公开(公告)号：US20240037775A1

公开(公告)日：2024-02-01

申请号：US18212893

申请日：2023-06-22

Applicant: Omnious Co., Ltd.

Inventor： Saad IMRAN ,  Hyung Won CHOI

IPC: G06T7/70 ,  G06V10/25 ,  G06V20/70

CPC classification number: G06T7/70 ,  G06V10/25 ,  G06V20/70 ,  G06V2201/07 ,  G06T2207/20081

Abstract: A method of creating training data for model training is provided. The method includes: receiving image data including at least one fashion item; performing location box labeling on an item location box which indicates a location of an item included in the image data by using an item location detection model; calculating a location box labeling result value and a location box labeling confidence value; receiving a user's location box review value for the location box labeling result value; determining a location noise value of the location box review value by using the item location detection model; and determining the location box review value as location box training data if the location noise value meets a predetermined first criterion.

公开(公告)号：US20240037919A1

公开(公告)日：2024-02-01

申请号：US18212897

申请日：2023-06-22

Applicant: Omnious Co., Ltd.

Inventor： Eun Seop SHIN ,  Won Jong JO ,  Jeong Tae CHO ,  Ji Hun LEE ,  Hyung Won CHOI ,  Yun Hun JANG ,  Jun Cheol PARK

IPC: G06V10/774 ,  G06V20/70 ,  G06V20/60 ,  G06V20/30 ,  G06V10/77

CPC classification number: G06V10/774 ,  G06V20/70 ,  G06V20/60 ,  G06V20/30 ,  G06V10/7715

Abstract: A method of automatically improving artificial intelligence (AI) model performance is provided. The method includes: collecting image data including at least one item; performing pre-training based on self-supervised training for a pre-training model by using the image data; and setting initial values of the AI model and performing fine-tuning by using the pre-training model.

公开(公告)号：US20240037140A1

公开(公告)日：2024-02-01

申请号：US18212891

申请日：2023-06-22

Applicant: Omnious Co., Ltd.

Inventor： Jae Young JUN ,  Jun Cheol PARK ,  Yun Hun JANG ,  Hyung Won CHOI ,  Essalim CHAHRAZAD

IPC: G06F16/583 ,  G06F16/532 ,  G06T7/50 ,  G06T7/70 ,  G06T7/90 ,  G06V10/44 ,  G06V10/80

CPC classification number: G06F16/583 ,  G06F16/532 ,  G06T7/50 ,  G06T7/70 ,  G06T7/90 ,  G06V10/44 ,  G06V10/806 ,  G06V2201/07

Abstract: A method of searching for similar products using a multi-task learning (MTL) model is provided. The method includes: converting, by using a multi-task learning model utilizing a unified backbone network, each of an original image including a fashion item into a single vector including at least one multi-task attribute; and generating a visual search database by storing the original image and the single vector of the original image together.

公开(公告)号：US20240037912A1

公开(公告)日：2024-02-01

申请号：US18212901

申请日：2023-06-22

Applicant: Omnious Co., Ltd.

Inventor： Jae Young JUN ,  Jun Cheol PARK ,  Yun Hun JANG ,  Hyung Won CHOI

IPC: G06V10/764 ,  G06T7/11 ,  G06T7/50 ,  G06T7/90 ,  G06V20/70

CPC classification number: G06V10/764 ,  G06T7/11 ,  G06T7/50 ,  G06T7/90 ,  G06V20/70 ,  G06V2201/07 ,  G06T2207/10024 ,  G06T2207/30242

Abstract: A method for analyzing fashion attributes using large amounts of pieces of image data is provided. The method includes: collecting image data including at least one item; statistically analyzing on the image data based on an attribute classification AI model; and visualizing the results of the statistical analysis, wherein the attribute classification AI model is a model for detecting said at least one item included in the image data, and for recognizing, labeling and classifying fashion attributes of the at least one item.