normalization and replacement hash code generation functions are adopted to optimize the model, and two loss functions are designed, which make the performance of this method exceed many supervised deep cross-media hash methods. Experiments on three datasets show that the average performance of this method is about 5 to 6 percentage points higher than the state-of-the-art unsupervised method, which proves the effectiveness and superiority of this method.

ICPR 2020

Cross-media Hash Retrieval using Multi-head Attention Network

cross-media retrieval.

multi-head attention network

convolutional neural network

collaborative learning

unsupervised learning

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

With this work we tackle immunofluorescence classification in renal biopsy, employing state-of-the-art Convolutional Neural Networks. In this setting, the aim of the probabilistic model is to assist an expert practitioner towards identifying the location pattern of antibody deposits within a glomerulus. Since modern neural networks often provide overconfident outputs, we stress the importance of having a reliable prediction, demonstrating that Temperature Scaling (TS), a recently introduced re-calibration technique, can be successfully applied to immunofluorescence classification in renal biopsy. Experimental results demonstrate that the designed model yields good accuracy on the specific task, and that TS is able to provide reliable probabilities, which are highly valuable for such a task given the low inter-rater agreement.

Confidence Calibration for Deep Renal Biopsy Immunofluorescence Image Classification


We propose a novel color image descriptor named Holistic and Hierarchical Order-Encoding Patterns (H2OEP) for texture classification. In H2OEP, the holistic order-encoding pattern compactly encodes color order variation tendencies for each pixel in color space. The hierarchical order-encoding pattern leverages min ordering, median ordering and max ordering to encode local neighboring relationships across different color channels. Finally, the generated order-encoding patterns are aggregated via central pixel encoding to build 3D joint histograms for image representation. Experiments on four benchmark texture databases demonstrate the effectiveness of the proposed descriptor for color texture classification.

Color Texture Description Based on Holistic and Hierarchical Order-Encoding Patterns

In this presentation we present a summary of our work on developing a specialized hardware architecture able to execute a novel deep convolutional neural network for stereo estimation in real time. We present the problem of computation complexity and propose step-by-step the development of an efficient, optimized and scalable hardware architecture to be implemented on an FPGA platform.

Porting a Convolutional Neural Network for Stereo Vision to Hardware

Adversarial Training (AT) and Virtual Adversarial Training (VAT) are the regularization techniques that train Deep Neural Networks (DNNs) with adversarial examples. In this paper, we propose xAT and xVAT that generate \textbf{multiplicative} perturbations to input examples for robust training of DNNs. Such perturbations are much more perceptible and interpretable than their \textbf{additive} counterparts exploited by AT and VAT. Furthermore, the multiplicative perturbations can be generated transductively or inductively while the standard AT and VAT only support a transductive implementation. We conduct a series of experiments that analyze the behavior of the multiplicative perturbations and demonstrate that xAT and xVAT can achieve competitive classification accuracies across multiple established benchmarks while being about 30\% faster than their additive counterparts. Furthermore, the resulting DNNs also demonstrate distinct weight distributions.

Learning with Multiplicative Perturbations

Semantic textual similarity is a fundamental task in text mining and natural language processing (NLP), which has profound research value. The essential step for text similarity is text representation learning. Recently, researches have explored the graph convolutional network (GCN) techniques on text representation, since GCN does well in handling complex structures and preserving syntactic information. However, current GCN models are usually limited to very shallow layers due to the vanishing gradient problem, which can not capture non-local dependency information of sentences. In this paper, we propose a GCNs-based context-aware (GCSTS) model that applies iterated GCN blocks to train deeper GCNs. Recurrently employing the same GCN block prevents over-fitting and provides broad effective input width. Combined with dense connections, GCSTS can be trained more deeply. Besides, we use dynamic graph structures in the block, which further extends the receptive field of each vertex in graphs, learning better sentence representations. Experiments show that our model outperforms existing models on several text similarity datasets, while also verify that GCNs-based text representation models can be trained in a deeper manner, rather than being trained in two or three layers.

