中文
相关论文

相关论文: Visual Relationship Prediction via Label Clusterin…

200 篇论文

Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data. These deep clustering methods mainly focus on the correlation among samples, e.g., selecting high precision pairs to gradually…

计算机视觉与模式识别 · 计算机科学 2019-08-13 Jianlong Wu , Keyu Long , Fei Wang , Chen Qian , Cheng Li , Zhouchen Lin , Hongbin Zha

While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior work has mostly been…

计算机视觉与模式识别 · 计算机科学 2020-07-16 Aruni RoyChowdhury , Xiang Yu , Kihyuk Sohn , Erik Learned-Miller , Manmohan Chandraker

We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the…

计算机视觉与模式识别 · 计算机科学 2019-08-28 Kai Han , Andrea Vedaldi , Andrew Zisserman

Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels…

计算机视觉与模式识别 · 计算机科学 2016-10-25 Hexiang Hu , Guang-Tong Zhou , Zhiwei Deng , Zicheng Liao , Greg Mori

Computer vision is driven by the many datasets available for training or evaluating novel methods. However, each dataset has a different set of class labels, visual definition of classes, images following a specific distribution, annotation…

计算机视觉与模式识别 · 计算机科学 2022-08-10 Jasper Uijlings , Thomas Mensink , Vittorio Ferrari

Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by…

计算机视觉与模式识别 · 计算机科学 2024-11-07 Xiang An , Kaicheng Yang , Xiangzi Dai , Ziyong Feng , Jiankang Deng

Clustering algorithms are one of the main analytical methods to detect patterns in unlabeled data. Existing clustering methods typically treat samples in a dataset as points in a metric space and compute distances to group together similar…

机器学习 · 计算机科学 2021-10-12 Tarek Naous , Srinjay Sarkar , Abubakar Abid , James Zou

The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE). However, high-dimensional vectors can encode complex linguistic information which leads to…

计算与语言 · 计算机科学 2021-09-16 Jun Zhao , Tao Gui , Qi Zhang , Yaqian Zhou

Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-style latent…

计算机视觉与模式识别 · 计算机科学 2020-07-21 Junjie Zhao , Donghuan Lu , Kai Ma , Yu Zhang , Yefeng Zheng

Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in…

机器学习 · 计算机科学 2015-02-19 Fangfang Li , Guandong Xu , Longbing Cao

Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation…

计算机视觉与模式识别 · 计算机科学 2023-03-17 Geeho Kim , Junoh Kang , Bohyung Han

Generalized Category Discovery (GCD) requires a model to both classify known categories and cluster unknown categories in unlabeled data. Prior methods leveraged self-supervised pre-training combined with supervised fine-tuning on the…

计算机视觉与模式识别 · 计算机科学 2023-05-18 Rabah Ouldnoughi , Chia-Wen Kuo , Zsolt Kira

Modern graph or network datasets often contain rich structure that goes beyond simple pairwise connections between nodes. This calls for complex representations that can capture, for instance, edges of different types as well as so-called…

社会与信息网络 · 计算机科学 2020-02-19 Ilya Amburg , Nate Veldt , Austin R. Benson

Due to the costliness of labelled data in real-world applications, semi-supervised learning, underpinned by pseudo labelling, is an appealing solution. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

计算机视觉与模式识别 · 计算机科学 2024-02-13 Changrui Chen , Jungong Han , Kurt Debattista

We consider the unsupervised learning problem of assigning labels to unlabeled data. A naive approach is to use clustering methods, but this works well only when data is properly clustered and each cluster corresponds to an underlying…

机器学习 · 计算机科学 2013-05-02 Marthinus Christoffel du Plessis , Masashi Sugiyama

Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it by proposing a joint…

计算机视觉与模式识别 · 计算机科学 2023-12-08 Zhenduo Zhang

Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

计算机视觉与模式识别 · 计算机科学 2022-10-18 Changrui Chen , Kurt Debattista , Jungong Han

Existing machine learning models demonstrate excellent performance in image object recognition after training on a large-scale dataset under full supervision. However, these models only learn to map an image to a predefined class index,…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Kai Han , Xiaohu Huang , Yandong Li , Sagar Vaze , Jie Li , Xuhui Jia

We present a general methodology that learns to classify images without labels by leveraging pretrained feature extractors. Our approach involves self-distillation training of clustering heads based on the fact that nearest neighbours in…

计算机视觉与模式识别 · 计算机科学 2023-11-13 Nikolas Adaloglou , Felix Michels , Hamza Kalisch , Markus Kollmann

Face recognition sees remarkable progress in recent years, and its performance has reached a very high level. Taking it to a next level requires substantially larger data, which would involve prohibitive annotation cost. Hence, exploiting…

计算机视觉与模式识别 · 计算机科学 2019-05-07 Lei Yang , Xiaohang Zhan , Dapeng Chen , Junjie Yan , Chen Change Loy , Dahua Lin
‹ 上一页 1 2 3 10 下一页 ›