中文
相关论文

相关论文: Nearest-Neighbor Inter-Intra Contrastive Learning …

200 篇论文

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

计算机视觉与模式识别 · 计算机科学 2020-10-26 Chih-Hui Ho , Nuno Vasconcelos

The goal of contrastive learning based pre-training is to leverage large quantities of unlabeled data to produce a model that can be readily adapted downstream. Current approaches revolve around solving an image discrimination task: given…

计算机视觉与模式识别 · 计算机科学 2021-11-30 Chenhongyi Yang , Lichao Huang , Elliot J. Crowley

Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…

机器学习 · 计算机科学 2021-10-29 Shuang Ma , Zhaoyang Zeng , Daniel McDuff , Yale Song

We develop an approach to learning visual representations that embraces multimodal data, driven by a combination of intra- and inter-modal similarity preservation objectives. Unlike existing visual pre-training methods, which solve a proxy…

计算机视觉与模式识别 · 计算机科学 2021-04-28 Xin Yuan , Zhe Lin , Jason Kuen , Jianming Zhang , Yilin Wang , Michael Maire , Ajinkya Kale , Baldo Faieta

Content creators often use music to enhance their videos, from soundtracks in movies to background music in video blogs and social media content. However, identifying the best music for a video can be a difficult and time-consuming task. To…

多媒体 · 计算机科学 2024-12-24 Shanti Stewart , Gouthaman KV , Lie Lu , Andrea Fanelli

Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models. In this paper, we find that existing contrastive learning based solutions for self-supervised video recognition focus on…

计算机视觉与模式识别 · 计算机科学 2021-10-26 Lin Zhang , Qi She , Zhengyang Shen , Changhu Wang

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Unsupervised learning is a challenging task due to the lack of labels. Multiple Object Tracking (MOT), which inevitably suffers from mutual object interference, occlusion, etc., is even more difficult without label supervision. In this…

计算机视觉与模式识别 · 计算机科学 2023-09-06 Sha Meng , Dian Shao , Jiacheng Guo , Shan Gao

Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation.…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Le Zhang , Rabiul Awal , Aishwarya Agrawal

Self-supervised methods have shown tremendous success in the field of computer vision, including applications in remote sensing and medical imaging. Most popular contrastive-loss based methods like SimCLR, MoCo, MoCo-v2 use multiple views…

计算机视觉与模式识别 · 计算机科学 2022-09-07 Umangi Jain , Alex Wilson , Varun Gulshan

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Jinyu Yang , Jiali Duan , Son Tran , Yi Xu , Sampath Chanda , Liqun Chen , Belinda Zeng , Trishul Chilimbi , Junzhou Huang

Different from general object detection, moving infrared small target detection faces huge challenges due to tiny target size and weak background contrast.Currently, most existing methods are fully-supervised, heavily relying on a large…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Weiwei Duan , Luping Ji , Shengjia Chen , Sicheng Zhu , Jianghong Huang , Mao Ye

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Jihai Zhang , Xiang Lan , Xiaoye Qu , Yu Cheng , Mengling Feng , Bryan Hooi

Video summarization aims at choosing parts of a video that narrate a story as close as possible to the original one. Most of the existing video summarization approaches focus on hand-crafted labels. As the number of videos grows…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Ivan Sosnovik , Artem Moskalev , Cees Kaandorp , Arnold Smeulders

Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…

计算机视觉与模式识别 · 计算机科学 2021-01-20 Nanxuan Zhao , Zhirong Wu , Rynson W. H. Lau , Stephen Lin

Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not…

计算机视觉与模式识别 · 计算机科学 2021-09-13 Ajinkya Tejankar , Soroush Abbasi Koohpayegani , Vipin Pillai , Paolo Favaro , Hamed Pirsiavash

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

机器学习 · 计算机科学 2021-04-08 Jeongwoo Ju , Heechul Jung , Yoonju Oh , Junmo Kim

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…

计算机视觉与模式识别 · 计算机科学 2022-04-05 Liangzhe Yuan , Rui Qian , Yin Cui , Boqing Gong , Florian Schroff , Ming-Hsuan Yang , Hartwig Adam , Ting Liu

Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower…

机器学习 · 计算机科学 2021-04-20 Shuang Ma , Zhaoyang Zeng , Daniel McDuff , Yale Song

MoCo is effective for unsupervised image representation learning. In this paper, we propose VideoMoCo for unsupervised video representation learning. Given a video sequence as an input sample, we improve the temporal feature representations…

计算机视觉与模式识别 · 计算机科学 2021-03-18 Tian Pan , Yibing Song , Tianyu Yang , Wenhao Jiang , Wei Liu