Zuheng Ming

Zuheng Ming, Zitong Yu, Musab Al-Ghadi et al.

Face Presentation Attack Detection (PAD) is an important measure to prevent spoof attacks for face biometric systems. Many works based on Convolution Neural Networks (CNNs) for face PAD formulate the problem as an image-level binary classification task without considering the context. Alternatively, Vision Transformers (ViT) using self-attention to attend the context of an image become the mainstreams in face PAD. Inspired by ViT, we propose a Video-based Transformer for face PAD (ViTransPAD) with short/long-range spatio-temporal attention which can not only focus on local details with short attention within a frame but also capture long-range dependencies over frames. Instead of using coarse image patches with single-scale as in ViT, we propose the Multi-scale Multi-Head Self-Attention (MsMHSA) architecture to accommodate multi-scale patch partitions of Q, K, V feature maps to the heads of transformer in a coarse-to-fine manner, which enables to learn a fine-grained representation to perform pixel-level discrimination for face PAD. Due to lack inductive biases of convolutions in pure transformers, we also introduce convolutions to the proposed ViTransPAD to integrate the desirable properties of CNNs by using convolution patch embedding and convolution projection. The extensive experiments show the effectiveness of our proposed ViTransPAD with a preferable accuracy-computation balance, which can serve as a new backbone for face PAD.

Souhail Bakkali, Zuheng Ming, Mickael Coustaty et al.

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a joint representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across modalities. The proposed learning objective is devised between intra- and inter-modality alignment tasks, where the similarity distribution per task is computed by contracting positive sample pairs while simultaneously contrasting negative ones in the joint representation space}. Extensive experiments on public document classification datasets demonstrate the effectiveness and the generality of our model on low-scale and large-scale datasets.

Musab Al-Ghadi, Zuheng Ming, Petra Gomez-Krämer et al.

In cases such as digital enrolment via mobile and online services, identity document verification is critical in order to efficiently detect forgery and therefore build user trust in the digital world. In this paper, an authentication model for identity documents based on forgery detection of guilloche patterns is proposed. The proposed approach is made up of two steps: feature extraction and similarity measure between a pair of feature vectors of identity documents. The feature extraction step involves learning the similarity between a pair of identity documents via a convolutional neural network (CNN) architecture and ends by extracting highly discriminative features between them. While, the similarity measure step is applied to decide if a given identity document is authentic or forged. In this work, these two steps are combined together to achieve two objectives: (i) extracted features should have good anticollision (discriminative) capabilities to distinguish between a pair of identity documents belonging to different classes, (ii) checking out the conformity of the guilloche pattern of a given identity document and its similarity to the guilloche pattern of an authentic version of the same country. Experiments are conducted in order to analyze and identify the most proper parameters to achieve higher authentication performance. The experimental results are performed on the MIDV-2020 dataset. The results show the ability of the proposed approach to extract the relevant characteristics of the processed pair of identity documents in order to model the guilloche patterns, and thus distinguish them correctly. The implementation code and the forged dataset are provided here (https://drive.google.com/id-FDGP-1)

Souhail Bakkali, Sanket Biswas, Zuheng Ming et al.

Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and often suffer a significant performance drop in real-world online industrial settings. A primary issue is their heavy reliance on OCR engines to extract local positional information within document pages, which limits the models' ability to capture global information and hinders their generalizability, flexibility, and robustness. In this paper, we introduce GlobalDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised manner using three novel pretext objective tasks. GlobalDoc improves the learning of richer semantic concepts by unifying language and visual representations, resulting in more transferable models. For proper evaluation, we also propose two novel document-level downstream VDU tasks, Few-Shot Document Image Classification (DIC) and Content-based Document Image Retrieval (DIR), designed to simulate industrial scenarios more closely. Extensive experimentation has been conducted to demonstrate GlobalDoc's effectiveness in practical settings.

Bo Zhang, Zuheng Ming, Wei Feng et al.

To benefit the complementary information between heterogeneous data, we introduce a new Multimodal Transformer (MMFormer) for Remote Sensing (RS) image classification using Hyperspectral Image (HSI) accompanied by another source of data such as Light Detection and Ranging (LiDAR). Compared with traditional Vision Transformer (ViT) lacking inductive biases of convolutions, we first introduce convolutional layers to our MMFormer to tokenize patches from multimodal data of HSI and LiDAR. Then we propose a Multi-scale Multi-head Self-Attention (MSMHSA) module to address the problem of compatibility which often limits to fuse HSI with high spectral resolution and LiDAR with relatively low spatial resolution. The proposed MSMHSA module can incorporate HSI to LiDAR data in a coarse-to-fine manner enabling us to learn a fine-grained representation. Extensive experiments on widely used benchmarks (e.g., Trento and MUUFL) demonstrate the effectiveness and superiority of our proposed MMFormer for RS image classification.

Minh-Duc Vu, Zuheng Ming, Fangchen Feng et al.

Object detection in remote sensing imagery plays a vital role in various Earth observation applications. However, unlike object detection in natural scene images, this task is particularly challenging due to the abundance of small, often barely visible objects across diverse terrains. To address these challenges, multimodal learning can be used to integrate features from different data modalities, thereby improving detection accuracy. Nonetheless, the performance of multimodal learning is often constrained by the limited size of labeled datasets. In this paper, we propose to use Masked Image Modeling (MIM) as a pre-training technique, leveraging self-supervised learning on unlabeled data to enhance detection performance. However, conventional MIM such as MAE which uses masked tokens without any contextual information, struggles to capture the fine-grained details due to a lack of interactions with other parts of image. To address this, we propose a new interactive MIM method that can establish interactions between different tokens, which is particularly beneficial for object detection in remote sensing. The extensive ablation studies and evluation demonstrate the effectiveness of our approach.

Taifour Yousra, Beghdadi Azeddine, Marie Luong et al.

Low-dose CT (LDCT) imaging is widely used to reduce radiation exposure to mitigate high exposure side effects, but often suffers from noise and artifacts that affect diagnostic accuracy. To tackle this issue, deep learning models have been developed to enhance LDCT images. Various loss functions have been employed, including classical approaches such as Mean Square Error and adversarial losses, as well as customized loss functions(LFs) designed for specific architectures. Although these models achieve remarkable performance in terms of PSNR and SSIM, these metrics are limited in their ability to reflect perceptual quality, especially for medical images. In this paper, we focus on one of the most critical elements of DL-based architectures, namely the loss function. We conduct an objective analysis of the relevance of different loss functions for LDCT image quality enhancement and their consistency with image quality metrics. Our findings reveal inconsistencies between LFs and quality metrics, and highlight the need of consideration of image quality metrics when developing a new loss function for image quality enhancement.

Bissmella Bahaduri, Zuheng Ming, Fangchen Feng et al.

Object detection in Remote Sensing Images (RSI) is a critical task for numerous applications in Earth Observation (EO). Differing from object detection in natural images, object detection in remote sensing images faces challenges of scarcity of annotated data and the presence of small objects represented by only a few pixels. Multi-modal fusion has been determined to enhance the accuracy by fusing data from multiple modalities such as RGB, infrared (IR), lidar, and synthetic aperture radar (SAR). To this end, the fusion of representations at the mid or late stage, produced by parallel subnetworks, is dominant, with the disadvantages of increasing computational complexity in the order of the number of modalities and the creation of additional engineering obstacles. Using the cross-attention mechanism, we propose a novel multi-modal fusion strategy for mapping relationships between different channels at the early stage, enabling the construction of a coherent input by aligning the different modalities. By addressing fusion in the early stage, as opposed to mid or late-stage methods, our method achieves competitive and even superior performance compared to existing techniques. Additionally, we enhance the SWIN transformer by integrating convolution layers into the feed-forward of non-shifting blocks. This augmentation strengthens the model's capacity to merge separated windows through local attention, thereby improving small object detection. Extensive experiments prove the effectiveness of the proposed multimodal fusion module and the architecture, demonstrating their applicability to object detection in multimodal aerial imagery.

Zuheng Ming, Jean-Christophe Burie, Muhammad Muzzamil Luqman

Rather than the visual images, the face recognition of the caricatures is far from the performance of the visual images. The challenge is the extreme non-rigid distortions of the caricatures introduced by exaggerating the facial features to strengthen the characters. In this paper, we propose dynamic multi-task learning based on deep CNNs for cross-modal caricature-visual face recognition. Instead of the conventional multi-task learning with fixed weights of the tasks, the proposed dynamic multi-task learning dynamically updates the weights of tasks according to the importance of the tasks, which enables the training of the networks focus on the hard task instead of being stuck in the overtraining of the easy task. The experimental results demonstrate the effectiveness of the dynamic multi-task learning for caricature-visual face recognition. The performance evaluated on the datasets CaVI and WebCaricature show the superiority over the state-of-art methods. The implementation code is available here.

Tanmoy Mondal, Abhijit Das, Zuheng Ming

In this work, we adhere to explore a Multi-Tasking learning (MTL) based network to perform document attribute classification such as the font type, font size, font emphasis and scanning resolution classification of a document image. To accomplish these tasks, we operate on either segmented word level or on uniformed size patches randomly cropped out of the document. Furthermore, a hybrid convolution neural network (CNN) architecture "MTL+MI", which is based on the combination of MTL and Multi-Instance (MI) of patch and word is used to accomplish joint learning for the classification of the same document attributes. The contribution of this paper are three fold: firstly, based on segmented word images and patches, we present a MTL based network for the classification of a full document image. Secondly, we propose a MTL and MI (using segmented words and patches) based combined CNN architecture ("MTL+MI") for the classification of same document attributes. Thirdly, based on the multi-tasking classifications of the words and/or patches, we propose an intelligent voting system which is based on the posterior probabilities of each words and/or patches to perform the classification of document's attributes of complete document image.

