公开(公告)号：US11983239B2

公开(公告)日：2024-05-14

申请号：US17342483

申请日：2021-06-08

Applicant: Lemon Inc.

Inventor： Xiaochen Lian ,  Mingyu Ding ,  Linjie Yang ,  Peng Wang ,  Xiaojie Jin

IPC: G06V20/56 ,  G06F18/213 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06V10/32 ,  G06V10/82

CPC classification number: G06F18/213 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06V10/82

Abstract: Systems and methods for obtaining attention features are described. Some examples may include: receiving, at a projector of a transformer, a plurality of tokens associated with image features of a first dimensional space; generating, at the projector of the transformer, projected features by concatenating the plurality of tokens with a positional map, the projected features having a second dimensional space that is less than the first dimensional space; receiving, at an encoder of the transformer, the projected features and generating encoded representations of the projected features using self-attention; decoding, at a decoder of the transformer, the encoded representations and obtaining a decoded output; and projecting the decoded output to the first dimensional space and adding the image features of the first dimensional space to obtain attention features associated with the image features.

公开(公告)号：US20220391636A1

公开(公告)日：2022-12-08

申请号：US17342486

申请日：2021-06-08

Applicant: Lemon Inc.

Inventor： Xiaochen Lian ,  Linjie Yang ,  Peng Wang ,  Xiaojie Jin ,  Mingyu Ding

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods for searching a search space are disclosed. Some examples may include using a first parallel module including a first plurality of stacked searching blocks and a second plurality of stacked searching blocks to output first feature maps of a first resolution and to output second feature maps of a second resolution. In some examples, a fusion module may include a plurality of searching blocks, where the fusion module is configured to generate multiscale feature maps by fusing one or more feature maps of the first resolution received from the first parallel module with one or more feature maps of the second resolution received from the first parallel module, and wherein the fusion module is configured to output the multiscale feature maps and output third feature maps of a third resolution.

公开(公告)号：US20220391635A1

公开(公告)日：2022-12-08

申请号：US17342483

申请日：2021-06-08

Applicant: Lemon Inc.

Inventor： Xiaochen Lian ,  Mingyu Ding ,  Linjie Yang ,  Peng Wang ,  Xiaojie Jin

IPC: G06K9/62 ,  G06N3/04

Abstract: Systems and methods for obtaining attention features are described. Some examples may include: receiving, at a projector of a transformer, a plurality of tokens associated with image features of a first dimensional space; generating, at the projector of the transformer, projected features by concatenating the plurality of tokens with a positional map, the projected features having a second dimensional space that is less than the first dimensional space; receiving, at an encoder of the transformer, the projected features and generating encoded representations of the projected features using self-attention; decoding, at a decoder of the transformer, the encoded representations and obtaining a decoded output; and projecting the decoded output to the first dimensional space and adding the image features of the first dimensional space to obtain attention features associated with the image features.

公开(公告)号：US20240221359A1

公开(公告)日：2024-07-04

申请号：US18540503

申请日：2023-12-14

Applicant: Lemon Inc. ,  Beijing Zitiao Network Technology Co., Ltd.

Inventor： Xiaojie Jin ,  Sen Pei

IPC: G06V10/764 ,  G06V10/44

CPC classification number: G06V10/764 ,  G06V10/44

Abstract: The present disclosure provides an image processing method, an electronic device, and a computer-readable storage medium. The method comprises: obtaining an image feature corresponding to a first image, where the image feature comprises a domain feature and a class feature; performing a feature filtering processing on the domain feature in the image feature to obtain the class feature of the first image, where a relevance between the domain feature and an image classification of the first image is below a first threshold; and determining an image class of the first image according to the class feature.

公开(公告)号：US11804043B2

公开(公告)日：2023-10-31

申请号：US17348181

申请日：2021-06-15

Applicant: Lemon Inc.

Inventor： Xiaojie Jin ,  Yi-Wen Chen ,  Xiaohui Shen

IPC: G06K9/00 ,  G06V20/40 ,  G06V10/46 ,  G06F18/214

CPC classification number: G06V20/41 ,  G06F18/214 ,  G06V10/462 ,  G06V2201/07

Abstract: The present disclosure describes techniques of detecting objects in a video. The techniques comprises extracting features from each frame of the video; generating a first attentive feature by applying a first attention model on at least some of features extracted from any particular frame among the plurality of frames, wherein the first attention model identifies correlations between a plurality of locations in the particular frame by computing relationships between any two locations among the plurality of locations; generating a second attentive feature by applying a second attention model on at least one pair of features at different levels selected from the features extracted from the particular frame, wherein the second attention model identifies a correlation between at least one pair of locations corresponding to the at least one pair of features; and generating a representation of an object included in the particular frame.

公开(公告)号：US11836595B1

公开(公告)日：2023-12-05

申请号：US17816167

申请日：2022-07-29

Applicant: Lemon Inc.

Inventor： Linjie Yang ,  Taojiannan Yang ,  Xiaojie Jin

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/04 ,  G06N3/08

Abstract: Systems and methods for performing neural architecture search are provided. In one aspect, the system includes a processor configured to select a plurality of candidate neural networks within a search space, evaluate a performance of each of the plurality of candidate neural networks by: training each candidate neural network on a training dataset to perform the predetermined task and determining a ranking metric for each candidate neural network based on an objective function. The ranking metric includes a weight-related metric that is determined based on weights of a prediction layer of each respective candidate neural network before and after the respective candidate neural network is trained. The processor is configured to rank the plurality of candidate neural networks based on the determined ranking metrics.