检索结果-内蒙古大学图书馆

EfficientFCN: Holistically-guided decoding for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianbo He, Junjun Zhang, Jiawei Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SenseTime Research China

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Blueprint Separable Residual Network for Efficient Image Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Zheyuan Liu, Yingqi Chen, Xiangyu Cai, Haoming Gu, Jinjin Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Macau China Shanghai AI Laboratory Shanghai China The University of Sydney Australia

Recent advances in single image super-resolution (SISR) have achieved extraordinary performance, but the computational cost is too heavy to apply in edge devices. To alleviate this problem, many novel and effective solutions have been proposed. Convolutional neural network (CNN) with the attention mechanism has attracted increasing attention due to its efficiency and effectiveness. However, there is still redundancy in the convolution operation. In this paper, we propose Blueprint Separable Residual Network (BSRN) containing two efficient designs. One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation. The other is to enhance the model ability by introducing more effective attention modules. The experimental results show that BSRN achieves state-of-the-art performance among existing efficient SR methods. Moreover, a smaller variant of our model BSRN-S won the first place in model complexity track of NTIRE 2022 Efficient SR Challenge. The code is available at https://***/xiaom233/BSRN. Copyright © 2022, The Authors. All rights reserved.

关键词： Blueprints

Local gradient difference features for classification of 2D-3D natural scene text images 25

学校读者我要写书评

暂无评论

Local gradient difference features for classification of 2D-...

25th International Conference on pattern recognition, ICPR 2020

作者： Nandanwar, Lokesh Shivakumara, Palaiahnakote Raghavendra, Ramachandra Lu, Tong Pal, Umapada Lopresti, Daniel Anuar, Nor Badrul Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Faculty of Information Technology and Electrical Engineering IIK NTNU Norway National Key Lab for Novel Software Technology Nanjing University Nanjing China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Computer Science and Engineering Lehigh University BethlehemPA United States

ISBN: (纸本)9781728188089

Methods developed for normal 2D text detection do not work well for text that is rendered using decorative, 3D effects, etc. This paper proposes a new method for classification of 2D and 3D natural scene text images so that an appropriate recognition method can be chosen accordingly based on the classification results for better performance. The proposed method explores local gradient differences for obtaining candidate pixels, which represent a stroke. To study the spatial distribution of candidate pixels, we propose a measure, called COLD, which is denser for pixels toward the center of strokes and scattered for non-stroke pixels. This observation leads us to introduce mass features for extracting the regular spatial pattern of COLD, which indicates a 2D text image. The extracted features are fed into a Neural Network (NN) for classification. The proposed method is tested on (i) a new dataset introduced in this work (ii) a second dataset assembled from standard natural scene datasets (iii) Non-Text Image datasets which does not contain text, rather it contains objects. Experimental results of the proposed method on images with text and non-text show that the proposed method is independent of text. The proposed approach improves text detection and recognition performance significantly after classification. © 2020 IEEE

关键词： Image classification

Word-Wise Handwriting Based Gender Identification Using Multi-Gabor Response Fusion 4th

学校读者我要写书评

暂无评论

Word-Wise Handwriting Based Gender Identification Using Mult...

4th Workshop on Document Analysis and recognition, DAR 2018, held in Conjunction with the 11th Indian Conference on vision, Graphics, and Image Processing, ICVGIP 2018

作者： Asadzadeh Kaljahi, Maryam Vidya Varshini, P.V. Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Guru, D.S. Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia Vellore Institute of Technology VelloreTamil Nadu India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China Department of Studies in Computer Science Manasagangotri University of Mysuru Mysore India

ISBN: (纸本)9789811393600

Handwriting based gender identification at the word level is challenging due to free style writing, use of different scripts, and inadequate information. This paper presents a new method based on Multi-Gabor Response (MGR) fusion for gender identification at the word level. It first explores weighted-gradient features for word segmentation from text line images. For each word, the proposed method obtains eight Gabor response images. Then it performs sliding window operation over MGR images to smooth the values. For each smoothed MGR images, we perform fusion operation that chooses the Gabor response value which contributes to the highest peak in the histogram. This process results in a feature matrix, which is fed to CNN for gender identification. Experimental results on our dataset (multi scripts) apart from English, and benchmark databases, namely, IAM, KHATT, and QUWI, which contain handwritten English and Arabic text, show that the proposed method outperforms the existing methods. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Image segmentation

Blind super-resolutionwith iterative kernel correction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gu, Jinjin Lu, Hannan Zuo, Wangmeng Dong, Chao School of Science and Engineering Chinese University of Hong Kong Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Harbin China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

Deep learning based methods have dominated superresolution (SR) field due to their remarkable performance in terms of effectiveness and efficiency. Most of these methods assume that the blur kernel during downsampling is predefined/ known (e.g., bicubic). However, the blur kernels involved in real applications are complicated and unknown, resulting in severe performance drop for the advanced SR methods. In this paper, we propose an Iterative Kernel Correction (IKC) method for blur kernel estimation in blind SR problem, where the blur kernels are unknown. We draw the observation that kernel mismatch could bring regular artifacts (either over-sharpening or over-smoothing), which can be applied to correct inaccurate blur kernels. Thus we introduce an iterative correction scheme - IKC that achieves better results than direct kernel estimation. We further propose an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD. Extensive experiments on synthetic and real-world images show that the proposed IKC method with SFTMD can provide visually favorable SR results and the state-of-the-art performance in blind SR problem. Copyright © 2019, The Authors. All rights reserved.

关键词： Network architecture

Suppressing model overfitting for image super-resolution networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Feng, Ruicheng Gu, Jinjin Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences School of Science and Engineering Chinese University of Hong Kong Shenzhen Hong Kong Chinese University of Hong Kong Hong Kong

Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit undesirable behaviors such as overfitting and memorization. To suppress model overfitting and further enjoy the merits of large model capacity, we thoroughly investigate generic approaches for supplying additional training data pairs. In particular, we introduce a simple learning principle MixUp [43] to train networks on interpolations of sample pairs, which encourages networks to support linear behavior in-between training samples. In addition, we propose a data synthesis method with learned degradation, enabling models to use extra high-quality images with higher content diversity. This strategy proves to be successful in reducing biases of data. By combining these components - MixUp and synthetic training data, large models can be trained without overfitting under very limited data samples and achieve satisfactory generalization performance. Our method won the second place in NTIRE2019 Real SR Challenge. Copyright © 2019, The Authors. All rights reserved.

关键词： Optical resolving power

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

Conditional sequential modulation for efficient global image retouching

学校读者我要写书评

暂无评论

arXiv 2020年

作者： He, Jingwen Liu, Yihao Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence Robotics for Society Korea Republic of University of Chinese Academy of Sciences China

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of 1×1 convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://***/hejingwenhejingwen/CSRNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels

Activating More Pixels in Image Super-Resolution Transformer

学校读者我要写书评

暂无评论

arXiv 2022年

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

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. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels