中文
相关论文

相关论文: A Dual-Branch Local-Global Framework for Cross-Res…

200 篇论文

Deep learning methods show promising results for overlapping cervical cell instance segmentation. However, in order to train a model with good generalization ability, voluminous pixel-level annotations are demanded which is quite expensive…

计算机视觉与模式识别 · 计算机科学 2020-07-22 Yanning Zhou , Hao Chen , Huangjing Lin , Pheng-Ann Heng

Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributions. In practice, annotations are scarce, and images are…

计算机视觉与模式识别 · 计算机科学 2026-01-26 Ba-Thinh Lam , Thanh-Huy Nguyen , Hoang-Thien Nguyen , Quang-Khai Bui-Tran , Nguyen Lan Vi Vu , Phat K. Huynh , Ulas Bagci , Min Xu

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

计算机视觉与模式识别 · 计算机科学 2022-10-27 Nitin Bansal , Pan Ji , Junsong Yuan , Yi Xu

Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has recently attracted considerable attention across various applications, including computer…

机器学习 · 计算机科学 2026-05-28 Ye Su , Hezhe Qiao , Wei Huang , Lin Chen

Semi-supervised learning utilizes insights from unlabeled data to improve model generalization, thereby reducing reliance on large labeled datasets. Most existing studies focus on limited samples and fail to capture the overall data…

计算机视觉与模式识别 · 计算机科学 2025-03-13 Xiuzhen Guo , Lianyuan Yu , Ji Shi , Na Lei , Hongxiao Wang

Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality…

计算机视觉与模式识别 · 计算机科学 2024-10-01 Meiying Zhang , Weiyuan Peng , Guangyao Ding , Chenyang Lei , Chunlin Ji , Qi Hao

Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Yixuan Dong , Fang-Yi Su , Jung-Hsien Chiang

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for…

计算机视觉与模式识别 · 计算机科学 2015-10-09 Eric Tzeng , Judy Hoffman , Trevor Darrell , Kate Saenko

Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large and consistently labeled datasets. Although current…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Lars Schmarje , Johannes Brünger , Monty Santarossa , Simon-Martin Schröder , Rainer Kiko , Reinhard Koch

Sparse-view Computed Tomography (CT) image reconstruction is a promising approach to reduce radiation exposure, but it inevitably leads to image degradation. Although diffusion model-based approaches are computationally expensive and suffer…

图像与视频处理 · 电气工程与系统科学 2024-03-15 Hanyu Chen , Zhixiu Hao , Lin Guo , Liying Xiao

Cross-domain Few-shot Segmentation (CD-FSS) aims to segment novel classes from target domains that are not involved in training and have significantly different data distributions from the source domain, using only a few annotated samples,…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Sujun Sun , Haowen Gu , Cheng Xie , Yanxu Ren , Mingwu Ren , Haofeng Zhang

High-resolution remote sensing imagery increasingly contains dense clusters of tiny objects, the detection of which is extremely challenging due to severe mutual occlusion and limited pixel footprints. Existing detection methods typically…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Zhicheng Zhao , Xuanang Fan , Lingma Sun , Chenglong Li , Jin Tang

Until open-world foundation models match the performance of specialized approaches, deep learning systems remain dependent on task- and sensor-specific data availability. To bridge the gap between available datasets and deployment domains,…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Frank Bieder , Hendrik Königshof , Haohao Hu , Fabian Immel , Yinzhe Shen , Jan-Hendrik Pauls , Christoph Stiller

Unsupervised Domain Adaptation (UDA) aims to align source and target domain distributions to close the domain gap, but still struggles with obtaining the target data. Fortunately, Domain Generalization (DG) excels without the need for any…

计算机视觉与模式识别 · 计算机科学 2025-05-13 Binbin Wei , Yuhang Zhang , Shishun Tian , Muxin Liao , Wei Li , Wenbin Zou

Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of…

计算与语言 · 计算机科学 2023-10-31 Nan Xu , Fei Wang , Mingtao Dong , Muhao Chen

Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue…

计算与语言 · 计算机科学 2022-03-23 Jiali Zeng , Yufan Jiang , Shuangzhi Wu , Yongjing Yin , Mu Li

Either human annotation or rule based automatic labeling is an effective method to augment data for relation extraction. However, the inevitable wrong labeling problem for example by distant supervision may deteriorate the performance of…

计算与语言 · 计算机科学 2020-04-30 Shanchan Wu , Kai Fan

Panoramic semantic segmentation is pivotal for comprehensive 360{\deg} scene understanding in critical applications like autonomous driving and virtual reality. However, progress in this domain is constrained by two key challenges: the…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Yaowen Chang , Zhen Cao , Xu Zheng , Xiaoxin Mi , Zhen Dong

Fully automatic large-scale land cover mapping belongs to the core challenges addressed by the remote sensing community. Usually, the basis of this task is formed by (supervised) machine learning models. However, in spite of recent growth…

计算机视觉与模式识别 · 计算机科学 2020-04-29 Michael Schmitt , Jonathan Prexl , Patrick Ebel , Lukas Liebel , Xiao Xiang Zhu

Semi-supervised semantic segmentation, which leverages a limited set of labeled images, helps to relieve the heavy annotation burden. While pseudo-labeling strategies yield promising results, there is still room for enhancing the…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Yuanbin Fu , Xiaojie Guo