Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)Yusuke Uchida
Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval. Another trend in the area of image retrieval is the use of binary feature such as ORB, FREAK, and BRISK. Considering the significant performance improvement in terms of accuracy in both image classification and retrieval by the Fisher vector of continuous feature descriptors, if the Fisher vector were also to be applied to binary features, we would receive the same benefits in binary feature based image retrieval and classification. In this paper, we derive the closed-form approximation of the Fisher vector of binary features which are modeled by the Bernoulli mixture model. In experiments, it is shown that the Fisher vector representation improves the accuracy of image retrieval by 25% compared with a bag of binary words approach.
Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)Yusuke Uchida
Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval. Another trend in the area of image retrieval is the use of binary feature such as ORB, FREAK, and BRISK. Considering the significant performance improvement in terms of accuracy in both image classification and retrieval by the Fisher vector of continuous feature descriptors, if the Fisher vector were also to be applied to binary features, we would receive the same benefits in binary feature based image retrieval and classification. In this paper, we derive the closed-form approximation of the Fisher vector of binary features which are modeled by the Bernoulli mixture model. In experiments, it is shown that the Fisher vector representation improves the accuracy of image retrieval by 25% compared with a bag of binary words approach.
US durable goods orders rose 1.8% in Jan vs. 1.7% increase expectedpaul young cpa, cga
This presentations looks at durable goods for United States. Durable goods are a key area in terms of looking at business investment. Business investment in areas like capital is key to productivity as well as business view on making strategic investments to expand their business.
You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話Yusuke Uchida
第7回全日本コンピュータビジョン勉強会「CVPR2021読み会」(前編)の発表資料です
https://kantocv.connpass.com/event/216701/
You Only Look One-level Featureの解説と、YOLO系の雑談や、物体検出における関連する手法等を広く説明しています
US durable goods orders rose 1.8% in Jan vs. 1.7% increase expectedpaul young cpa, cga
This presentations looks at durable goods for United States. Durable goods are a key area in terms of looking at business investment. Business investment in areas like capital is key to productivity as well as business view on making strategic investments to expand their business.
You Only Look One-level Featureの解説と見せかけた物体検出のよもやま話Yusuke Uchida
第7回全日本コンピュータビジョン勉強会「CVPR2021読み会」(前編)の発表資料です
https://kantocv.connpass.com/event/216701/
You Only Look One-level Featureの解説と、YOLO系の雑談や、物体検出における関連する手法等を広く説明しています
Semi supervised, weakly-supervised, unsupervised, and active learningYusuke Uchida
An overview of semi supervised learning, weakly-supervised learning, unsupervised learning, and active learning.
Focused on recent deep learning-based image recognition approaches.
DeNA AIシステム部内の輪講で発表した資料です。Deep fakesの種類やその検出法の紹介です。
主に下記の論文の紹介
S. Agarwal, et al., "Protecting World Leaders Against Deep Fakes," in Proc. of CVPR Workshop on Media Forensics, 2019.
A. Rossler, et al., "FaceForensics++: Learning to Detect Manipulated Facial Images," in Proc. of ICCV, 2019.
【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。
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.
7. 3.1 Belief Dynamics
• 検索によって信念がどのように変化したかに焦点を
当てる
• 検索の前後で信念のレベルを測る
– Rate your relative prior belief about the likelihood of each
outcome before you used the search engine
– Rate your relative posterior belief about the likelihood of
each outcome once you finished searching
• 回答は9段階、集計は5段階
NoYes EqualLean yes Lean no
14. 3.2 Answer Perceptions and Follow-on
Search
• 検索者は頻繁に複数の結果を確認するためその動
機を調査
– If you found an answer early in your search, did you still
consider multiple results before settling on your final
answer?
– 49%がyes
– そのモチベーションは最初の答えの確認
最初の答えを、反対
の答えから検証
15. 4.1 Searcher Questions
• Sep. 2012から2週間の間に230万人の米国内のBing
ユーザからのクエリをサンプルし、yes-no質問を自動抽
出
– user identifiers, timestamps, queries, result clicks, and the captions
(titles, snippets, URLs) of each of the top 10 results
– Be, have, do, 助動詞が利用されている疑問文を抽出
– 340万のyes-no質問を抽出された(サンプルの2%)
– Yes-no質問に対する信頼性の高い正解が得られる医療分野に限定、
専門家(内科医)に正解を求めた
• クエリは下記の条件を満たすようにフィルタ
– Top-10の検索結果が2週間の間で変わっていない
– セッション中唯一の検索クエリ、またはセッション中最後の検索
クエリで、それより前の検索で同じ単語が利用されていない
16. 4.1 Searcher Questions
• Yes-no質問に対する信頼性の高い正解が得られ
る医療分野に限定、Bingのクエリ分類器を用い、
医療分野の質問を抽出(2.5%)、そこからランダ
ムに1000個の質問をサンプル
• 信頼性担保のため少なくとも10ユーザから発行
された質問に限定
– Do food allergies make you tired?
食物アレルギーは疲労を引き起こすか
– Is congestive heart failure a heart attack?
うっ血性心不全は心臓麻痺か
– Can aspirin cause blood in urine?
アスピリンは血尿の原因となるか