Ray
Search results
知乎，让每一次点击都充满意义 —— 欢迎来到知乎，发现问题背后的世界。
Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [TPAMI 2022] Iterative energy-based projection on a normal data manifold for anomaly localization [2019]
Jun 23, 2020 · 另外还有两篇最近放出来的自监督学习的综述： Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey A survey on Semi-, Self- and Unsupervised Techniques in Image Classification
Jan 9, 2024 · 在强化学习（RL）与有监督学习（SL）混合的范式中，有监督微调（supervised fine-tuning）的目的是通过使用有标签的监督数据来改善强化学习智能体的性能。这阶段的目标是在强化学习任务之前，先通过监督学习阶段训练智能体，使其学到对任务的一些基本知识或技能。这可以提供更稳定的初始点，使 ...
[EMNLP 2022] Self-supervised Graph Masking Pre-training for Graph-to-Text Generation [paper] [COLING 2022] The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection [paper]
Feb 23, 2018 · 所以self-supervised learning他的目标并不仅仅是学出来的feature 在recognition task上要比imagenet pre-trained model好。更关键的是generalization和transfer的能力。他是否能够比imagenet pre-trained更能够adapt到其他的task，这其实是我们应该更加关心的一点。 （这里再扯开一点说，其实一切都是about generalization，RL最后能不 ...
论文名称：《Weakly Supervised Posture Mining for Fine-grained Classification》论文链接 ：https://o…
为啥Semi-supervised GAN这么好的技术，现在好像无人问津了？. - 知乎. 机器学习. 深度学习（Deep Learning）. 生成对抗网络（GAN）. 为啥Semi-supervised GAN这么好的技术，现在好像无人问津了？. 作为可以大量利用无监督数据同时又兼有监督辅助的算法，Semi-supervised GAN相关 ...
Self-Supervised Learning from Web Data for Multimodal Retrieval, arXiv 2019 Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models, CVPR 2018
Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases Comparison between Lumped-mass Modeling and Flow Simulation of the Reed-type Artificial Vocal Fold
