홈 › Papers

Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining

2022-11-07 · arXiv 2022 11 · Qiang Chen, Jian Wang, Chuchu Han, Shan Zhang, Zexian Li, Xiaokang Chen, Jiahui Chen, Xiaodi Wang, Shuming Han, Gang Zhang, Haocheng Feng, Kun Yao, Junyu Han, Errui Ding, Jingdong Wang

We present a strong object detector with encoder-decoder pretraining and finetuning. Our method, called Group DETR v2, is built upon a vision transformer encoder ViT-Huge~\cite{dosovitskiy2020image}, a DETR variant DINO~\cite{zhang2022dino}, and an efficient DETR training method Group DETR~\cite{chen2022group}. The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO. Group DETR v2 achieves $\textbf{64.5}$ mAP on COCO test-dev, and establishes a new SoTA on the COCO leaderboard https://paperswithcode.com/sota/object-detection-on-coco

📄 PDF Abstract BibTeX arXiv:2211.03594

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderObjectobject-detection Object Detection

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Position-Wise Feed-Forward Layer 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Adam 설명 없음

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer

2024-07-15 · Yu Wang, Xiangbo Su, Qiang Chen, Xinyu Zhang 외

Open-vocabulary object detection focusing on detecting novel categories guided by natural language. In this report, we propose Open-Vocabulary Light-Weighted Detection Transformer (OVLW-DETR), a deployment friendly open-…

Language Modeling Language Modelling object-detection Object Detection+2

DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection

2023-04-14 · CVPR 2023 1 · Zongheng Tang, Yifan Sun, Si Liu, Yi Yang

This paper presents a DETR-based method for cross-domain weakly supervised object detection (CDWSOD), aiming at adapting the detector from source to target domain through weak supervision. We think DETR has strong potent…

Decoder object-detection Object Detection Weakly Supervised Object Detection

RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervision

2024-09-13 · Shuo Wang, Chunlong Xia, Feng Lv, Yifeng Shi

RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO serie…

Decoder object-detection Object Detection

Points as Queries: Weakly Semi-supervised Object Detection by Points

2021-04-15 · CVPR 2021 1 · Liangyu Chen, Tong Yang, Xiangyu Zhang, Wei zhang 외

We propose a novel point annotated setting for the weakly semi-supervised object detection task, in which the dataset comprises small fully annotated images and large weakly annotated images by points. It achieves a bala…

object-detection Object Detection Semi-Supervised Object Detection

Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective

2024-01-01 · CVPR 2024 1 · Jinjing Zhao, Fangyun Wei, Chang Xu

With the transformative impact of the Transformer DETR pioneered the application of the encoder-decoder architecture to object detection. A collection of follow-up research e.g. Deformable DETR aims to enhance DETR w…