检索结果-内蒙古大学图书馆

Diabetic Retinopathy Grading with Weakly-Supervised Lesion Priors

学校读者我要写书评

暂无评论

Diabetic Retinopathy Grading with Weakly-Supervised Lesion P...

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Junlin Hou Fan Xiao Jilan Xu Rui Feng Yuejie Zhang Haidong Zou Lina Lu Wenwen Xue School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Shanghai Eye Diseases Prevention & Treatment Center Shanghai China

Explicit information of lesions can provide visual instructions for diabetic retinopathy (DR) grading on fundus images. However, pixel-level lesion annotations are extremely difficult and time-consuming to acquire. In this work, we propose a novel weakly-supervised lesion-aware network for DR grading, which enhances the discriminative features with lesion priors by only image-level supervision. Specifically, we design a lesion attention module that generates lesion activation maps by introducing an auxiliary task of binary DR identification. Lesion activation maps are utilized to assist the network to focus on the most relevant regions for boosting DR grading performance. Besides, we particularly devise an adaptive joint loss to balance the DR identification and DR grading tasks dynamically. Extensive results on the public DR dataset demonstrate the superiority and generality of our proposed lesion-aware network. The interpretability of generated lesion activation maps is also verified by the comparison with ground truth segmentation masks.

关键词： Visualization Image segmentation Retinopathy Annotations Signal processing Boosting Diabetes

MOTION MATTERS: A NOVEL MOTION MODELING FOR CROSS-VIEW GAIT FEATURE LEARNING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jingqi Gao, Jiaqi Zhang, Yuzhen Shan, Hongming Zhang, Junping Shanghai Key Lab of Intelligent Information Processing School of Computer Science China Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China

As a unique biometric that can be perceived at a distance, gait has broad applications in person authentication, social security and so on. Existing gait recognition methods suffer from changes in viewpoint and clothing and barely consider extracting diverse motion features, a fundamental characteristic in gaits, from gait sequences. This paper proposes a novel motion modeling method to extract the discriminative and robust representation. Specifically, we first extract the motion features from the encoded motion sequences in the shallow layer. Then we continuously enhance the motion feature in deep layers. This motion modeling approach is independent of mainstream work in building network architectures. As a result, one can apply this motion modeling method to any backbone to improve gait recognition performance. In this paper, we combine motion modeling with one commonly used backbone (GaitGL) as GaitGL-M to illustrate motion modeling. Extensive experimental results on two commonly-used cross-view gait datasets demonstrate the superior performance of GaitGL-M over existing state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

Intra-Guided Dual-Energy Material Decomposition Method for Dual-Source CBCT Systems 46

学校读者我要写书评

暂无评论

Intra-Guided Dual-Energy Material Decomposition Method for D...

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Zhong, Xinyun Lyu, Tianling Wu, Zhan Gao, Wei Xi, Yan Zhao, Wei Zhu, Wentao Chen, Yang Zhejiang Lab Hangzhou China First-Imaging Tech. Shanghai China Beihang University Beijing China Southeast University School of Computer Science and Engineering Laboratory of Image Science and Technology Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

Dual-energy CBCT imaging plays a crucial role in advanced imaging applications due to its ability to quantify material components. Although there are multiple established systems for dual-energy imaging, they often come with high deployment costs. This study investigates the feasibility of dual-energy material decomposition on a less expensive dual-source CBCT system. Due to the specific geometry of dual-source CBCT, cone-beam (CB) artifacts seriously degrade the material decomposition quality when the direct inversion method is adopted. In this paper, a novel dual-source intra-guided material decomposition framework is proposed to suppress CB artifacts in the material maps. Firstly, a dual-source two-pass algorithm is developed for artifact pre-correction during image reconstruction. Then, the structure of small cone-angle regions from one X-ray source is utilized to guide cone beam artifact removal in large cone-angle regions from another source. Finally, direct matrix inverse material decomposition is applied to the filtered image. Extensive experiments have been conducted on the authentic human phantom and demonstrate that the proposed framework achieves excellent performance in cone beam artifact reduction compared to other methods, and significantly enhances the quality of the material maps. © 2024 IEEE.

