检索结果-内蒙古大学图书馆

Low-Cost Automated visual Screw Inspection System

学校读者我要写书评

暂无评论

Low-Cost Automated Visual Screw Inspection System

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Li, Yiran Li, Jiayi Yang, Xiaoying Li, Cheng'ao Xiong, Xihan Fang, Yutong Ding, Shusheng Cui, Tianxiang School of Computer Science University of Nottingham Ningbo China Ningbo China School of Aerospace Engineering University of Nottingham Ningbo China Ningbo China Imperial College London Deparment of Computing London United Kingdom Ningbo Open University Teaching Research Center Ningbo China Business School Ningbo University Ningbo China

ISBN: (纸本)9781665430654

Despite the significant achievements in the development of automation technologies, the application of autonomous robots to improve the production efficiency of small-scale indus-tries has been largely ignored. While there has been excellent progress in industrial image processing systems implementation, most of the work has focused on a unique aspect of specific objects rather than introducing a general inspection system. Thus, this paper discusses the critical industrial topic of quality control, which develops rapidly through the use of autonomous systems. Given the high cost of implementing automated systems, this paper presents an affordable low-budget solution for the visual inspection system. This method of inspecting screw dimensions consists of four visual inspection parts and a special mechanical supporting structure. The designed system was able to check the overall screw dimensions, including screw head diameter, screw head driven type, screw length, screw thread length, and screw head thickness. It could also separate the qualified screws from the unqualified ones after the inspection process. The accuracy of most inspection cases is 100%, meaning the error ranges within 0.1mm, which meets all the non-negotiable requirements and most of the target requirements. The visual inspection parts can be further enhanced by building a template matching library that includes different angles of the screw head or by using Hough Transform to identify the defect types of the screw thread. © 2023 IEEE.

关键词： Automated quality control computer-assisted visual inspection Industrial computer vision Low-cost

Downstream Task-agnostic Transferable Attacks on Language-Image Pre-training Models

学校读者我要写书评

暂无评论

Downstream Task-agnostic Transferable Attacks on Language-Im...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yiqiang Lv Jingjing Chen Zhipeng Wei Kai Chen Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing

Vision-language pre-trained models (e.g., CLIP) trained on large-scale datasets via self-supervised learning, are drawing increasing research attention since they can achieve superior performances on multi-modal downstream tasks. Nevertheless, we find that the adversarial perturbations crafted on vision-language pre-trained models can be used to attack different corresponding downstream task models. Specifically, to investigate such adversarial transferability, we introduce a task-agnostic method named Global and Local Augmentation (GLA) attack to generate highly transferable adversarial examples on CLIP, to attack black-box downstream task models. GLA adopts random crop and resize at both global and local patch levels, to create more diversity and make adversarial noises robust. Then GLA generates the adversarial perturbations by minimizing the cosine similarity between intermediate features from augmented adversarial and benign examples. Extensive experiments on three CLIP image encoders with different backbones and three different downstream tasks demonstrate the superiority of our method compared with other strong baselines. The code is available at https://***/yqlvcoding/GLAattack.

关键词：

GenRec: unifying video generation and recognition with diffusion models 24

学校读者我要写书评

暂无评论

GenRec: unifying video generation and recognition with diffu...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zejia Weng Xitong Yang Zhen Xing Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University and Shanghai Collaborative Innovation Center of Intelligent Visual Computing Department of Computer Science University of Maryland

ISBN: (纸本)9798331314385

Video diffusion models are able to generate high-quality videos by learning strong spatial-temporal priors on large-scale datasets. In this paper, we aim to investigate whether such priors derived from a generative process are suitable for video recognition, and eventually joint optimization of generation and recognition. Building upon Stable Video Diffusion, we introduce GenRec, the first unified framework trained with a random-frame conditioning process so as to learn generalized spatial-temporal representations. The resulting framework can naturally supports generation and recognition, and more importantly is robust even when visual inputs contain limited information. Extensive experiments demonstrate the efficacy of GenRec for both recognition and generation. In particular, GenRec achieves competitive recognition performance, offering 75.8% and 87.2% accuracy on SSV2 and K400, respectively. GenRec also performs the best on class-conditioned image-to-video generation, achieving 46.5 and 49.3 FVD scores on SSV2 and EK-100 datasets. Furthermore, GenRec demonstrates extraordinary robustness in scenarios that only limited frames can be observed. Code will be available at https://***/wengzejia1/GenRec.

