Arindam Das

Bio: Arindam Das is an academic researcher from Valeo. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 4, co-authored 26 publications receiving 99 citations. Previous affiliations of Arindam Das include HCL Technologies & Xerox.

Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks

Abstract: In this article, a region-based Deep Convolutional Neural Network framework is presented for document structure learning. The contribution of this work involves efficient training of region based classifiers and effective ensembling for document image classification. A primary level of ‘inter-domain’ transfer learning is used by exporting weights from a pre-trained VGG16 architecture on the ImageNet dataset to train a document classifier on whole document images. Exploiting the nature of region based influence modelling, a secondary level of ‘intra-domain’ transfer learning is used for rapid training of deep learning models for image segments. Finally, a stacked generalization based ensembling is utilized for combining the predictions of the base deep neural network models. The proposed method achieves state-of-the-art accuracy of 92.21% on the popular RVL-CDIP document image dataset, exceeding the benchmarks set by the existing algorithms.

Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks

Abstract: In this work, a region-based Deep Convolutional Neural Network framework is proposed for document structure learning The contribution of this work involves efficient training of region based classifiers and effective ensembling for document image classification A primary level of `inter-domain' transfer learning is used by exporting weights from a pre-trained VGG16 architecture on the ImageNet dataset to train a document classifier on whole document images Exploiting the nature of region based influence modelling, a secondary level of `intra-domain' transfer learning is used for rapid training of deep learning models for image segments Finally, stacked generalization based ensembling is utilized for combining the predictions of the base deep neural network models The proposed method achieves state-of-the-art accuracy of 922% on the popular RVL-CDIP document image dataset, exceeding benchmarks set by existing algorithms

Generalized stacking of layerwise-trained Deep Convolutional Neural Networks for document image classification

Abstract: This article presents our recent study of a lightweight Deep Convolutional Neural Network (DCNN) architecture for document image classification. Here, we concentrated on training of a committee of generalized, compact and powerful base DCNNs. A support vector machine (SVM) is used to combine the outputs of individual DCNNs. The main novelty of the present study is introduction of supervised layerwise training of DCNN architecture in document classification tasks for better initialization of weights of individual DCNNs. Each DCNN of the committee is trained for a specific part or the whole document. Also, here we used the principle of generalized stacking for combining the normalized outputs of all the members of the DCNN committee. The proposed document classification strategy has been tested on the well-known Tobacco3482 document image dataset. Results of our experimentations show that the proposed strategy involving a considerably smaller network architecture can produce comparable document classification accuracies in competition with the state-of-the-art architectures making it more suitable for use in comparatively low configuration mobile devices.

TiledSoilingNet: Tile-level Soiling Detection on Automotive Surround-view Cameras Using Coverage Metric

Abstract: Automotive cameras, particularly surround-view cameras, tend to get soiled by mud, water, snow, etc. For higher levels of autonomous driving, it is necessary to have a soiling detection algorithm which will trigger an automatic cleaning system. Localized detection of soiling in an image is necessary to control the cleaning system. It is also necessary to enable partial functionality in unsoiled areas while reducing confidence in soiled areas. Although this can be solved using a semantic segmentation task, we explore a more efficient solution targeting deployment in low power embedded system. We propose a novel method to regress the area of each soiling type within a tile directly. We refer to this as coverage. The proposed approach is better than learning the dominant class in a tile as multiple soiling types occur within a tile commonly. It also has the advantage of dealing with coarse polygon annotation, which will cause the segmentation task. The proposed soiling coverage decoder is an order of magnitude faster than an equivalent segmentation decoder. We also integrated it into an object detection and semantic segmentation multi-task model using an asynchronous back-propagation algorithm. A portion of the dataset used will be released publicly as part of our WoodScape dataset to encourage further research.

Spatio-Contextual Deep Network Based Multimodal Pedestrian Detection For Autonomous Driving.

Abstract: Pedestrian Detection is the most critical module of an Autonomous Driving system. Although a camera is commonly used for this purpose, its quality degrades severely in low-light night time driving scenarios. On the other hand, the quality of a thermal camera image remains unaffected in similar conditions. This paper proposes an end-to-end multimodal fusion model for pedestrian detection using RGB and thermal images. Its novel spatio-contextual deep network architecture is capable of exploiting the multimodal input efficiently. It consists of two distinct deformable ResNeXt-50 encoders for feature extraction from the two modalities. Fusion of these two encoded features takes place inside a multimodal feature embedding module (MuFEm) consisting of several groups of a pair of Graph Attention Network and a feature fusion unit. The output of the last feature fusion unit of MuFEm is subsequently passed to two CRFs for their spatial refinement. Further enhancement of the features is achieved by applying channel-wise attention and extraction of contextual information with the help of four RNNs traversing in four different directions. Finally, these feature maps are used by a single-stage decoder to generate the bounding box of each pedestrian and the score map. We have performed extensive experiments of the proposed framework on three publicly available multimodal pedestrian detection benchmark datasets, namely KAIST, CVC-14, and UTokyo. The results on each of them improved the respective state-of-the-art performance. A short video giving an overview of this work along with its qualitative results can be seen at this https URL.

