Oct 8, 2021 · Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully transformer-based architecture for image classification. In this paper, we integrate Vision and Detection Transformers (ViDT) to build an effective and efficient object detector.

transformer-based architecture for image classification. In this paper, we integrate Vision and Detection Transformers(ViDT) to build an effective and efficient ob-ject detector. ViDT introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector, followed by a computation-

Instead of utilizing a CNN to extract features, WB-DETR serializes the image directly and encodes the local features of input into each individual token.

In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information. To achieve this goal, we present TS3D, a Transformer-based Stereo-aware 3D object detector.

In this article, we propose an end-to-end transformer-based oriented object detector, consisting of three dedicated modules to address these issues. First, Gaussian positional encoding (PE) is proposed to encode the angle, position, and size of oriented boxes using Gaussian distributions.

Nov 1, 2023 · We provide a comprehensive summary of state-of-the-art Transformer-based object detectors from the past three years, highlighting recent breakthroughs in Transformer architecture for object detection.

Jul 27, 2023 · In this work, we develop a new image inpainting detection approach. First, we propose a locally enhanced transformer architecture tailored for image inpainting detection.

Mar 9, 2023 · Finally, based on the Swin Deformable Transformer backbone, we propose a novel object detection network, namely, Swin Deformable Transformer-BiPAFPN-YOLOX. experimental results on the COCO dataset show that the training period is reduced by 55.4%, average precision is increased by 2.4%, average precision of small objects is increased by 3.7% ...

Nov 1, 2024 · A Transformer-CNN architecture using a self-attention mechanism-based transformer and convolutional neural network (CNN) is proposed to improve the recognition rate of SOD, which uses the Transformer and CNN to extract the …

Feb 4, 2025 · Object recognition in remote sensing images presents unique challenges due to the diverse scales, shapes, and distributions of objects, particularly small and complex ones. Existing frameworks, such as RT-DETR, struggle to accurately detect small objects because of their limited ability to extract fine-grained details and integrate multi-scale information. To overcome these challenges, we ...