paper-with-me

홈 › Papers

Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR

2023-03-13 · Feng Li, Ailing Zeng, Shilong Liu, Hao Zhang, Hongyang Li, Lei Zhang, Lionel M. Ni

Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively increased tokens in multi-scale features, especially for about 75\% of low-level features, are quite computationally inefficient, which hinders real applications of DETR models. In this paper, we present Lite DETR, a simple yet efficient end-to-end object detection framework that can effectively reduce the GFLOPs of the detection head by 60\% while keeping 99\% of the original performance. Specifically, we design an efficient encoder block to update high-level features (corresponding to small-resolution feature maps) and low-level features (corresponding to large-resolution feature maps) in an interleaved way. In addition, to better fuse cross-scale features, we develop a key-aware deformable attention to predict more reliable attention weights. Comprehensive experiments validate the effectiveness and efficiency of the proposed Lite DETR, and the efficient encoder strategy can generalize well across existing DETR-based models. The code will be available in \url{https://github.com/IDEA-Research/Lite-DETR}.

📄 PDF Abstract BibTeX arXiv:2303.07335

Code (1)

idea-research/lite-detr 공식 구현 pytorch

Tasks

object-detectionObject Detection

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
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…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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…

Similar Papers 제목 키워드 기반

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

2023-01-01 · CVPR 2023 1 · Feng Li, Ailing Zeng, Shilong Liu, Hao Zhang 외

Recent DEtection TRansformer-based (DETR) models have obtained remarkable performance. Its success cannot be achieved without the re-introduction of multi-scale feature fusion in the encoder. However, the excessively…

object-detectionObject Detection

LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection

2024-06-05 · Qiang Chen, Xiangbo Su, Xinyu Zhang, Jian Wang 외

In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decode…

Decoderobject-detectionObject DetectionReal-Time Object Detection

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 ModelingLanguage Modellingobject-detectionObject Detection+2

Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity

2021-11-29 · ICLR 2022 4 · Byungseok Roh, Jaewoong Shin, Wuhyun Shin, Saehoon Kim

DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work…

Computational EfficiencyDecoderobject-detectionObject Detection

Cross Resolution Encoding-Decoding For Detection Transformers

2024-10-05 · Ashish Kumar, Jaesik Park

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decodin…

object-detectionObject Detection