关键词：

End-to-end Optimized Lossy Compression for Neural-morphic Spiking Camera Captured Data

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 6074-6086页

作者： Feng, Kexiang Jia, Chuanmin Pan, Jingshan Ma, Siwei Gao, Wen Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Peking University National Engineering Research Center of Visual Technology Beijing100871 China Peking University Wangxuan Institute of Computer Technology Beijing100080 China Shandong Computer Science Center National Supercomputer in Jinan Jinan250014 China Peking University National Engineering Research Center of Visual Technology School of Computer Science Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China

Recently, the bio-inspired spike camera with continuous motion recording capability has attracted tremendous attention due to its ultra high temporal resolution imaging characteristic. Such imaging feature results in huge data storage and transmission burden compared to that of traditional camera, raising severe challenge and imminent necessity in compression for spike camera captured content. Existing lossy data compression methods could not be applied for compressing spike streams efficiently due to integrate-and-fire characteristic and binarized data structure. Considering the imaging principle and information fidelity of spike cameras, we propose a novel Reconstruction-based Contextual Spike Compression (RCSC) framework, which contains scene reconstruction, contextual image compression and spike generation. To our knowledge, it is the first learning-based model for efficient and robust spike stream compression with informative fidelity. Extensive experimental results show that our model outperforms the state-of-the-art conventional codec VVC intra by 6.14% and surpasses the state-of-the-art learned codec by 2.53% in BD-rate reduction, establishing a strong baseline for spike compression. © 1991-2012 IEEE.

关键词： Image compression

TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Tianlun Chen, Zhineng Bai, Jinfeng Xie, Hongtao Jiang, Yu-Gang Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Fudan University China Tomorrow Advance Life China University of Science and Technology of China China

Text irregularities pose significant challenges to scene text recognizers. Thin-Plate Spline (TPS)based rectification is widely regarded as an effective means to deal with them. Currently, the calculation of TPS transformation parameters purely depends on the quality of regressed text borders. It ignores the text content and often leads to unsatisfactory rectified results for severely distorted text. In this work, we introduce TPS++, an attention-enhanced TPS transformation that incorporates the attention mechanism to text rectification for the first time. TPS++ formulates the parameter calculation as a joint process of foreground control point regression and content-based attention score estimation, which is computed by a dedicated designed gated-attention block. TPS++ builds a more flexible content-aware rectifier, generating a natural text correction that is easier to read by the subsequent recognizer. Moreover, TPS++ shares the feature backbone with the recognizer in part and implements the rectification at feature-level rather than image-level, incurring only a small overhead in terms of parameters and inference time. Experiments on public benchmarks show that TPS++ consistently improves the recognition and achieves state-of-the-art accuracy. Meanwhile, it generalizes well on different backbones and recognizers. Code is at https://***/simplify23/TPS PP. Copyright © 2023, The Authors. All rights reserved.

关键词： Character recognition

Learning to Rank Patches for Unbiased Image Redundancy Reduction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Luo, Yang Chen, Zhineng Zhou, Peng Wu, Zuxuan Gao, Xieping Jiang, Yu-Gang School of Computer Science Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China University of Maryland College Park United States College of Information Science and Engineering Hunan Normal University China

