paper-with-me

홈 › Papers

Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

2022-06-22 · Ming Li, Jie Wu, Jinhang Cai, Jie Qin, Yuxi Ren, Xuefeng Xiao, Min Zheng, Rui Wang, Xin Pan

Recently, Synthetic data-based Instance Segmentation has become an exceedingly favorable optimization paradigm since it leverages simulation rendering and physics to generate high-quality image-annotation pairs. In this paper, we propose a Parallel Pre-trained Transformers (PPT) framework to accomplish the synthetic data-based Instance Segmentation task. Specifically, we leverage the off-the-shelf pre-trained vision Transformers to alleviate the gap between natural and synthetic data, which helps to provide good generalization in the downstream synthetic data scene with few samples. Swin-B-based CBNet V2, SwinL-based CBNet V2 and Swin-L-based Uniformer are employed for parallel feature learning, and the results of these three models are fused by pixel-level Non-maximum Suppression (NMS) algorithm to obtain more robust results. The experimental results reveal that PPT ranks first in the CVPR2022 AVA Accessibility Vision and Autonomy Challenge, with a 65.155% mAP.

📄 PDF Abstract BibTeX arXiv:2206.10845

Code (0)

등록된 구현이 없습니다.

Tasks

Instance SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

CBNet CBNet is a backbone architecture that consists of multiple identical backbones (specially called Assistant Backbones and Lead Backbone) and composite connections between…

Similar Papers 제목 키워드 기반

Pre-training Vision Transformers with Very Limited Synthesized Images

2023-07-27 · ICCV 2023 1 · Ryo Nakamura, Hirokatsu Kataoka, Sora Takashima, Edgar Josafat Martinez Noriega 외

Formula-driven supervised learning (FDSL) is a pre-training method that relies on synthetic images generated from mathematical formulae such as fractals. Prior work on FDSL has shown that pre-training vision transformers…

Data Augmentation

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

2021-03-22 · Lucas Stoffl, Maxime Vidal, Alexander Mathis

We propose a new end-to-end trainable approach for multi-instance pose estimation by combining a convolutional neural network with a transformer. We cast multi-instance pose estimation from images as a direct set predict…

DecoderKeypoint Detectionobject-detectionObject Detection+1

Learning Spectral Methods by Transformers

2025-01-02 · Yihan He, Yuan Cao, Hong-Yu Chen, Dennis Wu 외

Transformers demonstrate significant advantages as the building block of modern LLMs. In this work, we study the capacities of Transformers in performing unsupervised learning. We show that multi-layered Transformers, gi…

In-Context Learning

A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task

2024-02-19 · Jannik Brinkmann, Abhay Sheshadri, Victor Levoso, Paul Swoboda 외

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated …

End-to-End Video Instance Segmentation with Transformers

2020-11-30 · CVPR 2021 1 · Yuqing Wang, Zhaoliang Xu, Xinlong Wang, Chunhua Shen 외

Video instance segmentation (VIS) is the task that requires simultaneously classifying, segmenting and tracking object instances of interest in video. Recent methods typically develop sophisticated pipelines to tackle th…

Instance SegmentationSegmentationSemantic SegmentationVideo Instance Segmentation+1