LayoutLM: Pre-training of Text and Layout for Document Image Understanding

Abstract: Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the LayoutLM to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents. Furthermore, we also leverage image features to incorporate words' visual information into LayoutLM. To the best of our knowledge, this is the first time that text and layout are jointly learned in a single framework for document-level pre-training. It achieves new state-of-the-art results in several downstream tasks, including form understanding (from 70.72 to 79.27), receipt understanding (from 94.02 to 95.24) and document image classification (from 93.07 to 94.42). The code and pre-trained LayoutLM models are publicly available at https://aka.ms/layoutlm.

A Saliency-Based Convolutional Neural Network for Table and Chart Detection in Digitized Documents

Abstract: Within the realm of information extraction from documents, detection of tables and charts is particularly needed as they contain a visual summary of the most valuable information contained in a document. For a complete automation of the visual information extraction process from tables and charts, it is necessary to develop techniques that localize them and identify precisely their boundaries. In this paper we aim at solving the table/chart detection task through an approach that combines deep convolutional neural networks, graphical models and saliency concepts. In particular, we propose a saliency-based fully-convolutional neural network performing multi-scale reasoning on visual cues followed by a fully-connected conditional random field (CRF) for localizing tables and charts in digital/digitized documents. Performance analysis, carried out on an extended version of the ICDAR 2013 (with annotated charts as well as tables) dataset, shows that our approach yields promising results, outperforming existing models.

Multimodal deep networks for text and image-based document classification

Abstract: Classification of document images is a critical step for accelerating archival of old manuscripts, online subscription and administrative procedures. Computer vision and deep learning have been suggested as a first solution to classify documents based on their visual appearance. However, achieving the fine-grained classification that is required in real-world setting cannot be achieved by visual analysis alone. Often, the relevant information is in the actual text content of the document, although this text is not available in digital form. In this work, we introduce a novel pipeline based on off-the-shelf architectures to deal with document classification by taking into account both text and visual information. We design a multimodal neural network that is able to learn both the image and from word embeddings, computed on noisy text extracted by OCR. We show that this approach allows us to improve single-modality classification accuracy by several points on the small Tobacco3482 and large RVL-CDIP datasets, even without clean text information. We release a post-OCR text classification (https://github.com/Quicksign/ocrized-text-dataset) that complements the Tobacco3482 and RVL-CDIP ones to encourage researchers to look into multi-modal text/image classification.

Epileptic Signal Classification With Deep EEG Features by Stacked CNNs

Abstract: The scalp electroencephalogram (EEG)-based epileptic seizure/nonseizure detection has been comprehensively studied, and fruitful achievements have been reported in the past. Yet, few investigations have been paid to the preictal stage detection, which is practically more crucial to epileptics in taking precautions before seizure onset. In this article, a novel epileptic preictal state classification and seizure detection algorithm based on deep features learned by stacked convolutional neural networks (SCNNs) is developed. The mean amplitude of sub-band spectrum map (MAS) obtained from the average sub-band spectra of multichannel EEGs is adopted for representation. The probability feature vectors by stacked convolutional neural networks (CNNs) are extracted in the softmax layer of CNNs, where an adaptive and discriminative feature weighting fusion (AWF) is developed for performance enhancement. Following the deep extraction layer, the effective kernel extreme learning machine (KELM) is adopted for feature learning and epileptic classification. Experiments on the benchmark CHB-MIT database and a real recorded epileptic database are conducted for performance demonstration. Comparisons to many state-of-the-art epileptic classification methods are provided to show the superiority of the proposed SCNN+AWF algorithm.

Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks

Abstract: In this article, a region-based Deep Convolutional Neural Network framework is presented for document structure learning. The contribution of this work involves efficient training of region based classifiers and effective ensembling for document image classification. A primary level of ‘inter-domain’ transfer learning is used by exporting weights from a pre-trained VGG16 architecture on the ImageNet dataset to train a document classifier on whole document images. Exploiting the nature of region based influence modelling, a secondary level of ‘intra-domain’ transfer learning is used for rapid training of deep learning models for image segments. Finally, a stacked generalization based ensembling is utilized for combining the predictions of the base deep neural network models. The proposed method achieves state-of-the-art accuracy of 92.21% on the popular RVL-CDIP document image dataset, exceeding the benchmarks set by the existing algorithms.