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods rely on supervisory signals. They may compel models to preserve content that aligns with labeled categories and discard content belonging to unlabeled categories. This categorical inductive bias makes these methods less effective in real-world scenarios. To address this issue, we propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches (LTRP). We observe that image reconstruction of masked image modeling models is sensitive to the removal of visible patches when the masking ratio is high (e.g., 90%). Building upon it, we implement LTRP via two steps: inferring the semantic density score of each patch by quantifying variation between reconstructions with and without this patch, and learning to rank the patches with the pseudo score. The entire process is self-supervised, thus getting out of the dilemma of categorical inductive bias. We design extensive experiments on different datasets and tasks. The results demonstrate that LTRP outperforms both supervised and other self-supervised methods due to the fair assessment of image content. Code is available at https://***/irsLu/ltrp. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Retrieval Augmented Recipe Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Guoshan Yin, Hailong Zhu, Bin Chen, Jingjing Ngo, Chong-Wah Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Singapore Management University Singapore

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallucinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset. © 2024, CC BY-NC-ND.

关键词： Food ingredients

An Optimization Method of Primer Design Based on Attention-BiLSTM 2

学校读者我要写书评

暂无评论

An Optimization Method of Primer Design Based on Attention-B...

2nd International Conference on Robotics, Artificial Intelligence and Intelligent Control, RAIIC 2023

作者： Bai, Binhao Long, Jinyu Yang, Zhibo Li, Junli Wei, Ping Sichuan Normal University College of Computer Science Chengdu China Sichuan Normal University Visual Computing and Virtual Reality Key Laboratory of Sichuan Chengdu China Sichuan Center of Translational Medicine Sichuan Key Laboratory of Translational Medicine of Traditional Chinese Medicine Sichuan Academy of Traditional Chinese Medicine Chengdu China

ISBN: (纸本)9798350328004

In this paper, we propose a method to predict the success of primer amplification based on the relationship existing between the sequence of primer and template, which can optimize the primer design and select the primer with better amplification from the candidate primer set. The double-stranded structure between primer and template nucleotide sequences is represented here by a number of words, each consisting of five characters that form sentences, as the dataset for the experiment, which is learned using an attention-based mechanism of bidirectional long short-term memory neural network model (Attention-BiLSTM), and then predicts primer amplification. The model predicted the results of polymerase chain reaction (PCR) involving specific primers and specific DNA templates with 82% accuracy, an improvement of about 2% over the performance of the LSTM with more stable value. These results show that the model can be used to effectively predict the results of PCR. This is the first paper to optimize primer design by screening the candidate primer set with a neural network model. © 2023 IEEE.

关键词： Neural network models

Deformable Mixer Transformer with Gating for Multi-Task Learning of Dense Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Yangyang Yang, Yibo Ghanem, Bernard Zhang, Lefei Du, Bo Tao, Dacheng School of Computer Science Wuhan University Wuhan China Visual Computing Center King Abdullah University of Science and Technology Jeddah Saudi Arabia Sydney Ai Centre School of Computer Science The University of Sydney Sydney Australia

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer with shared gating for multi-task learning of dense prediction. This combination may offer a simple and efficient solution owing to its powerful and flexible task-specific learning and advantages of lower cost, less complexity and smaller parameters than the traditional MTL methods. We introduce deformable mixer Transformer with gating (DeMTG), a simple and effective encoder-decoder architecture up-to-date that incorporates the convolution and attention mechanism in a unified network for MTL. It is exquisitely designed to use advantages of each block, and provide deformable and comprehensive features for all tasks from local and global perspective. First, the deformable mixer encoder contains two types of operators: the channel-aware mixing operator leveraged to allow communication among different channels, and the spatial-aware deformable operator with deformable convolution applied to efficiently sample more informative spatial locations. Second, the taskaware gating transformer decoder is used to perform the task-specific predictions, in which task interaction block integrated with self-attention is applied to capture task interaction features, and the task query block integrated with gating attention is leveraged to select corresponding task-specific features. Further, the experiment results demonstrate that the proposed DeMTG uses fewer GFLOPs and significantly outperforms current Transformer-based and CNN-based competitive models on a variety of metrics on three dense prediction datasets (i.e., NYUD-v2, PASCAL-Context, and Cityscapes). For example, by using Swin-L as a backbone, our method achieves 57.55 mIoU segmentation

关键词： Forecasting