English
Related papers

Related papers: V-DETR: DETR with Vertex Relative Position Encodin…

200 papers

Relative position encoding (RPE) is important for transformer to capture sequence ordering of input tokens. General efficacy has been proven in natural language processing. However, in computer vision, its efficacy is not well studied and…

Computer Vision and Pattern Recognition · Computer Science 2021-07-30 Kan Wu , Houwen Peng , Minghao Chen , Jianlong Fu , Hongyang Chao

This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling. Our method introduces learnable spatial relationships between object queries…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Zhengjian Kang , Ye Zhang , Xiaoyu Deng , Xintao Li , Yongzhe Zhang

DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features in the transformer decoder remain fixed,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Chuxin Wang , Wenfei Yang , Xiang Liu , Tianzhu Zhang

This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Xiuquan Hou , Meiqin Liu , Senlin Zhang , Ping Wei , Badong Chen , Xuguang Lan

We introduce a novel MV-DETR pipeline which is effective while efficient transformer based detection method. Given input RGBD data, we notice that there are super strong pretraining weights for RGB data while less effective works for depth…

Computer Vision and Pattern Recognition · Computer Science 2024-08-14 Zichao Dong , Yilin Zhang , Xufeng Huang , Hang Ji , Zhan Shi , Xin Zhan , Junbo Chen

We propose 3DETR, an end-to-end Transformer based object detection model for 3D point clouds. Compared to existing detection methods that employ a number of 3D-specific inductive biases, 3DETR requires minimal modifications to the vanilla…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Ishan Misra , Rohit Girdhar , Armand Joulin

In this paper, we are interested in Detection Transformer (DETR), an end-to-end object detection approach based on a transformer encoder-decoder architecture without hand-crafted postprocessing, such as NMS. Inspired by Conditional DETR, an…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Xiaokang Chen , Fangyun Wei , Gang Zeng , Jingdong Wang

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a…

Computer Vision and Pattern Recognition · Computer Science 2023-10-02 Depu Meng , Xiaokang Chen , Zejia Fan , Gang Zeng , Houqiang Li , Yuhui Yuan , Lei Sun , Jingdong Wang

Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works…

Computer Vision and Pattern Recognition · Computer Science 2023-07-31 Changyong Shu , JIajun Deng , Fisher Yu , Yifan Liu

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Manyuan Zhang , Guanglu Song , Yu Liu , Hongsheng Li

Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Hongzhi Gao , Zheng Chen , Zehui Chen , Lin Chen , Jiaming Liu , Shanghang Zhang , Feng Zhao

Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Zhenxin Li , Shiyi Lan , Jose M. Alvarez , Zuxuan Wu

Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Eslam Mohamed , Ahmad El-Sallab

DEtection TRansformer (DETR) started a trend that uses a group of learnable queries for unified visual perception. This work begins by applying this appealing paradigm to LiDAR-based point cloud segmentation and obtains a simple yet…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Zeqi Xiao , Wenwei Zhang , Tai Wang , Chen Change Loy , Dahua Lin , Jiangmiao Pang

With the prevalence of LiDAR sensors in autonomous driving, 3D object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames…

Computer Vision and Pattern Recognition · Computer Science 2022-08-11 Zhipeng Luo , Changqing Zhou , Liang Pan , Gongjie Zhang , Tianrui Liu , Yueru Luo , Haiyu Zhao , Ziwei Liu , Shijian Lu

Despite the promising results, existing oriented object detection methods usually involve heuristically designed rules, e.g., RRoI generation, rotated NMS. In this paper, we propose an end-to-end framework for oriented object detection,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Qiang Zhou , Chaohui Yu , Zhibin Wang , Fan Wang

We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression…

Computer Vision and Pattern Recognition · Computer Science 2020-05-29 Nicolas Carion , Francisco Massa , Gabriel Synnaeve , Nicolas Usunier , Alexander Kirillov , Sergey Zagoruyko

3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships. Therefore, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Yongdong Luo , Haojia Lin , Xiawu Zheng , Yigeng Jiang , Fei Chao , Jie Hu , Guannan Jiang , Songan Zhang , Rongrong Ji

In this paper, we develop position embedding transformation (PETR) for multi-view 3D object detection. PETR encodes the position information of 3D coordinates into image features, producing the 3D position-aware features. Object query can…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Yingfei Liu , Tiancai Wang , Xiangyu Zhang , Jian Sun

Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their performance through self-supervised pre-training of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-04 Yan Ma , Weicong Liang , Bohan Chen , Yiduo Hao , Bojian Hou , Xiangyu Yue , Chao Zhang , Yuhui Yuan
‹ Prev 1 2 3 10 Next ›