检索结果-内蒙古大学图书馆

Reconnoitering the class distinguishing abilities of the features, to know them better

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sadhukhan, Payel Palit, Sarbani Sengupta, Kausik Institute for Advancing Intelligence Tcg Crest West Bengal Kolkata700091 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute West Bengal Kolkata700108 India

The relevance of machine learning (ML) in our daily lives is closely intertwined with its explainability. Explainability can allow end-users to have a transparent and humane reckoning of a ML scheme's capability and utility. It will also foster the user's confidence in the automated decisions of a system. Explaining the variables or features to explain a model's decision is a need of the present times. We could not really find any work, which explains the features on the basis of their class-distinguishing abilities (specially when the real world data are mostly of multi-class nature). In any given dataset, a feature is not equally good at making distinctions between the different possible categorizations (or classes) of the data points. In this work, we explain the features on the basis of their class or category-distinguishing capabilities. We particularly estimate the class-distinguishing capabilities (scores) of the variables for pair-wise class combinations. We validate the explainability given by our scheme empirically on several realworld, multi-class datasets. We further utilize the class-distinguishing scores in a latent feature context and propose a novel decision making protocol. Another novelty of this work lies with a refuse to render decision option when the latent variable (of the test point) has a high class-distinguishing potential for the likely classes. © 2022, CC BY.

关键词： Decision making

Matching individual Ladoga ringed seals across short-term image sequences (vol 102, pg 957, 2022)

学校读者我要写书评

暂无评论

MAMMALIAN BIOLOGY 2022年第3期102卷 1045-1045页

作者： Nepovinnykh, E. Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering School of Engineering Science Lappeenranta-Lahti University of Technology LUT P.O.Box 20 53851 Lappeenranta Finland Department of Artificial Intelligence Institute of Computer Science and Technology Peter the Great St. Petersburg Polytechnic University Polytechnicheskaya 29 Saint Petersburg Russian Federation 195251 Department of Computer Science and Computational Experiment Southern Federal University Rostov-on-Don Russian Federation 344006 Interregional Charitable Public Organization “Biologists for Nature Conservation” (BFNC) 24 line 3-7 Saint Petersburg Russian Federation 199106

Automated wildlife reidentification has attracted increasing attention in recent years as it provides a non-invasive tool to identify and to track individual wild animals over time. In this paper, the first steps are taken towards the automatic photo-identification of the Ladoga ringed seals (Pusa hispida ladogensis). A method is proposed that takes a sequence of images, each containing multiple individuals as the input, and produces cropped images of seals grouped based on one certain individual per group. The method starts by detecting each seal from the images and proceeds to matching the individual seals between the images. It is shown that high grouping accuracy can be obtained with a general-purpose image retrieval method on an image sequence taken from the same location within a relatively short period of time. Each resulting group contains multiple images of one individual with slightly different variations, for example, in pose and illumination. Utilizing these images simultaneously provides more information for the individual re-identification compared to the traditional approach, i.e., which utilizes just one image at a time. It is further demonstrated that a convolutional neural network based method can be used to extract the unique pelage patterns of the seals despite the low contrast. Finally, a method is proposed and experiments with the novel Ladoga ringed seals data are carried out to provide a proof-of-concept for the individual re-identification.

关键词： Animal re-identification Convolutional neural networks Instance segmentation Ladoga ringed seal Photo-identification

Activating More Pixels in Image Super-Resolution Transformer

学校读者我要写书评

暂无评论

Activating More Pixels in Image Super-Resolution Transformer

Conference on computer vision and pattern recognition (CVPR)

作者： Xiangyu Chen Xintao Wang Jiantao Zhou Yu Qiao Chao Dong State Key Laboratory of Internet of Things for Smart City University of Macau Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory ARC Lab Tencent PCG

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB.

关键词：

TREC 2020 NEWS Track Background Linking Task 29

学校读者我要写书评

暂无评论

TREC 2020 NEWS Track Background Linking Task

29th Text REtrieval Conference, TREC 2020

作者： Gautam, Rahul Mitra, Mandar Roy, Dwaipayan Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B.T.Road Kolkata700108 India

The Background Linking task is a problem that focuses on providing users with suggestions for articles to read next, when the user is reading a news article. The suggested articles should provide adequate context and background information for the article that the user is currently reading. In this paper, we describe several methods that we explored for this task, and report their results. © 2020 29th Text REtrieval Conference, TREC 2020 - Proceedings. All Rights Reserved.