Zuheng Ming, Muriel Visani, Muhammad Muzzamil Luqman et al.

The widespread deployment of face recognition-based biometric systems has made face Presentation Attack Detection (face anti-spoofing) an increasingly critical issue. This survey thoroughly investigates the face Presentation Attack Detection (PAD) methods, that only require RGB cameras of generic consumer devices, over the past two decades. We present an attack scenario-oriented typology of the existing face PAD methods and we provide a review of over 50 of the most recent face PAD methods and their related issues. We adopt a comprehensive presentation of the methods that have most influenced face PAD following the proposed typology, and in chronological order. By doing so, we depict the main challenges, evolutions and current trends in the field of face PAD, and provide insights on its future research. From an experimental point of view, this survey paper provides a summarized overview of the available public databases and extensive comparative experimental results of different PAD methods.

Zuheng Ming, Jean-Christophe Burie, Muhammad Muzzamil Luqman

Face recognition of realistic visual images has been well studied and made a significant progress in the recent decade. Unlike the realistic visual images, the face recognition of the caricatures is far from the performance of the visual images. This is largely due to the extreme non-rigid distortions of the caricatures introduced by exaggerating the facial features to strengthen the characters. The heterogeneous modalities of the caricatures and the visual images result the caricature-visual face recognition is a cross-modal problem. In this paper, we propose a method to conduct caricature-visual face recognition via multi-task learning. Rather than the conventional multi-task learning with fixed weights of tasks, this work proposes an approach to learn the weights of tasks according to the importance of tasks. The proposed multi-task learning with dynamic tasks weights enables to appropriately train the hard task and easy task instead of being stuck in the over-training easy task as conventional methods. The experimental results demonstrate the effectiveness of the proposed dynamic multi-task learning for cross-modal caricature-visual face recognition. The performances on the datasets CaVI and WebCaricature show the superiority over the state-of-art methods.

Souhail Bakkali, Zuheng Ming, Muhammad Muzzamil Luqman et al.

Benefiting from the advance of deep convolutional neural network approaches (CNNs), many face detection algorithms have achieved state-of-the-art performance in terms of accuracy and very high speed in unconstrained applications. However, due to the lack of public datasets and due to the variation of the orientation of face images, the complex background and lighting, defocus and the varying illumination of camera captured images, face detection on identity documents under unconstrained environments has not been sufficiently studied. To address this problem more efficiently, we survey three state-of-the-art face detection methods based on general images, i.e. Cascade-CNN, MTCNN and PCN, for face detection in camera captured images of identity documents, given different image quality assessments. For that, The MIDV-500 dataset, which is the largest and most challenging dataset for identity documents, is used to evaluate the three methods. The evaluation results show the performance and the limitations of the current methods for face detection on identity documents under the wild complex environments. These results show that the face detection task in camera captured images of identity documents is challenging, providing a space to improve in the future works.

Zuheng Ming, Junshi Xia, Muhammad Muzzamil Luqman et al.

Benefiting from the joint learning of the multiple tasks in the deep multi-task networks, many applications have shown the promising performance comparing to single-task learning. However, the performance of multi-task learning framework is highly dependant on the relative weights of the tasks. How to assign the weight of each task is a critical issue in the multi-task learning. Instead of tuning the weights manually which is exhausted and time-consuming, in this paper we propose an approach which can dynamically adapt the weights of the tasks according to the difficulty for training the task. Specifically, the proposed method does not introduce the hyperparameters and the simple structure allows the other multi-task deep learning networks can easily realize or reproduce this method. We demonstrate our approach for face recognition with facial expression and facial expression recognition from a single input image based on a deep multi-task learning Conventional Neural Networks (CNNs). Both the theoretical analysis and the experimental results demonstrate the effectiveness of the proposed dynamic multi-task learning method. This multi-task learning with dynamic weights also boosts of the performance on the different tasks comparing to the state-of-art methods with single-task learning.

Zuheng Ming, Junshi Xia, Muhammad Muzzamil Luqman et al.

This paper proposes a holistic multi-task Convolutional Neural Networks (CNNs) with the dynamic weights of the tasks,namely FaceLiveNet+, for face authentication. FaceLiveNet+ can employ face verification and facial expression recognition as a solution of liveness control simultaneously. Comparing to the single-task learning, the proposed multi-task learning can better capture the feature representation for all of the tasks. The experimental results show the superiority of the multi-task learning to the single-task learning for both the face verification task and facial expression recognition task. Rather using a conventional multi-task learning with fixed weights for the tasks, this work proposes a so called dynamic-weight-unit to automatically learn the weights of the tasks. The experiments have shown the effectiveness of the dynamic weights for training the networks. Finally, the holistic evaluation for face authentication based on the proposed protocol has shown the feasibility to apply the FaceLiveNet+ for face authentication.