English
Related papers

Related papers: FQDet: Fast-converging Query-based Detector

200 papers

State-of-the-art handwritten text recognition (HTR) systems commonly use Transformers, whose growing key-value (KV) cache makes decoding slow and memory-intensive. We introduce DRetHTR, a decoder-only model built on Retentive Networks…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Changhun Kim , Martin Mayr , Thomas Gorges , Fei Wu , Mathias Seuret , Andreas Maier , Vincent Christlein

Unsupervised domain adaptation object detection (UDAOD) research on Detection Transformer(DETR) mainly focuses on feature alignment and existing methods can be divided into two kinds, each of which has its unresolved issues. One-stage…

Computer Vision and Pattern Recognition · Computer Science 2024-01-19 Weixi Weng , Chun Yuan

In standard hospital blood tests, the traditional process requires doctors to manually isolate leukocytes from microscopic images of patients' blood using microscopes. These isolated leukocytes are then categorized via automatic leukocyte…

Computer Vision and Pattern Recognition · Computer Science 2024-01-11 Yifei Chen , Chenyan Zhang , Ben Chen , Yiyu Huang , Yifei Sun , Changmiao Wang , Xianjun Fu , Yuxing Dai , Feiwei Qin , Yong Peng , Yu Gao

Query-based methods have garnered significant attention in object detection since the advent of DETR, the pioneering query-based detector. However, these methods face challenges like slow convergence and suboptimal performance. Notably,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Hongbin Xu , Yamei Xia , Shuai Zhao , Bo Cheng

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Neural and Evolutionary Computing · Computer Science 2019-11-07 Noam Shazeer

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Shilong Liu , Feng Li , Hao Zhang , Xiao Yang , Xianbiao Qi , Hang Su , Jun Zhu , Lei Zhang

The training paradigm of DETRs is heavily contingent upon pre-training their backbone on the ImageNet dataset. However, the limited supervisory signals provided by the image classification task and one-to-one matching strategy result in an…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Haodong Ouyang

Small object detection in complex scenes exposes a fundamental tension in neural network design: backbone attention distributes computation uniformly regardless of content, pyramid necks inflate activation magnitudes during upsampling…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Bo Gao , Jingcheng Tong , Xingsheng Chen , Han Yu , Zichen Li

Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes. This diminishes the detectors' speed, thereby becoming the computational bottleneck in advanced oriented object detection systems. This…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Xingxing Xie , Gong Cheng , Jiabao Wang , Xiwen Yao , Junwei Han

Self-supervised pre-training and transformer-based networks have significantly improved the performance of object detection. However, most of the current self-supervised object detection methods are built on convolutional-based…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Guoqiang Jin , Fan Yang , Mingshan Sun , Ruyi Zhao , Yakun Liu , Wei Li , Tianpeng Bao , Liwei Wu , Xingyu Zeng , Rui Zhao

This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Fangyi Chen , Han Zhang , Kai Hu , Yu-kai Huang , Chenchen Zhu , Marios Savvides

Dense object detection is widely used in automatic driving, video surveillance, and other fields. This paper focuses on the challenging task of dense object detection. Currently, detection methods based on greedy algorithms, such as…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Yueming Huang , Chenrui Ma , Hao Zhou , Hao Wu , Guowu Yuan

Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted components, it is very difficult to reason about the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Wenchao Zhang , Chong Fu , Xiangshi Chang , Tengfei Zhao , Xiang Li , Chiu-Wing Sham

Detection Transformers represent end-to-end object detection approaches based on a Transformer encoder-decoder architecture, exploiting the attention mechanism for global relation modeling. Although Detection Transformers deliver results on…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Bastian Wittmann , Fernando Navarro , Suprosanna Shit , Bjoern Menze

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Yangyang Xu , Xiangtai Li , Haobo Yuan , Yibo Yang , Lefei Zhang

It has been proven that, compared to using 32-bit floating-point numbers in the training phase, Deep Convolutional Neural Networks (DCNNs) can operate with low precision during inference, thereby saving memory space and power consumption.…

Artificial Intelligence · Computer Science 2022-10-03 Binyi Wu , Bernd Waschneck , Christian Georg Mayr

This paper proposes novel methods to enhance the performance of monocular 3D object detection models by leveraging the generalized feature extraction capabilities of a vision foundation model. Unlike traditional CNN-based approaches, which…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Jihyeok Kim , Seongwoo Moon , Sungwon Nah , David Hyunchul Shim

Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance. However, the learned queries usually explore the global context to generate the final set…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Tian Qiu , Linyun Zhou , Wenxiang Xu , Lechao Cheng , Zunlei Feng , Mingli Song

This paper is on Few-Shot Object Detection (FSOD), where given a few templates (examples) depicting a novel class (not seen during training), the goal is to detect all of its occurrences within a set of images. From a practical perspective,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Adrian Bulat , Ricardo Guerrero , Brais Martinez , Georgios Tzimiropoulos

Object localization in general environments is a fundamental part of vision systems. While dominating on the COCO benchmark, recent Transformer-based detection methods are not competitive in diverse domains. Moreover, these methods still…

Computer Vision and Pattern Recognition · Computer Science 2023-07-21 Mingqiao Ye , Lei Ke , Siyuan Li , Yu-Wing Tai , Chi-Keung Tang , Martin Danelljan , Fisher Yu
‹ Prev 1 4 5 6 7 8 10 Next ›