公开(公告)号：US20220270353A1

公开(公告)日：2022-08-25

申请号：US17740211

申请日：2022-05-09

Applicant: Lemon Inc.

Inventor： Song Bai ,  Jieneng Chen ,  Shuyang Sun ,  Ju He ,  Bin Lu

IPC: G06V10/77 ,  G06V10/774 ,  G06V10/48 ,  G06V10/26 ,  G06N20/00

Abstract: Implementations of the present disclosure relate to methods, devices, and computer program products for data augmentation. In the method, mixed data is generated from first data and second data, and the mixed data comprises a first portion from the first data and a second portion from the second data. An attention map is obtained for the mixed data based on distributions of the first and second portions in the mixed data, here the attention map describes contributions of the first and second data to the mixed data. A label is determined for the mixed data based on the attention map and a first label for the first data and a second label for the second data. With these implementations, the label is determined based on the contributions of the first and second images in an accurate and effective way, and thus has a value that is much closer to the ground true.

公开(公告)号：US20250113087A1

公开(公告)日：2025-04-03

申请号：US18395356

申请日：2023-12-22

Applicant: Lemon Inc.

Inventor： Ju He ,  Qihang Yu ,  Inkyu Shin ,  Xueqing Deng ,  Xiaohui Shen ,  Liang-Chieh Chen

IPC: H04N21/845 ,  H04N21/44

Abstract: The present disclosure describes techniques for implementing video segmentation. A video is divided into a plurality of clips. Each of the plurality of clips comprises several frames. Axial-trajectory attention is applied to each of the plurality of clips by a first sub-model. Clip features corresponding to each of the plurality of clips are generated by the first sub-model. A set of object queries corresponding to each of the plurality of clips is generated based on the clip features by a transformer decoder. Trajectory attention is applied to refine sets of object queries corresponding to the plurality of clips by a second sub-model. Video-level segmentation results are generated based on the refined object queries.

公开(公告)号：US20250045929A1

公开(公告)日：2025-02-06

申请号：US18365060

申请日：2023-08-03

Applicant: Lemon Inc.

Inventor： Qihang Yu ,  Ju He ,  Xueqing Deng ,  Xiaohui Shen ,  Liang-Chieh Chen

IPC: G06T7/12 ,  G06T3/40 ,  G06V10/44 ,  G06V10/764 ,  G06V10/771

Abstract: Single-stage frameworks for open-vocabulary panoptic segmentation are provided. One aspect provides a computing system comprising a processor and memory storing instructions that, when executed by the processor, cause the processor to: receive an image; extract a plurality of feature maps from the image using a convolutional neural network-based vision-language model; generate a plurality of pixel features from the plurality of feature maps; generate a plurality of mask predictions from the plurality of pixel features; generate a plurality of in-vocabulary class predictions corresponding to the plurality of mask predictions using the plurality of pixel features; generate a plurality of out-of-vocabulary class predictions using the plurality of feature maps; perform geometric ensembling on the plurality of in-vocabulary class predictions and the plurality of out-of-vocabulary class predictions to generate a plurality of final class predictions; and output the plurality of mask predictions and the plurality of final class predictions.