-
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
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：US20220284590A1
公开(公告)日：2022-09-08
申请号：US17192599
申请日：2021-03-04
Applicant: Lemon Inc.
Inventor： Linjie Yang , Ziyu Jiang , Ding Liu , Longyin Wen
Abstract: Systems and method directed to performing video object segmentation are provided. In examples, video data representing a sequence of image frames and video data representing an object mask may be received at a video object segmentation server. Image features may be generated based on a first image frame of the sequence of image frames, image features may be generated based on a second image frame of the sequence of image frames; and object features may be generated based on the object mask. A transform matrix may be computed based on the image features of the first image frame and image features of the second image frame; the transform matrix may be applied to the object features resulting in transformed object features. A predicted object mask associated with the second image frame may be obtained by decoding the transformed object features.
-
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
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.
-
公开(公告)号：US20220398450A1
公开(公告)日：2022-12-15
申请号：US17348246
申请日：2021-06-15
Applicant: Lemon Inc.
Inventor： Xiaojie JIN , Daquan Zhou , Xiaochen Lian , Linjie Yang , Jiashi Feng
Abstract: A super-network comprising a plurality of layers may be generated. Each layer may comprise cells with different structures. A predetermined number of cells from each layer may be selected. A plurality of cells may be generated based on selected cells using a local mutation model, wherein the local mutation model comprises a mutation window for removing redundant edges from each selected cell. Performance of the plurality of cells may be evaluated using a differentiable fitness scoring function. The operations of the generating a plurality of cells using the local mutation model, the evaluating performance of the plurality of cells using the differentiable fitness scoring function and the selecting the subset of cells based on the evaluation results may be iteratively performed until the super-network converges. A search space for each layer may be generated based on a predetermined top number of cells with largest fitness scores after the super-network converges.
-
公开(公告)号：US20220284552A1
公开(公告)日：2022-09-08
申请号：US17192549
申请日：2021-03-04
Applicant: Lemon Inc.
Inventor： Linjie Yang , Ding Liu , Xueyan Zou
Abstract: Systems and methods are directed to inpainting video. More specifically, initial video data including a sequence of image frames containing missing or corrupted pixel information may be received. Optical flow displacement values and optical flow validity masks may be generated for neighboring image frames of initial video data. Image features from image feature maps of one or more neighboring image frames may be warp-shifted to image feature maps of a current image frame using the optical flow displacement values and warp-shifted image features from the feature maps of the one or more neighboring image frames may be selected based on one or more of the optical flow validity masks. A sequence of complete image frames may be generated based on the selected warp-shifted image features from the feature maps of the one or more neighboring image frames and image features from the image feature maps of the current image frame.
-
Patent Agency Ranking
公开(公告)号：US12205299B2
公开(公告)日：2025-01-21
申请号：US17396055
申请日：2021-08-06
Applicant: Lemon Inc.
Inventor： Linjie Yang , Peter Lin , Imran Saleemi
Abstract: The present disclosure describes techniques of improving video matting. The techniques comprise extracting features from each frame of a video by an encoder of a model, wherein the video comprises a plurality of frames; incorporating, by a decoder of the model, into any particular frame temporal information extracted from one or more frames previous to the particular frame, wherein the particular frame and the one or more previous frames are among the plurality of frames of the video, and the decoder is a recurrent decoder; and generating a representation of a foreground object included in the particular frame by the model, wherein the model is trained using segmentation dataset and matting dataset.
-
公开(公告)号：US20240338848A1
公开(公告)日：2024-10-10
申请号：US18296438
申请日：2023-04-06
Applicant: Lemon Inc.
Inventor： Sijie Zhu , Linjie Yang , Xiaohui Shen , Heng Wang
IPC: G06T7/73 , G06V10/75 , G06V10/77 , G06V10/774
CPC classification number: G06T7/74 , G06V10/751 , G06V10/7715 , G06V10/774 , G06T2207/20081
Abstract: A unified place recognition framework handles both retrieval and re-ranking with a unified transformer model. The re-ranking modules utilizes feature correlation, attention value, and x/y coordinates into account, and learns to determine whether an image pair is from a same location.
-
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
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
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.
-
10.发明申请公开(公告)号：US20250139954A1
公开(公告)日：2025-05-01
申请号：US18926902
申请日：2024-10-25
Applicant: Lemon Inc.
Inventor： Xueqing Deng , Qi Fan , Peng Wang , Linjie Yang , Xiaojie Jin
IPC: G06V10/778 , G06V10/77 , G06V10/82
Abstract: The present application discloses a method and an apparatus for training a backbone network, an image processing method and apparatus, and a device. A weight selection cycle is set, where the weight selection cycle may include at least one backbone network training cycle. The backbone network is trained with sample data in the current weight selection cycle, and a cumulative weight adjustment amount for each weight in the backbone network in the current weight selection cycle is recorded. A target weight for which the cumulative weight adjustment amount meets a preset condition is selected from the backbone network based on the cumulative weight adjustment amount for each weight, and only the target weight in the backbone network is adjusted in a next weight selection cycle, to complete training of the backbone network in the next weight selection cycle based on the adjusted target weight.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.017 seconds)
