中文
相关论文

相关论文: Ensemble of ConvNeXt V2 and MaxViT for Long-Tailed…

200 篇论文

In vision domain, large-scale natural datasets typically exhibit long-tailed distribution which has large class imbalance between head and tail classes. This distribution poses difficulty in learning good representations for tail classes.…

计算机视觉与模式识别 · 计算机科学 2023-05-05 Anthony Meng Huat Tiong , Junnan Li , Guosheng Lin , Boyang Li , Caiming Xiong , Steven C. H. Hoi

Long-tailed pulmonary anomalies in chest radiography present formidable diagnostic challenges. Despite the recent strides in diffusion-based methods for enhancing the representation of tailed lesions, the paucity of rare lesion exemplars…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Xinquan Yang , Jinheng Xie , Yawen Huang , Yuexiang Li , Huimin Huang , Hao Zheng , Xian Wu , Yefeng Zheng , Linlin Shen

In this paper, we propose an Aligned Contrastive Learning (ACL) algorithm to address the long-tailed recognition problem. Our findings indicate that while multi-view training boosts the performance, contrastive learning does not…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Jiali Ma , Jiequan Cui , Maeno Kazuki , Lakshmi Subramanian , Karlekar Jayashree , Sugiri Pranata , Hanwang Zhang

The global demand for radiologists is increasing rapidly due to a growing reliance on medical imaging services, while the supply of radiologists is not keeping pace. Advances in computer vision and image processing technologies present…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Shehroz S. Khan , Petar Przulj , Ahmed Ashraf , Ali Abedi

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide the first systematic analysis on the underperformance of…

计算机视觉与模式识别 · 计算机科学 2020-06-20 Yu Li , Tao Wang , Bingyi Kang , Sheng Tang , Chunfeng Wang , Jintao Li , Jiashi Feng

Although contrastive learning methods have shown prevailing performance on a variety of representation learning tasks, they encounter difficulty when the training dataset is long-tailed. Many researchers have combined contrastive learning…

机器学习 · 计算机科学 2023-08-09 Min-Kook Suh , Seung-Woo Seo

Chest X-ray classification suffers from severe class imbalance where gradient updates bias toward majority classes, causing feature drift and poor performance on rare but critical pathologies. We propose a Momentum-Anchored Multi-Scale…

计算机视觉与模式识别 · 计算机科学 2026-05-06 Duy Hoang Khuong , Duy Nguyen Huu , Ngu Huynh Cong Viet

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e.g. LVIS. In this…

计算机视觉与模式识别 · 计算机科学 2020-04-15 Jingru Tan , Changbao Wang , Buyu Li , Quanquan Li , Wanli Ouyang , Changqing Yin , Junjie Yan

The automatic diagnosis of chest diseases is a popular and challenging task. Most current methods are based on convolutional neural networks (CNNs), which focus on local features while neglecting global features. Recently, self-attention…

计算机视觉与模式识别 · 计算机科学 2025-05-19 Xinran Li , Yu Liu , Xiujuan Xu , Xiaowei Zhao

Medical image analysis using computer-based algorithms has attracted considerable attention from the research community and achieved tremendous progress in the last decade. With recent advances in computing resources and availability of…

图像与视频处理 · 电气工程与系统科学 2023-10-03 Huyen Tran , Duc Thanh Nguyen , John Yearwood

The long-tailed image classification task remains important in the development of deep neural networks as it explicitly deals with large imbalances in the class frequencies of the training data. While uncommon in engineered datasets, this…

计算机视觉与模式识别 · 计算机科学 2023-07-12 Marc-Antoine Lavoie , Steven Waslander

Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and re-sampling methods, that utilise the class…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Konstantinos Panagiotis Alexandridis , Ismail Elezi , Jiankang Deng , Anh Nguyen , Shan Luo

Effectively handling the co-occurrence of non-IID data and long-tailed distributions remains a critical challenge in federated learning. While fine-tuning vision-language models (VLMs) like CLIP has shown to be promising in addressing…

机器学习 · 计算机科学 2025-03-11 Shihao Hou , Xinyi Shang , Shreyank N Gowda , Yang Lu , Chao Wu , Yan Yan , Hanzi Wang

Real world data often exhibits a long-tailed and open-ended (with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and…

计算机视觉与模式识别 · 计算机科学 2022-08-18 Ziwei Liu , Zhongqi Miao , Xiaohang Zhan , Jiayun Wang , Boqing Gong , Stella X. Yu

Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise learning framework to…

计算机视觉与模式识别 · 计算机科学 2023-05-23 Na Dong , Yongqiang Zhang , Mingli Ding , Gim Hee Lee

As most ''in the wild'' data collections of the natural world, the North America Camera Trap Images (NACTI) dataset shows severe long-tailed class imbalance, noting that the largest 'Head' class alone covers >50% of the 3.7M images in the…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Zehua Liu , Tilo Burghardt

Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, practical test class distributions often…

计算机视觉与模式识别 · 计算机科学 2022-10-28 Yifan Zhang , Bryan Hooi , Lanqing Hong , Jiashi Feng

Developing a robust algorithm to diagnose and quantify the severity of COVID-19 using Chest X-ray (CXR) requires a large number of well-curated COVID-19 datasets, which is difficult to collect under the global COVID-19 pandemic. On the…

图像与视频处理 · 电气工程与系统科学 2021-04-16 Sangjoon Park , Gwanghyun Kim , Yujin Oh , Joon Beom Seo , Sang Min Lee , Jin Hwan Kim , Sungjun Moon , Jae-Kwang Lim , Jong Chul Ye

The visual relationship recognition (VRR) task aims at understanding the pairwise visual relationships between interacting objects in an image. These relationships typically have a long-tail distribution due to their compositional nature.…

计算机视觉与模式识别 · 计算机科学 2022-03-30 Jun Chen , Aniket Agarwal , Sherif Abdelkarim , Deyao Zhu , Mohamed Elhoseiny

Real-world data often exhibits a long-tailed distribution, in which head classes occupy most of the data, while tail classes only have very few samples. Models trained on long-tailed datasets have poor adaptability to tail classes and the…

计算机视觉与模式识别 · 计算机科学 2023-09-29 Qiong Chen , Tianlin Huang , Geren Zhu , Enlu Lin