홈 › Papers

Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

2020-12-13 · CVPR 2021 1 · Golnaz Ghiasi, Yin Cui, Aravind Srinivas, Rui Qian, Tsung-Yi Lin, Ekin D. Cubuk, Quoc V. Le, Barret Zoph

Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge. Here, we perform a systematic study of the Copy-Paste augmentation ([13, 12]) for instance segmentation where we randomly paste objects onto an image. Prior studies on Copy-Paste relied on modeling the surrounding visual context for pasting the objects. However, we find that the simple mechanism of pasting objects randomly is good enough and can provide solid gains on top of strong baselines. Furthermore, we show Copy-Paste is additive with semi-supervised methods that leverage extra data through pseudo labeling (e.g. self-training). On COCO instance segmentation, we achieve 49.1 mask AP and 57.3 box AP, an improvement of +0.6 mask AP and +1.5 box AP over the previous state-of-the-art. We further demonstrate that Copy-Paste can lead to significant improvements on the LVIS benchmark. Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3.6 mask AP on rare categories.

📄 PDF Abstract BibTeX arXiv:2012.07177

Code (5)

tensorflow/tpu/tree/master/models/official/detection/projects/copy_paste 공식 구현 tf

PaddlePaddle/PaddleOCR paddle

RocketFlash/CAP_augmentation

conradry/copy-paste-aug pytorch

open-mmlab/mmdetection pytorch

Tasks

Data Augmentation Image Augmentation Instance Segmentation Object Detection Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…

Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …

Entropy Regularization 설명 없음

Sigmoid Activation 설명 없음

PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Residual Connection 설명 없음

X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion

2022-12-07 · Hanqing Zhao, Dianmo Sheng, Jianmin Bao, Dongdong Chen 외

Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training data for free and significantly boosts t…

Data Augmentation Instance Segmentation Object Object Detection+4

Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation

2022-10-07 · Evan Ling, Dezhao Huang, Minhoe Hur

Modern object detection and instance segmentation networks stumble when picking out humans in crowded or highly occluded scenes. Yet, these are often scenarios where we require our detectors to work well. Many works have…

Human Instance Segmentation Instance Segmentation object-detection Object Detection+2

SDI-Paste: Synthetic Dynamic Instance Copy-Paste for Video Instance Segmentation

2024-10-16 · Sahir Shrestha, Weihao Li, Gao Zhu, Nick Barnes

Data augmentation methods such as Copy-Paste have been studied as effective ways to expand training datasets while incurring minimal costs. While such methods have been extensively implemented for image level tasks, we f…

Data Augmentation Instance Segmentation MORPH Semantic Segmentation+1

TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation

2021-07-21 · Jiawei Yang, Yao Zhang, Yuan Liang, Yang Zhang 외

Deep learning models are notoriously data-hungry. Thus, there is an urging need for data-efficient techniques in medical image analysis, where well-annotated data are costly and time consuming to collect. Motivated by th…

Data Augmentation Medical Image Analysis Tumor Segmentation

CopyPaste: An Augmentation Method for Speech Emotion Recognition

2020-10-27 · Raghavendra Pappagari, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velazquez 외

Data augmentation is a widely used strategy for training robust machine learning models. It partially alleviates the problem of limited data for tasks like speech emotion recognition (SER), where collecting data is expen…

Data Augmentation Emotion Recognition Speaker Recognition Speech Emotion Recognition+1