paper-with-me

홈 › Papers

OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer

2024-06-09 · Shengjian Wu, Li Sun, Qingli Li

DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge compared with CNN-based detectors. This paper aims to stabilize DETR training through the online distillation. It utilizes a teacher model, accumulated by Exponential Moving Average (EMA), and distills its knowledge into the online model in following three aspects. First, the matching relation between object queries and ground truth (GT) boxes in the teacher is employed to guide the student, so queries within the student are not only assigned labels based on their own predictions, but also refer to the matching results from the teacher. Second, the teacher's initial query is given to the online student, and its prediction is directly constrained by the corresponding output from the teacher. Finally, the object queries from teacher's different decoding stages are used to build the auxiliary groups to accelerate the convergence. For each GT, two queries with the least matching costs are selected into this extra group, and they predict the GT box and participate the optimization. Extensive experiments show that the proposed OD-DETR successfully stabilizes the training, and significantly increases the performance without bringing in more parameters.

📄 PDF Abstract BibTeX arXiv:2406.05791

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling

2024-01-01 · CVPR 2024 1 · Yu Wang, Xin Li, Shengzhao Weng, Gang Zhang 외

DETR is a novel end-to-end transformer architecture object detector which significantly outperforms classic detectors when scaling up. In this paper we focus on the compression of DETR with knowledge distillation. Wh…

General KnowledgeKnowledge Distillation

Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling

2022-11-15 · Yu Wang, Xin Li, Shengzhao Wen, Fukui Yang 외

DETR is a novel end-to-end transformer architecture object detector, which significantly outperforms classic detectors when scaling up the model size. In this paper, we focus on the compression of DETR with knowledge dis…

General KnowledgeKnowledge Distillation

DETRDistill: A Universal Knowledge Distillation Framework for DETR-families

2022-11-17 · ICCV 2023 1 · Jiahao Chang, Shuo Wang, HaiMing Xu, Zehui Chen 외

Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world. While knowledge distillation (KD) can be…

Knowledge Distillationobject-detectionObject Detection

Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection

2023-01-01 · ICCV 2023 1 · Liangqi Li, Jiaxu Miao, Dahu Shi, Wenming Tan 외

Current methods for open-vocabulary object detection (OVOD) rely on a pre-trained vision-language model (VLM) to acquire the recognition ability. In this paper, we propose a simple yet effective framework to Distill …

Knowledge DistillationLanguage ModelingLanguage Modellingobject-detection+3

CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs

2025-02-15 · Qizhen Lan, Qing Tian

Object detection has advanced significantly with Detection Transformers (DETRs). However, these models are computationally demanding, posing challenges for deployment in resource-constrained environments (e.g., self-driv…

DenoisingKnowledge Distillationobject-detectionObject Detection+1