中文
相关论文

相关论文: Whitening-based Contrastive Learning of Sentence E…

200 篇论文

Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce linearity of the latent…

机器学习 · 计算机科学 2022-03-04 Bang You , Oleg Arenz , Youping Chen , Jan Peters

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…

计算机视觉与模式识别 · 计算机科学 2022-10-20 Shentong Mo , Zhun Sun , Chao Li

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…

计算与语言 · 计算机科学 2023-01-26 Xiang Chen , Xin Xie , Zhen Bi , Hongbin Ye , Shumin Deng , Ningyu Zhang , Huajun Chen

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…

计算机视觉与模式识别 · 计算机科学 2024-09-13 Vlad Sobal , Mark Ibrahim , Randall Balestriero , Vivien Cabannes , Diane Bouchacourt , Pietro Astolfi , Kyunghyun Cho , Yann LeCun

Representations of events described in text are important for various tasks. In this work, we present SWCC: a Simultaneous Weakly supervised Contrastive learning and Clustering framework for event representation learning. SWCC learns event…

计算与语言 · 计算机科学 2022-03-16 Jun Gao , Wei Wang , Changlong Yu , Huan Zhao , Wilfred Ng , Ruifeng Xu

Previous deep learning approaches for survival analysis have primarily relied on ranking losses to improve discrimination performance, which often comes at the expense of calibration performance. To address such an issue, we propose a novel…

机器学习 · 计算机科学 2024-11-22 Dongjoon Lee , Hyeryn Park , Changhee Lee

Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly sampled negative…

机器学习 · 计算机科学 2020-10-06 Mike Wu , Milan Mosse , Chengxu Zhuang , Daniel Yamins , Noah Goodman

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…

This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks. We present the first backdoor attack framework, BadCSE, for state-of-the-art sentence…

计算与语言 · 计算机科学 2022-10-21 Xiaoyi Chen , Baisong Xin , Shengfang Zhai , Shiqing Ma , Qingni Shen , Zhonghai Wu

Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning…

计算与语言 · 计算机科学 2023-10-10 Christos Theodoropoulos , James Henderson , Andrei C. Coman , Marie-Francine Moens

Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbalanced data distribution, and the risk of overfitting. In…

计算机视觉与模式识别 · 计算机科学 2023-08-02 Bolun Cai , Pengfei Xiong , Shangxuan Tian

Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization…

计算机视觉与模式识别 · 计算机科学 2019-12-13 Xingang Pan , Xiaohang Zhan , Jianping Shi , Xiaoou Tang , Ping Luo

Text embedding models play a crucial role in natural language processing, particularly in information retrieval, and their importance is further highlighted with the recent utilization of RAG (Retrieval- Augmented Generation). This study…

信息检索 · 计算机科学 2024-12-24 Jeongsu Yu

Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While…

计算机视觉与模式识别 · 计算机科学 2022-01-04 Tri Huynh , Simon Kornblith , Matthew R. Walter , Michael Maire , Maryam Khademi

Contrastive learning has been studied for improving the performance of learning sentence embeddings. The current state-of-the-art method is the SimCSE, which takes dropout as the data augmentation method and feeds a pre-trained transformer…

计算与语言 · 计算机科学 2021-11-25 Junlei Zhang , Zhenzhong lan

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

计算机视觉与模式识别 · 计算机科学 2022-11-03 Zhiwei Lin , Yongtao Wang , Hongxiang Lin

Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature…

计算机视觉与模式识别 · 计算机科学 2021-10-15 Yifan Zhang , Bryan Hooi , Dapeng Hu , Jian Liang , Jiashi Feng

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…

计算机视觉与模式识别 · 计算机科学 2021-08-20 Anjan Dutta , Massimiliano Mancini , Zeynep Akata

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…

计算机视觉与模式识别 · 计算机科学 2022-11-22 Jiabo Huang , Shaogang Gong

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

计算与语言 · 计算机科学 2021-09-23 Aili Shen , Xudong Han , Trevor Cohn , Timothy Baldwin , Lea Frermann