关键词：

Anomaly Handwritten Text Detection for Automatic Descriptive Answer Evaluation 22

学校读者我要写书评

暂无评论

Anomaly Handwritten Text Detection for Automatic Descriptive...

Proceedings of the 2022 11th International Conference on Computing and pattern recognition

作者： Nilanjana Chatterjee Palaiahnaakote Shivakumara Umapada Pal Tong Lu Yue Lu Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Faculty of Computer Science and Information Technology University of Malaya Malaysia National Key Lab for Novel Software Technology Nanjing University China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University China

ISBN: (纸本)9781450397056

Although there are advanced technologies for character recognition, automatic descriptive answer evaluation is an open challenge for the document image analysis community due to large diversified handwritten text and answers to the question. This paper presents a novel method for detecting anomaly handwritten text in the responses written by the students to the questions. The method is proposed based on the fact that when the students are confident in answering questions, the students usually write answers legibly and neatly while they are not confident, they write sloppy writing which may not be easy for the reader to understand. To detect such anomaly handwritten text, we explore a new combination of Fourier transform and deep learning model for detecting edges. This result preserves the structure of handwritten text. For extracting features for classification of anomaly text and normal text, the proposed method studies the behavior of writing style, especially the variation at ascenders and descenders. Therefore, the proposed work draws principal axis which is invariant to rotation, scaling and some extent to distortion for the edge images. With respect to principal axis, the proposed method draws medial axis using uppermost and lowermost points. The distance between the medial axis and principal axis points are considered as feature vector. Further, the feature vector is passed to Artificial Neural Network for classification of anomaly text. The proposed method is evaluated by testing on our own dataset, standard dataset of gender identification (IAM) and handwritten forgery detection dataset (ACPR 2019). The results on different datasets show that the proposed work outperforms the existing methods.

关键词：

IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Jiancheng Zhou, Donghao Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The Chinese University of Hong Kong Hong Kong

Single-shot face anti-spoofing (FAS) is a key technique for securing face recognition systems, and it requires only static images as input. However, single-shot FAS remains a challenging and under-explored problem due to two main reasons: 1) on the data side, learning FAS from RGB images is largely context-dependent, and single-shot images without additional annotations contain limited semantic information. 2) on the model side, existing single-shot FAS models are infeasible to provide proper evidence for their decisions, and FAS methods based on depth estimation require expensive per-pixel annotations. To address these issues, a large binocular NIR image dataset (BNI-FAS) is constructed and published, which contains more than 300,000 real face and plane attack images, and an Interpretable FAS Transformer (IFAST) is proposed that requires only weak supervision to produce interpretable predictions. Our IFAST can produce pixel-wise disparity maps by the proposed disparity estimation Transformer with Dynamic Matching Attention (DMA) block. Besides, a well-designed confidence map generator is adopted to cooperate with the proposed dual-teacher distillation module to obtain the final discriminant results. The comprehensive experiments show that our IFAST can achieve state-of-the-art results on BNI-FAS, proving the effectiveness of the single-shot FAS based on binocular NIR images. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

Continuous Motion Numeral recognition Using RNN Architecture in Air-Writing Environment 5th

学校读者我要写书评

暂无评论

Continuous Motion Numeral Recognition Using RNN Architecture...

5th Asian Conference on pattern recognition, ACPR 2019

作者： Rahman, Adil Roy, Prasun Pal, Umapada Department of Information Technology Heritage Institute of Technology Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9783030414030

