CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...Antonio Tejero de Pablos
Introduction of the CVPR2022 paper: Balanced multimodal learning via on-the-fly gradient modulation @ The All Japan Computer Vision Study Group (2022/08/07)
ArcFace: Additive Angular Margin Loss for Deep Face Recognitionharmonylab
出典: Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou : ArcFace: Additive Angular Margin Loss for Deep Face Recognition, Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2019)
公開URL:https://arxiv.org/abs/1801.07698
概要 : 顔認識のための畳み込みニューラルネットワーク(DCNN)の課題は識別力を高める適切な損失関数を設計することです。本論文では、顔認識のための識別性の高い特徴量を得るために、Additive Angular Margin Loss (ArcFace)を提案します。一般的な顔認識ベンチマークから1兆ペアの大規模データセットなどを用いて、最先端顔認識技術との比較実験を行いました。結果は、従来手法を凌駕する精度を持つことが明らかになりました。
CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...Antonio Tejero de Pablos
Introduction of the CVPR2022 paper: Balanced multimodal learning via on-the-fly gradient modulation @ The All Japan Computer Vision Study Group (2022/08/07)
ArcFace: Additive Angular Margin Loss for Deep Face Recognitionharmonylab
出典: Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou : ArcFace: Additive Angular Margin Loss for Deep Face Recognition, Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2019)
公開URL:https://arxiv.org/abs/1801.07698
概要 : 顔認識のための畳み込みニューラルネットワーク(DCNN)の課題は識別力を高める適切な損失関数を設計することです。本論文では、顔認識のための識別性の高い特徴量を得るために、Additive Angular Margin Loss (ArcFace)を提案します。一般的な顔認識ベンチマークから1兆ペアの大規模データセットなどを用いて、最先端顔認識技術との比較実験を行いました。結果は、従来手法を凌駕する精度を持つことが明らかになりました。
In order to protect privacy, many technologies are used for various purposes. This slide is an introductory overview of these technologies for each purpose, including private information retrieval, secure computation, pseudonymization, anonymization and differential privacy.
超スマート社会の光と影:普通の人はどう変わる Opportunities and Perils of the "Society 5.0": What it...Takushi Otani
The Japan’s The 5th Science and Technology Basic Plan proposed an initiative to build "society 5.0" where ICT would prevail and change many feature of society, such as industry, health-care, consumers' life and so on. This presentation was held at a symposium organized by the Center for Research and Development Strategy, Japan Science and Technology Agency, and pointed out opportunities and perils of ordinary people in the "Society 5.0" from the view of information ethics. (in Japanese)
第5期科学技術基本計画(http://www8.cao.go.jp/cstp/kihonkeikaku/index5.html)が提案する超スマート社会において、「普通の人」にはどのようなチャンスとリスクがあるか、情報倫理学の観点から分析。2016年2月26日のCRDSシンポジウムで発表。
This slide shows (1) AI and Accountability , (2) AI Ethics, (2) Privacy Protection. Several AI ethics documents such as IEEE EAD, EC-HELG Ethics Guideline for Trustworthy AI, Social Principles of Human-Centric AI(Japan), focus on AI's transparency, accountability and trust. We follow the discussions of these documents around the above (1),(2) and (3) topics.
What is Accountability of AI? We answer to this question by clarifying responsibility, explainability and liability of limited autonomous AI with several bright and dark real examples.
Then we move to the concept of "Trust " which is of not limited to single AI system but group AI ‘s behavior.
K-anonymization has been regarded as a great method to make a bad person indistinguishable among k people whose quasi identifiers are same.
It, unfortunately, has a problematic side effect of defamation. In this case, defamation means the case where other good k-1 people are suspected as a bad person because both of a bad person and good people have the same quasi identifiers because of k-anonymization. This slide shows a mathematical model of defamation and proposes an algorithm which minimizes the probability of defamation.
