paper-with-me

홈 › Papers

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

2024-07-15 · Yu Wang, Xiangbo Su, Qiang Chen, Xinyu Zhang, Teng Xi, Kun Yao, Errui Ding, Gang Zhang, Jingdong Wang

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-vocabulary detector with strong performance and low latency. Building upon OVLW-DETR, we provide an end-to-end training recipe that transferring knowledge from vision-language model (VLM) to object detector with simple alignment. We align detector with the text encoder from VLM by replacing the fixed classification layer weights in detector with the class-name embeddings extracted from the text encoder. Without additional fusing module, OVLW-DETR is flexible and deployment friendly, making it easier to implement and modulate. improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time open-vocabulary detectors on standard Zero-Shot LVIS benchmark. Source code and pre-trained models are available at [https://github.com/Atten4Vis/LW-DETR].

📄 PDF Abstract BibTeX arXiv:2407.10655

Code (1)

atten4vis/lw-detr 공식 구현 pytorch

Tasks

Language ModelingLanguage Modellingobject-detectionObject DetectionOpen-vocabulary object detectionOpen Vocabulary Object Detection

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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
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…

Similar Papers 제목 키워드 기반

A Lightweight Modular Framework for Low-Cost Open-Vocabulary Object Detection Training

2024-08-20 · Bilal Faye, Binta Sow, Hanane Azzag, Mustapha Lebbah

Object detection is a fundamental challenge in computer vision, centered on recognizing objects within images, with diverse applications in areas like image analysis, robotics, and autonomous vehicles. Although existing …

Autonomous VehiclesComputational Efficiencyobject-detectionObject Detection+5

Open-Vocabulary DETR with Conditional Matching

2022-03-22 · Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang 외

Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ideally, we would like to extend an open-vo…

Language Modellingobject-detectionObject DetectionOpen-vocabulary object detection+1

OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation

2026-03-07 · Leilei Wang, Longfei Liu, Xi Shen, Xuanlong Yu 외 arxiv

Real-time open-vocabulary object detection (OVOD) is essential for practical deployment in dynamic environments, where models must recognize a large and evolving set of categories under strict latency constraints. Curren…

Data AugmentationObject Detection

DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer

2026-05-11 · Soichiro Okazaki, Tatsuya Sasaki, Hiroki Ohashi arxiv

Open-vocabulary object detection (OVOD) aims to detect both seen and unseen categories, yet existing methods often struggle to generalize to novel objects due to limited integration of global and local contextual cues. W…

Object Detection

DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection

2026-04-03 · Siheng Wang, Yanshu Li, Bohan Hu, Zhengdao Li 외 arxiv

Open-vocabulary object detection (OVOD) enables models to recognize objects beyond predefined categories, but existing approaches remain limited in practical deployment. On the one hand, multimodal designs often incur su…

Object Detection