Air-writing, defined as character tracing in a three dimensional free space through hand gestures, is the way forward for peripheral-independent, virtual interaction with devices. While single unistroke character recognition is fairly simple, continuous writing recognition becomes challenging owing to absence of delimiters between characters. Moreover, stray hand motion while writing adds noise to the input, making accurate recognition difficult. The key to accurate recognition of air-written characters lies in noise elimination and character segmentation from continuous writing. We propose a robust and hardware-independent framework for multi-digit unistroke numeral recognition in air-writing environment. We present a sliding window based method which isolates a small segment of the spatio-temporal input from the air-writing activity for noise removal and digit segmentation. Recurrent Neural Networks (RNN) show great promise in dealing with temporal data and is the basis of our architecture. recognition of digits which have other digits as their sub-shapes is challenging. Capitalizing on how digits are commonly written, we propose a novel priority scheme to determine digit precedence. We only use sequential coordinates as input, which can be obtained from any generic camera, making our system widely accessible. Our experiments were conducted on English numerals using a combination of MNIST and Pendigits datasets along with our own air-written English numerals dataset (ISI-Air Dataset). Additionally, we have created a noise dataset to classify noise. We observe a drop in accuracy with increase in the number of digits written in a single continuous motion because of noise generated between digit transitions. However, under standard conditions, our system produced an accuracy of 98.45% and 82.89% for single and multiple digit English numerals, respectively. © Springer Nature Switzerland AG 2020.

关键词： Recurrent neural networks

PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Das, Dipayan Bhattacharya, Saumik Pal, Umapada Chanda, Sukalpa Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Dept. of Electronics and Electrical Communication Engg IIT Kharagpur India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Østfold University College Norway

—Reservoir Computing (RC) offers a viable option to deploy AI algorithms on low-end embedded system platforms. Liquid State Machine (LSM) is a bio-inspired RC model that mimics the cortical microcircuits and uses spiking neural networks (SNN) that can be directly realized on neuromorphic hardware. In this paper, we present a novel Parallelized LSM (PLSM) architecture that incorporates spatio-temporal read-out layer and semantic constraints on model output. To the best of our knowledge, such a formulation has been done for the first time in literature, and it offers a computationally lighter alternative to traditional deep-learning models. Additionally, we also present a comprehensive algorithm for the implementation of parallelizable SNNs and LSMs that are GPU-compatible. We implement the PLSM model to classify unintentional/accidental video clips, using the Oops dataset. From the experimental results on detecting unintentional action in video, it can be observed that our proposed model outperforms a self-supervised model and a fully supervised traditional deep learning model. All the implemented codes can be found at our repository https://***/anonymoussentience2020/Parallelized_LSM_for_Unintentional_Action_recognition. © 2021, CC BY-NC-ND.

关键词： Biomimetics

Video Capsule Endoscopy Classification using Focal Modulation Guided Convolutional Neural Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Srivastava, Abhishek Tomar, Nikhil Kumar Bagci, Ulas Jha, Debesh Computer Vision and Pattern Recognition Unit Indian Statistical Institute India School of Informatics and Computer Science Indira Gandhi National Open University India Department of Radiology Feinberg School of Medicine Northwestern University United States

Video capsule endoscopy is a hot topic in computer vision and medicine. Deep learning can have a positive impact on the future of video capsule endoscopy technology. It can improve the anomaly detection rate, reduce physicians’ time for screening, and aid in real-world clinical analysis. computer-Aided diagnosis (CADx) classification system for video capsule endoscopy has shown a great promise for further improvement. For example, detection of cancerous polyp and bleeding can lead to swift medical response and improve the survival rate of the patients. To this end, an automated CADx system must have high throughput and decent accuracy. In this paper, we propose FocalConvNet, a focal modulation network integrated with lightweight convolutional layers for the classification of small bowel anatomical landmarks and luminal findings. FocalConvNet leverages focal modulation to attain global context and allows global-local spatial interactions throughout the forward pass. Moreover, the convolutional block with its intrinsic inductive/learning bias and capacity to extract hierarchical features allows our FocalConvNet to achieve favourable results with high throughput. We compare our FocalConvNet with other state-of-the-art (SOTA) on Kvasir-Capsule, a large-scale VCE dataset with 44,228 frames with 13 classes of different anomalies. Our proposed method achieves the weighted F1-score, recall and Matthews correlation coefficient (MCC) of 0.6734, 0.6373 and 0.2974, respectively outperforming other SOTA methodologies. Furthermore, we report the highest throughput of 148.02 images/second rate to establish the potential of FocalConvNet in a real-time clinical environment. The code of the proposed FocalConvNet is available at https://***/ NoviceMAn-prog/FocalConvNet. © 2022, CC BY.

关键词： Modulation