Social Effects by the Singularity -Pre-Singularity Era-Hiroshi Nakagawa
Contents:
Stance of scientists community against Pre-Singularity problems
Amplification vs. Replacement
AI takes over jobs
Boarder line between amplification and replacement
Autonomous driver: trolley problem
The right to be forgotten
Towards black box
Responsibility
Vulnerability of financial dealing system made of many AI agent traders connected via internet
AI and weapon
Filter bubble phenomena
Analogy: Selfish gene
AI and privacy
The right to be forgotten, Profiling and Don’t Track
Feeling of friendliness to android
Again self conscious and identity
Privacy Protectin Models and Defamation caused by k-anonymityHiroshi Nakagawa
Introduction of Privacy Protection Mathematical Models are the topics of this slide. The Models explained are 1) Private Information Retrieval, 2) IR with Homomorphic Encryption, 3) k-anonymity, 4) l-diversity, and finally 5) Defamation caused by k-Anonymity
Japanese Personal Information Protection Act (PIPA) was passed the diet in Sep.2015. De-identified Information is introduced. It is the data anonymized enough not to de-anonymized easily. It is permitted to freely use without the consent of data subject. Notice that pseudonymized is not regarded as De-identified Information. Boarder line between pseudonymized and anonymized is a critical issue. I discuss this topic in this slide.
セル生産方式におけるロボットの活用には様々な問題があるが,その一つとして 3 体以上の物体の組み立てが挙げられる.一般に,複数物体を同時に組み立てる際は,対象の部品をそれぞれロボットアームまたは治具でそれぞれ独立に保持することで組み立てを遂行すると考えられる.ただし,この方法ではロボットアームや治具を部品数と同じ数だけ必要とし,部品数が多いほどコスト面や設置スペースの関係で無駄が多くなる.この課題に対して音𣷓らは組み立て対象物に働く接触力等の解析により,治具等で固定されていない対象物が組み立て作業中に運動しにくい状態となる条件を求めた.すなわち,環境中の非把持対象物のロバスト性を考慮して,組み立て作業条件を検討している.本研究ではこの方策に基づいて,複数物体の組み立て作業を単腕マニピュレータで実行することを目的とする.このとき,対象物のロバスト性を考慮することで,仮組状態の複数物体を同時に扱う手法を提案する.作業対象としてパイプジョイントの組み立てを挙げ,簡易な道具を用いることで単腕マニピュレータで複数物体を同時に把持できることを示す.さらに,作業成功率の向上のために RGB-D カメラを用いた物体の位置検出に基づくロボット制御及び動作計画を実装する.
This paper discusses assembly operations using a single manipulator and a parallel gripper to simultaneously
grasp multiple objects and hold the group of temporarily assembled objects. Multiple robots and jigs generally operate
assembly tasks by constraining the target objects mechanically or geometrically to prevent them from moving. It is
necessary to analyze the physical interaction between the objects for such constraints to achieve the tasks with a single
gripper. In this paper, we focus on assembling pipe joints as an example and discuss constraining the motion of the
objects. Our demonstration shows that a simple tool can facilitate holding multiple objects with a single gripper.
【DLゼミ】XFeat: Accelerated Features for Lightweight Image Matchingharmonylab
公開URL:https://arxiv.org/pdf/2404.19174
出典:Guilherme Potje, Felipe Cadar, Andre Araujo, Renato Martins, Erickson R. ascimento: XFeat: Accelerated Features for Lightweight Image Matching, Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)
概要:リソース効率に優れた特徴点マッチングのための軽量なアーキテクチャ「XFeat(Accelerated Features)」を提案します。手法は、局所的な特徴点の検出、抽出、マッチングのための畳み込みニューラルネットワークの基本的な設計を再検討します。特に、リソースが限られたデバイス向けに迅速かつ堅牢なアルゴリズムが必要とされるため、解像度を可能な限り高く保ちながら、ネットワークのチャネル数を制限します。さらに、スパース下でのマッチングを選択できる設計となっており、ナビゲーションやARなどのアプリケーションに適しています。XFeatは、高速かつ同等以上の精度を実現し、一般的なラップトップのCPU上でリアルタイムで動作します。
81. IEEE Ethics Guideline
• 1. General Principles
• 2. Embedding Values into
Autonomous Intelligent Systems
• 3. Methodologies to Guide Ethical
Research and Design
• 4. Safety and Beneficence of
Artificial General Intelligence
• (AGI) and Artificial
Superintelligence (ASI)
• 5. Personal Data and Individual
Access Control
• 6. Reframing Autonomous Weapons
Systems
• 7. Economics/Humanitarian Issues
• 8. Law