关键词： Image reconstruction

AN EMPIRICAL ANALYSIS OF UNCERTAINTY IN LARGE LANGUAGE MODEL EVALUATIONS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xie, Qiujie Li, Qingqiu Yu, Zhuohao Zhang, Yuejie Zhang, Yue Yang, Linyi Zhejiang University China School of Engineering Westlake University China School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Peking University China Westlake Institute for Advanced Study China University College London United Kingdom Huawei Noah’s Ark Lab Hong Kong

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias, little research has concentrated on the stability of LLM evaluators. In this paper, we conduct extensive experiments involving 9 widely used LLM evaluators across 2 different evaluation settings to investigate the uncertainty in model-based LLM evaluations. We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes. With careful comparative analyses, we find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent. By utilizing uncertainty to enhance LLM’s reliability and detection capability in Out-Of-Distribution (OOD) data, we further fine-tune an uncertainty-aware LLM evaluator named ConfiLM using a human-annotated fine-tuning set and assess ConfiLM’s OOD evaluation ability on a manually designed test set sourced from the 2024 Olympics. Experimental results demonstrate that incorporating uncertainty as additional information during the fine-tuning phase can largely improve the model’s evaluation performance in OOD scenarios. The code and data are released at: https://***/hasakiXie123/LLM-Evaluator-Uncertainty. © 2025, CC BY-NC-SA.

关键词： Digital elevation model

Multi-Object Localization and Irrelevant-Semantic Separation for Nuclei Segmentation in Histopathology Images 48

学校读者我要写书评

暂无评论

Multi-Object Localization and Irrelevant-Semantic Separation...

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Tang, Ya Ye, Xiongjun Li, Xuanya Chen, Zhineng Xiangtan University Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan411105 China Chinese Academy of Medical Sciences Peking Union Medical College National Cancer Center Cancer Hospital Beijing100021 China Baidu Inc. Beijing100085 China Fudan University School of Computer Science Shanghai200438 China

ISBN: (纸本)9781728163277

Automated segmentation of nuclei in histopathology images is critical for cancer diagnosis and prognosis. Due to the high variability of nuclei morphology, numerous nuclei overlapping, and the wide existence of nuclei clusters, this task still remains challenging. In this paper, we propose an effective nuclei segmentation method for histopathology images based on a novel neural network for multi-object localization and irrelevant-semantic separation (MI-Net), which includes a multi-object localization module (MOLM), a deep boundary awareness module (DBAM), and an irrelevant semantic separation module (ISSM). Specifically, the MOLM is used to calibrate features to capture more comprehensive information about the location of nuclei. It alleviates the problem of cell adhesion in histopathology images. The DBAM is intended to extract boundary information and solve the blurred boundary problem effectively. The ISSM is used to separate foreground features from background features and effectively address the problem of complex backgrounds in histopathology images. It also solves the low contrast problem between the target objects and the background. We evaluate MI-Net on the famous MoNuSeg dataset and compare it with ten state-of-the-art methods. MI-Net surpasses the best-performed method by margins from 1.12% to 2.29% over standard evaluation metrics, showing its effectiveness on nuclei segmentation. © 2023 IEEE.

关键词： Semantics

Balanced Contrastive Learning for Long-Tailed Visual Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Jianggang Wang, Zheng Chen, Jingjing Chen, Yi-Ping Phoebe 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 Department of Computer Science and Information Technology La Trobe University Australia

