公开(公告)号：US20250117947A1

公开(公告)日：2025-04-10

申请号：US18893037

申请日：2024-09-23

Applicant: NEC Laboratories America, Inc.

Inventor： Abhishek Aich ,  Yumin Suh ,  Samuel Schulter ,  Manyi Yao

IPC: G06T7/11 ,  B60W30/09 ,  G06V10/40 ,  G06V10/764

Abstract: Methods and systems for segmentation include encoding an image using a backbone model to generate feature maps. An exit point based on one of the feature maps. The feature maps are processed with a dynamic transformer encoder that includes layers, exiting the dynamic transformer encoder at a layer identified by the exit point. An output of the dynamic transformer encoder is decoded to output a segmentation of the image.

公开(公告)号：US20250118096A1

公开(公告)日：2025-04-10

申请号：US18904571

申请日：2024-10-02

Applicant: NEC Laboratories America, Inc.

Inventor： Samuel Schulter ,  Abhishek Aich ,  Vijay Kumar Baikampady Gopalkrishna

IPC: G06V20/70 ,  G06F40/40 ,  G06T11/60 ,  G06V10/774 ,  G06V10/82 ,  G06V10/86 ,  G06V20/50

Abstract: Methods and systems for object detection include generating a negative description for an input image based on a positive description of the input image using a language model. A negative image is generated based on the input image and the negative description by replacing a portion of the input image that is described by the positive description with content that is described by the negative description using a generative image model. An object detection model is trained with the input image, the positive description, the negative description, and the negative image.

公开(公告)号：US20240160927A1

公开(公告)日：2024-05-16

申请号：US18503313

申请日：2023-11-07

Applicant: NEC Laboratories America, Inc.

Inventor： Yumin Suh ,  Samuel Schulter ,  Xiang Yu ,  Abhishek Aich

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: Systems and methods for performing multiple tasks with a single artificial intelligence model that can include training a supernet model for an application by splitting the application into tasks, and splitting the supernet model into subnets. The methods and systems can further assign the tasks computing budgets, and match the tasks to subnets by matching the computing budget of the tasks to the computing capacity of the subnets. Further, the methods and systems can perform the tasks with matching subnets to produce parameters that are used by the supernet to perform the application. The supernet combines all of the task to produce a model for the application and the supernet retains weights for the tasks to be used in subsequent applications.

公开(公告)号：US20240378874A1

公开(公告)日：2024-11-14

申请号：US18659785

申请日：2024-05-09

Applicant: NEC Laboratories America, Inc.

Inventor： Samuel Schulter ,  Abhishek Aich

IPC: G06V10/80 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V20/70

Abstract: Systems and methods are provided for multi-dataset panoptic segmentation, including processing received images from multiple datasets to extract multi-scale features using a backbone network, each of the multiple datasets including a unique label space, generating text-embeddings for class names from the unique label space for each of the multiple datasets, and integrating the text-embeddings with visual features extracted from the received images to create a unified semantic space. A transformer-based segmentation model is trained using the unified semantic space to predict segmentation masks and classes for the received images, and a unified panoptic segmentation map is generated from the predicted segmentation masks and classes by performing inference using a panoptic interference algorithm.