Several recent papers have explored self-supervised learning methods for vision transformers (ViT). Key approaches include:
1. Masked prediction tasks that predict masked patches of the input image.
2. Contrastive learning using techniques like MoCo to learn representations by contrasting augmented views of the same image.
3. Self-distillation methods like DINO that distill a teacher ViT into a student ViT using different views of the same image.
4. Hybrid approaches that combine masked prediction with self-distillation, such as iBOT.
技術動向の調査として、ICML Workshop Uncertainty & Robustness in Deep Learningの中で、面白そうなタイトルを中心に読んで各論文を4スライドでまとめました。
最新版:https://speakerdeck.com/masatoto/icml-2021-workshop-shen-ceng-xue-xi-falsebu-que-shi-xing-nituite-e0debbd2-62a7-4922-a809-cb07c5da2d08(文章を修正しました。)
Several recent papers have explored self-supervised learning methods for vision transformers (ViT). Key approaches include:
1. Masked prediction tasks that predict masked patches of the input image.
2. Contrastive learning using techniques like MoCo to learn representations by contrasting augmented views of the same image.
3. Self-distillation methods like DINO that distill a teacher ViT into a student ViT using different views of the same image.
4. Hybrid approaches that combine masked prediction with self-distillation, such as iBOT.
技術動向の調査として、ICML Workshop Uncertainty & Robustness in Deep Learningの中で、面白そうなタイトルを中心に読んで各論文を4スライドでまとめました。
最新版:https://speakerdeck.com/masatoto/icml-2021-workshop-shen-ceng-xue-xi-falsebu-que-shi-xing-nituite-e0debbd2-62a7-4922-a809-cb07c5da2d08(文章を修正しました。)
This document discusses generative adversarial networks (GANs) and their relationship to reinforcement learning. It begins with an introduction to GANs, explaining how they can generate images without explicitly defining a probability distribution by using an adversarial training process. The second half discusses how GANs are related to actor-critic models and inverse reinforcement learning in reinforcement learning. It explains how GANs can be viewed as training a generator to fool a discriminator, similar to how policies are trained in reinforcement learning.
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...Deep Learning JP
The document proposes modifications to self-attention in Transformers to improve faithful signal propagation without shortcuts like skip connections or layer normalization. Specifically, it introduces a normalization-free network that uses dynamic isometry to ensure unitary transformations, a ReZero technique to implement skip connections without adding shortcuts, and modifications to attention and normalization techniques to address issues like rank collapse in Transformers. The methods are evaluated on tasks like CIFAR-10 classification and language modeling, demonstrating improved performance over standard Transformer architectures.
First part shows several methods to sample points from arbitrary distributions. Second part shows application to population genetics to infer population size and divergence time using obtained sequence data.
第6回 統計・機械学習若手シンポジウムの公演で使用したユーザーサイド情報検索システムについてのスライドです。
https://sites.google.com/view/statsmlsymposium21/
Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data? (SDM 2022) https://arxiv.org/abs/2105.12353
Retrieving Black-box Optimal Images from External Databases (WSDM 2022) https://arxiv.org/abs/2112.14921
This document discusses generative adversarial networks (GANs) and their relationship to reinforcement learning. It begins with an introduction to GANs, explaining how they can generate images without explicitly defining a probability distribution by using an adversarial training process. The second half discusses how GANs are related to actor-critic models and inverse reinforcement learning in reinforcement learning. It explains how GANs can be viewed as training a generator to fool a discriminator, similar to how policies are trained in reinforcement learning.
【DL輪読会】Deep Transformers without Shortcuts: Modifying Self-attention for Fait...Deep Learning JP
The document proposes modifications to self-attention in Transformers to improve faithful signal propagation without shortcuts like skip connections or layer normalization. Specifically, it introduces a normalization-free network that uses dynamic isometry to ensure unitary transformations, a ReZero technique to implement skip connections without adding shortcuts, and modifications to attention and normalization techniques to address issues like rank collapse in Transformers. The methods are evaluated on tasks like CIFAR-10 classification and language modeling, demonstrating improved performance over standard Transformer architectures.
First part shows several methods to sample points from arbitrary distributions. Second part shows application to population genetics to infer population size and divergence time using obtained sequence data.
第6回 統計・機械学習若手シンポジウムの公演で使用したユーザーサイド情報検索システムについてのスライドです。
https://sites.google.com/view/statsmlsymposium21/
Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data? (SDM 2022) https://arxiv.org/abs/2105.12353
Retrieving Black-box Optimal Images from External Databases (WSDM 2022) https://arxiv.org/abs/2112.14921
生成AIがもたらすコンテンツ経済圏の新時代 The New Era of Content Economy Brought by Generative AI
[DL輪読会]MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
1. 1
DEEP LEARNING JP
[DL Papers]
http://deeplearning.jp/
MuseGAN:Multi-track Sequential Generative Adversarial
Networks for Symbolic Music Generation and
Accompaniment
Shu Kumata, Matsuo Lab
2. はじめに
• 本論⽂を選んだ理由
• ⾳楽⽣成に興味がある
• GANベースのモデルで⼊出⼒がピアノロール形式
• 書誌情報等
• Author
• Hao-Wen Dong,* Wen-Yi Hsiao,* Li-Chia Yang, and Yi-Hsuan Yang (*equal
contribution)
• Academia Sinica(China)
• AAAI2018