Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019045802) DISTANCE METRIC LEARNING USING PROXIES
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2019/045802 International Application No.: PCT/US2018/032538
Publication Date: 07.03.2019 International Filing Date: 14.05.2018
IPC:
G06K 9/46 (2006.01) ,G06K 9/66 (2006.01) ,G06K 9/62 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36
Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46
Extraction of features or characteristics of the image
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62
Methods or arrangements for recognition using electronic means
64
using simultaneous comparisons or correlations of the image signals with a plurality of references, e.g. resistor matrix
66
references adjustable by an adaptive method, e.g. learning
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62
Methods or arrangements for recognition using electronic means
Applicants:
GOOGLE LLC [US/US]; 1600 Amphitheatre Parkway Mountain View, California 94043, US
Inventors:
MOYSHOVITZ-ATTIAS, Yair; US
LEUNG, King Hong; US
SINGH, Saurabh; US
TOSHEV, Alexander; US
IOFFE, Sergey; US
Agent:
PROBST, Joseph J.; US
BATAVIA, Neil, M.; US
Priority Data:
15/690,42630.08.2017US
15/710,37720.09.2017US
Title (EN) DISTANCE METRIC LEARNING USING PROXIES
(FR) APPRENTISSAGE DE MESURE DE DISTANCE À L'AIDE DE MANDATAIRES
Abstract:
(EN) The present disclosure provides systems and methods that enable distance metric learning using proxies. A machine-learned distance model can be trained in a proxy space in which a loss function compares an embedding provided for an anchor data point of a training dataset to a positive proxy and one or more negative proxies, where each of the positive proxy and the one or more negative proxies serve as a proxy for two or more data points included in the training dataset. Thus, each proxy can approximate a number of data points, enabling faster convergence. According to another aspect, the proxies of the proxy space can themselves be learned parameters, such that the proxies and the model are trained jointly. Thus, the present disclosure enables faster convergence (e.g., reduced training time). The present disclosure provides example experiments which demonstrate a new state of the art on several popular training datasets.
(FR) L'invention concerne des systèmes et des procédés permettant un apprentissage de mesure de distance à l'aide de mandataires. Un modèle de distance appris par machine peut être appris dans un espace mandataire où une fonction de perte compare une intégration prévue pour un point de données d'ancrage d'un ensemble de données d'apprentissage avec un mandataire positif et un ou plusieurs mandataires négatifs, chaque mandataire parmi le mandataire positif et le ou les mandataires négatifs servant de mandataire pour au moins deux points de données inclus dans l'ensemble de données d'apprentissage. Chaque mandataire peut estimer approximativement un certain nombre de points de données, ce qui permet une convergence plus rapide. Selon un autre aspect, les mandataires de l'espace mandataires peuvent eux-mêmes être des paramètres appris afin d'apprendre conjointement les mandataires et le modèle. Ainsi, l'invention permet une convergence plus rapide (par exemple, un temps d'apprentissage réduit). L'invention concerne des expériences données à titre d'exemple qui démontrent un nouvel état de la technique sur plusieurs ensembles de données d'apprentissage populaires.
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: English (EN)
Filing Language: English (EN)