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle to represent and classify the tail classes. Although the problem of learning unbiased classifiers has been well studied, methods for representing imbalanced data are under-explored. In this paper, we focus on representation learning for imbalanced data. Recently, supervised contrastive learning has shown promising performance on balanced data recently. However, through our theoretical analysis, we find that for long-tailed data, it fails to form a regular simplex which is an ideal geometric configuration for representation learning. To correct the optimization behavior of SCL and further improve the performance of long-tailed visual recognition, we propose a novel loss for balanced contrastive learning (BCL). Compared with SCL, we have two improvements in BCL: class-averaging, which balances the gradient contribution of negative classes;class-complement, which allows all classes to appear in every mini-batch. The proposed balanced contrastive learning (BCL) method satisfies the condition of forming a regular simplex and assists the optimization of cross-entropy. Equipped with BCL, the proposed two-branch framework can obtain a stronger feature representation and achieve competitive performance on long-tailed benchmark datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018. Our code is available at this URL. Copyright © 2022, The Authors. All rights reserved.

关键词： Benchmarking

ClickVOS: Click Video Object Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Pinxue Hong, Lingyi Zhou, Xinyu Gao, Shuyong Li, Wanyun Li, Jinglun Chen, Zhaoyu Li, Xiaoqiang Zhang, Wei Zhang, Wenqiang the Shanghai Engineering Research Center of AI&Robotics Academy for Engineering&Technology Fudan University Shanghai China the Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China the School of Computer Engineering and Science Shanghai University Shanghai China Engineering Research Center of AI&Robotics Ministry of Education Academy for Engineering&Technology Fudan University Shanghai China

—Video Object Segmentation (VOS) task aims to segment objects in videos. However, previous settings either require time-consuming manual masks of target objects at the first frame during inference or lack the flexibility to specify arbitrary objects of interest. To address these limitations, we propose the setting named Click Video Object Segmentation (ClickVOS) which segments objects of interest across the whole video according to a single click per object in the first frame. And we provide the extended datasets DAVIS-P and YouTubeVOS-P that with point annotations to support this task. ClickVOS is of significant practical applications and research implications due to its only 1-2 seconds interaction time for indicating an object, comparing annotating the mask of an object needs several minutes. However, ClickVOS also presents increased challenges. To address this task, we propose an end-to-end baseline approach named called Attention Before Segmentation (ABS), motivated by the attention process of humans. ABS utilizes the given point in the first frame to perceive the target object through a concise yet effective segmentation attention. Although the initial object mask is possibly inaccurate, in our ABS, as the video goes on, the initially imprecise object mask can self-heal instead of deteriorating due to error accumulation, which is attributed to our designed improvement memory that continuously records stable global object memory and updates detailed dense memory. In addition, we conduct various baseline explorations utilizing off-the-shelf algorithms from related fields, which could provide insights for the further exploration of ClickVOS. The experimental results demonstrate the superiority of the proposed ABS approach. Extended datasets and codes will be available at https://***/PinxueGuo/ClickVOS. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion compensation

DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images

学校读者我要写书评

暂无评论

DRDM: A Disentangled Representations Diffusion Model for Syn...

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Huang, Enbo Zhang, Yuan Huang, Faliang Zhang, Guangyu Liu, Yang Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer and Information Engineering Nanning Normal University Nanning China College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (纸本)9798350368741

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photo-realistic images from source portraits in specific desired poses and appearances. First, a pose encoder is responsible for encoding pose features into a high-dimensional space to guide the generation of person images. Second, a body-part subspace decoupling block (BSDB) disentangles features from the different body parts of a source figure and feeds them to the various layers of the noise prediction block, thereby supplying the network with rich disentangled features for generating a realistic target image. Moreover, during inference, we develop a parsing map-based disentangled classifier-free guided sampling method, which amplifies the conditional signals of texture and pose. Extensive experimental results on the Deepfashion dataset demonstrate the effectiveness of our approach in achieving pose transfer and appearance control. The associated project can be found at https://***/lovemusiceb/DRDM. © 2025 IEEE.

关键词： Diffusion Model Disentangled Representation Human Parsing Person image synthesis

GenRec: Unifying Video Generation and Recognition with Diffusion Models

学校读者我要写书评

暂无评论

arXiv 2024年

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

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. Copyright © 2024, The Authors. All rights reserved.

关键词： Spatio-temporal data