Výsledky vyhledávání - "Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition"

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning Autor Qu, Liangqiong, Zhou, Yuyin, Liang, Paul Pu, Xia, Yingda, Wang, Feifei, Adeli, Ehsan, Fei-Fei, Li, Rubin, Daniel

“…Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data…”
Získat plný text

CRAFT: Concept Recursive Activation FacTorization for Explainability Autor Fel, Thomas, Picard, Agustin, Bethune, Louis, Boissin, Thibaut, Vigouroux, David, Colin, Julien, Cadenc, Remi, Serre, Thomas

“…Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity…”
Získat plný text

Directional Connectivity-based Segmentation of Medical Images Autor Yang, Ziyun, Farsiu, Sina

“…Anatomical consistency in biomarker segmentation is crucial for many medical image analysis tasks. A promising paradigm for achieving anatomically consistent…”
Získat plný text

Deep Unlearning via Randomized Conditionally Independent Hessians Autor Mehta, Ronak, Pal, Sourav, Singh, Vikas, Ravi, Sathya N.

“…Recent legislation has led to interest in machine unlearning, i. e., removing specific training samples from a predictive model as if they never existed in the…”
Získat plný text

Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning Autor Guo, Pengfei, Wang, Puyang, Zhou, Jinyuan, Jiang, Shanshan, Patel, Vishal M.

“…Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep…”
Získat plný text

Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping Autor Fu, Huan, Gong, Mingming, Wang, Chaohui, Batmanghelich, Kayhan, Zhang, Kun, Tao, Dacheng

“…Unsupervised domain mapping aims to learn a function GXY to translate domain X to Y in the absence of paired examples. Finding the optimal GXY without paired…”
Získat plný text

DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis Autor Haghighi, Fatemeh, Taher, Mohammad Reza Hosseinzadeh, Gotway, Michael B., Liang, Jianming

“…Discriminative learning, restorative learning, and adversarial learning have proven beneficial for self-supervised learning schemes in computer vision and…”
Získat plný text

Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning Autor Yang, Zhibo, Huang, Lihan, Chen, Yupei, Wei, Zijun, Ahn, Seoyoung, Zelinsky, Gregory, Samaras, Dimitris, Hoai, Minh

“…Human gaze behavior prediction is important for behavioral vision and for computer vision applications. Most models mainly focus on predicting free-viewing…”
Získat plný text

Learned Representation-Guided Diffusion Models for Large-Image Generation Autor Graikos, Alexandros, Yellapragada, Srikar, Le, Minh-Quan, Kapse, Saarthak, Prasanna, Prateek, Saltz, Joel, Samaras, Dimitris

“…To synthesize high-fidelity samples, diffusion models typically require auxiliary data to guide the generation process. However, it is impractical to procure…”
Získat plný text

Networks for Joint Affine and Non-Parametric Image Registration Autor Shen, Zhengyang, Han, Xu, Xu, Zhenlin, Niethammer, Marc

“…We introduce an end-to-end deep-learning framework for 3D medical image registration. In contrast to existing approaches, our framework combines two…”
Získat plný text

Metric Learning for Image Registration Autor Niethammer, Marc, Kwitt, Roland, Vialard, Francois-Xavier

“…Image registration is a key technique in medical image analysis to estimate deformations between image pairs. A good deformation model is important for…”
Získat plný text

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency Autor Wang, Feng, Yang, Timing, Yu, Yaodong, Ren, Sucheng, Wei, Guoyizhe, Wang, Angtian, Shao, Wei, Zhou, Yuyin, Yuille, Alan, Xie, Cihang

“…In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn…”
Získat plný text

TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model Autor Xu, Meilong, Gupta, Saumya, Hu, Xiaoling, Li, Chen, Abousamra, Shahira, Samaras, Dimitris, Prasanna, Prateek, Chen, Chao

“…Accurately modeling multi-class cell topology is crucial in digital pathology, as it provides critical insights into tissue structure and pathology. The…”
Získat plný text

MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images Autor Ganguly, Aniruddha, Chatterjee, Debolina, Huang, Wentao, Zhang, Jie, Yurovsky, Alisa, Johnson, Travis Steele, Chen, Chao

“…Recent advances in Spatial Transcriptomics (ST) pair histology images with spatially resolved gene expression profiles, enabling predictions of gene expression…”
Získat plný text

Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation Autor Mathew, Shawn, Nadeem, Saad, Kumari, Sruti, Kaufman, Arie

“…Colorectal cancer screening modalities, such as optical colonoscopy (OC) and virtual colonoscopy (VC), are critical for diagnosing and ultimately removing…”
Získat plný text

GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency Autor Tian, Lin, Greer, Hastings, Vialard, Francois-Xavier, Kwitt, Roland, Estepar, Raul San Jose, Rushmore, Richard Jarrett, Makris, Nikolaos, Bouix, Sylvain, Niethammer, Marc

“…We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration. Contrary to…”
Získat plný text

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Autor Tang, Feilong, Liu, Chengzhi, Xu, Zhongxing, Hu, Ming, Huang, Zile, Xue, Haochen, Chen, Ziyang, Peng, Zelin, Yang, Zhiwei, Zhou, Sijin, Li, Wenxue, Li, Yulong, Song, Wenxuan, Su, Shiyan, Feng, Wei, Su, Jionglong, Lin, Minquan, Peng, Yifan, Cheng, Xuelian, Razzak, Imran, Ge, Zongyuan

“…Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often…”
Získat plný text

MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling Autor Zhang, Xuzhe, Wu, Yuhao, Angelini, Elsa, Li, Ang, Guo, Jia, Rasmussen, Jerod M., OConnor, Thomas G., Wadhwa, Pathik D., Jackowski, Andrea Parolin, Li, Hai, Posner, Jonathan, Laine, Andrew F., Wang, Yun

“…Robust segmentation is critical for deriving quantitative measures from large-scale, multi-center, and longitudinal medical scans. Manually annotating medical…”
Získat plný text

Task Programming: Learning Data Efficient Behavior Representations Autor Sun, Jennifer J., Kennedy, Ann, Zhan, Eric, Anderson, David J., Yue, Yisong, Perona, Pietro

“…Specialized domain knowledge is often necessary to accurately annotate training sets for in-depth analysis, but can be burdensome and time-consuming to acquire…”
Získat plný text

Robust Histopathology Image Analysis: To Label or to Synthesize? Autor Hou, Le, Agarwal, Ayush, Samaras, Dimitris, Kurc, Tahsin M., Gupta, Rajarsi R., Saltz, Joel H.

“…Detection, segmentation and classification of nuclei are fundamental analysis operations in digital pathology. Existing state-of-the-art approaches demand…”
Získat plný text