中文
相关论文

相关论文: Balanced Hierarchical Contrastive Learning with De…

200 篇论文

Recently, multi-view and multi-label classification have become significant domains for comprehensive data analysis and exploration. However, incompleteness both in views and labels is still a real-world scenario for multi-view multi-label…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Bingyan Nie , Wulin Xie , Jiang Long , Xiaohuan Lu

Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry…

计算机视觉与模式识别 · 计算机科学 2023-04-19 Chang Xu , Jian Ding , Jinwang Wang , Wen Yang , Huai Yu , Lei Yu , Gui-Song Xia

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

机器学习 · 计算机科学 2021-10-05 Ramakrishnan Sundareswaran , Jansel Herrera-Gerena , John Just , Ali Jannesari

Contrastive learning methods have attracted considerable attention due to their remarkable success in analyzing graph-structured data. Inspired by the success of contrastive learning, we propose a novel framework for contrastive…

机器学习 · 计算机科学 2023-06-21 Xiaojuan Zhang , Jun Fu , Shuang Li

Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of…

计算机视觉与模式识别 · 计算机科学 2021-09-20 Foivos I. Diakogiannis , François Waldner , Peter Caccetta

Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting…

机器学习 · 计算机科学 2026-02-02 Willian T. Lunardi , Abdulrahman Banabila , Dania Herzalla , Martin Andreoni

We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information. This allows us to cope with the main…

计算机视觉与模式识别 · 计算机科学 2018-10-17 Weifeng Ge , Weilin Huang , Dengke Dong , Matthew R. Scott

Classification algorithms in machine learning often assume a flat label space. However, most real world data have dependencies between the labels, which can often be captured by using a hierarchy. Utilizing this relation can help develop a…

机器学习 · 计算机科学 2020-06-09 Palash Goyal , Shalini Ghosh

Deep neural networks have reached remarkable achievements in medical image processing tasks, specifically in classifying and detecting various diseases. However, when confronted with limited data, these networks face a critical…

计算机视觉与模式识别 · 计算机科学 2024-09-25 Matina Mahdizadeh Sani , Ali Royat , Mahdieh Soleymani Baghshah

New advancements in radio data post-processing are underway within the SKA precursor community, aiming to facilitate the extraction of scientific results from survey images through a semi-automated approach. Several of these developments…

Existing deep learning-based cross-view geo-localization methods primarily focus on improving the accuracy of cross-domain image matching, rather than enabling models to comprehensively capture contextual information around the target and…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Suofei Zhang , Xinxin Wang , Xiaofu Wu , Quan Zhou , Haifeng Hu

Deep learning models are known to be vulnerable to adversarial examples that are elaborately designed for malicious purposes and are imperceptible to the human perceptual system. Autoencoder, when trained solely over benign examples, has…

计算机视觉与模式识别 · 计算机科学 2022-08-30 Zhaoxi Zhang , Leo Yu Zhang , Xufei Zheng , Jinyu Tian , Jiantao Zhou

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Qiang Zhou , Chaohui Yu , Zhibin Wang , Fan Wang

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Jizong Peng , Ping Wang , Chrisitian Desrosiers , Marco Pedersoli

The vast amount of unlabeled multi-temporal and multi-sensor remote sensing data acquired by the many Earth Observation satellites present a challenge for change detection. Recently, many generative model-based methods have been proposed…

图像与视频处理 · 电气工程与系统科学 2022-02-16 Yuxing Chen , Lorenzo Bruzzone

While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However,…

计算机视觉与模式识别 · 计算机科学 2018-05-02 Yen-Cheng Liu , Yu-Ying Yeh , Tzu-Chien Fu , Sheng-De Wang , Wei-Chen Chiu , Yu-Chiang Frank Wang

In spite of great success in many image recognition tasks achieved by recent deep models, directly applying them to recognize low-resolution images may suffer from low accuracy due to the missing of informative details during resolution…

计算机视觉与模式识别 · 计算机科学 2024-09-10 Shiming Ge , Kangkai Zhang , Haolin Liu , Yingying Hua , Shengwei Zhao , Xin Jin , Hao Wen

Semi-supervised learning approaches have emerged as an active area of research to combat the challenge of obtaining large amounts of annotated data. Towards the goal of improving the performance of semi-supervised learning methods, we…

计算机视觉与模式识别 · 计算机科学 2021-12-22 Ashima Garg , Shaurya Bagga , Yashvardhan Singh , Saket Anand

Image denoising is a typical ill-posed problem due to complex degradation. Leading methods based on normalizing flows have tried to solve this problem with an invertible transformation instead of a deterministic mapping. However, the…

计算机视觉与模式识别 · 计算机科学 2023-02-01 Wenchao Du , Hu Chen , Yi Zhang , H. Yang

This paper presents a novel online learning method that aims at finding a separator hyperplane between data points labelled as either positive or negative. Since weights and biases of artificial neurons can directly be related to…

机器学习 · 计算机科学 2023-09-13 Ákos Hajnal
‹ 上一页 1 8 9 10 下一页 ›