paper-with-me

홈 › Papers

Rethinking Transformer-based Set Prediction for Object Detection

2020-11-21 · ICCV 2021 10 · Zhiqing Sun, Shengcao Cao, Yiming Yang, Kris Kitani

DETR is a recently proposed Transformer-based method which views object detection as a set prediction problem and achieves state-of-the-art performance but demands extra-long training time to converge. In this paper, we investigate the causes of the optimization difficulty in the training of DETR. Our examinations reveal several factors contributing to the slow convergence of DETR, primarily the issues with the Hungarian loss and the Transformer cross-attention mechanism. To overcome these issues we propose two solutions, namely, TSP-FCOS (Transformer-based Set Prediction with FCOS) and TSP-RCNN (Transformer-based Set Prediction with RCNN). Experimental results show that the proposed methods not only converge much faster than the original DETR, but also significantly outperform DETR and other baselines in terms of detection accuracy.

📄 PDF Abstract BibTeX arXiv:2011.10881

Code (1)

edward-sun/tsp-detection 공식 구현 pytorch

Tasks

Objectobject-detectionObject DetectionPrediction

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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…
Detr 설명 없음

Similar Papers 제목 키워드 기반

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

2021-06-01 · NeurIPS 2021 12 · Yuxin Fang, Bencheng Liao, Xinggang Wang, Jiemin Fang 외

Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure? To answer this question, we present You Only Look at One…

Objectobject-detectionObject Detection

Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer

2021-06-07 · Zilong Huang, Youcheng Ben, Guozhong Luo, Pei Cheng 외

Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, …

image-classificationImage Classificationobject-detectionObject Detection+2

FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers

2025-10-17 · Haisheng Su, Junjie Zhang, Feixiang Song, Sanping Zhou 외 arxiv

Detecting 3D objects accurately from multi-view 2D images is a challenging yet essential task in the field of autonomous driving. Current methods resort to integrating depth prediction to recover the spatial information …

3D Object DetectionAutonomous Driving

Embracing Single Stride 3D Object Detector with Sparse Transformer

2021-12-13 · CVPR 2022 1 · Lue Fan, Ziqi Pang, Tianyuan Zhang, Yu-Xiong Wang 외

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly…

3D Object DetectionAutonomous DrivingObjectobject-detection+2

GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem

2026-06-28 · Rui-Xi Wang, Runzhong Wang, Connor W. Coley arxiv

Predicting tandem mass spectra (MS/MS) from molecular structures represents a central task in analytical chemistry with direct relevance to clinical metabolomics, systems biology, and adjacent disciplines. In this work, …

Object Detection