GCNs-Based Context-Aware Short Text Similarity Model

In this paper, we design a novel Cascade Attention Guided Residue Learning GAN (CAR-GAN) to solve the challenging cross-modal audio-to-image translation task. Particularly, it employs cascaded attention guidance and a coarse-to-fine generation strategy. A novel residue learning model is also proposed to tackle the cross-modal class-label dis-match problem between audio and image modality. By introducing the residue module, generators learn to produce residue features between two stages, which pushes the output closer to its corresponding real image in a high-level semantic space. Finally, the proposed joint classification loss facilitates the model generation and keeps consistency in the label domain. Experimental results show the state-of-the-art performance on the cross-modal translation task.

Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation

Multi-view learning is a learning task in which data is described by several concurrent representations. Its main challenge is most often to exploit the complementarities between these representations to help solve a classification/regression task. This is a challenge that can be met nowadays if there is a large amount of data available for learning. However, this is not necessarily true for all real-world problems, where data are sometimes scarce (e.g. problems related to the medical environment). In these situations, an effective strategy is to use intermediate representations based on the dissimilarities between instances. This work presents new ways of constructing these dissimilarity representations, learning them from data with Random Forest classifiers. More precisely, two methods are proposed, which modify the Random Forest proximity measure, to adapt it to the context of High Dimension Low Sample Size (HDLSS) multi-view classification problems. The second method, based on an Instance Hardness measurement, is significantly more accurate than other state-of-the-art measurements including the original RF Proximity measurement and the Large Margin Nearest Neighbor (LMNN) metric learning measurement.

A Novel Random Forest Dissimilarity Measure for Multi-View Learning

Human action recognition is one of the challenging and active research fields due to its wide applications. Recently, graph convolutions for skeleton-based action recognition have attracted much attention. Generally, the adjacency matrices of the graph are fixed to the hand-crafted physical connectivity of the human joints, or learned adaptively via deep learning. The hand-crafted or learned adjacency matrices are fixed when processing each frame of an action sequence. However, the interactions of different subsets of joints may play a core role at different phases of an action. Therefore, it is reasonable to evolve the graph topology with time. In this paper, a recurrent graph convolution is proposed, in which the graph topology is evolved via a long short-term memory (LSTM) network. The proposed recurrent graph convolutional network (R-GCN) can recurrently learn the data-dependent graph topologies for different layers, different time steps and different kinds of actions. Experimental results on the NTU RGB+D and Kinetics-Skeleton datasets demonstrate the advantages of the proposed R-GCN.

Recurrent Graph Convolutional Networks for Skeleton-based Action Recognitions

Feature selection has become a crucial part of many classification problems in which high-dimensional datasets may contain tens of thousands of features. In this paper, we propose a novel feature selection method scoring the features through
estimating the Bayes error rate based on kernel density estimation. Additionally, we update the scores of features dynamically by quantitatively interpreting the effects of feature relevance and redundancy in a new way. Distinguishing from the common
heuristic applied by many feature selection methods, which prefers choosing features that are not relevant to each other, our approach penalizes only monotonically correlated features and rewards any other kind of relevance among features based on Spearman's rank correlation coefficient and normalized mutual information. We conduct extensive experiments on seventeen diverse classification benchmarks and the results show that our approach overperforms other seventeen popular state-of-the-art feature selection methods in most cases.

Watermelon: a Novel Feature Selection Method Based on Bayes Error Rate Estimation and a New Interpretation of Feature Relevance and Redundancy

We propose a Stable Age Translation GAN (SATGAN) to generate fake face images at different ages to augment age biased face datasets for Cross-Age Face Recognition (CAFR) . The proposed SATGAN consists of both generator and discriminator. As a part of the generator, a novel Mask Attention Module (MAM) is introduced to make the generator focus on the face area. In addition, the generator employs a Uniform Distribution Discriminator (UDD) to supervise the learning of latent feature map and enforce the uniform distribution. Besides, the discriminator employs a Feature Separation Module (FSM) to disentangle identity information from the age information.

Premium content

Cross-media Hash Retrieval using Multi-head Attention Network

Downloads

Next from ICPR 2020

Confidence Calibration for Deep Renal Biopsy Immunofluorescence Image Classification

Similar lecture

Deep Universal Blind Image Denoising