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

Ghiasi, Golnaz; Cui, Yin; Srinivas, Aravind; Qian, Rui; Lin, Tsung-Yi; Cubuk, Ekin D.; Le, Quoc V.; Zoph, Barret

doi:10.1109/cvpr46437.2021.00294

Cited by 745 publications

(366 citation statements)

References 41 publications

Supporting

Mentioning

362

Contrasting

Unclassified

Order By: Relevance

“…In Section 4.1, we saw that training much longer (72 epochs) reduced the gains for BoT50. One way to address this is to increase the amount of multi-scale jitter which has been known to improve the performance of detection and segmentation systems [15,18]. Table 3 shows that BoT50 is significantly better than R50 ( + 2.1% on AP bb and + 1.7% on AP mk ) for multi-scale jitter of [0.5, 2.0], while also showing significant gains ( + 2.2% on AP bb and + 1.6% on AP mk ) for scale jitter of [0.1, 2.0], suggesting that BoTNet (self-attention) benefits more from extra augmentations such as multi-scale jitter compared to ResNet (pure convolutions).…”

Section: Scale Jitter Helps Botnet More Than Resnetmentioning

confidence: 99%

Bottleneck Transformers for Visual Recognition

Srinivas¹,

Lin²,

Parmar³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing the spatial convolutions with global self-attention in the final three bottleneck blocks of a ResNet and no other changes, our approach improves upon the baselines significantly on instance segmentation and object detection while also reducing the parameters, with minimal overhead in latency. Through the design of BoTNet, we also point out how ResNet bottleneck blocks with self-attention can be viewed as Transformer blocks. Without any bells and whistles, BoTNet achieves 44.4% Mask AP and 49.7% Box AP on the COCO Instance Segmentation benchmark using the Mask R-CNN framework; surpassing the previous best published single model and single scale results of ResNeSt [72] evaluated on the COCO validation set. Finally, we present a simple adaptation of the BoTNet design for image classification, resulting in models that achieve a strong performance of 84.7% top-1 accuracy on the ImageNet benchmark while being up to 2.33x faster in "compute" 1 time than the popular EfficientNet models on TPU-v3 hardware. We hope our simple and effective approach will serve as a strong baseline for future research in self-attention models for vision. 2

show abstract

Section: Scale Jitter Helps Botnet More Than Resnetmentioning

confidence: 99%

Bottleneck Transformers for Visual Recognition

Srinivas¹,

Lin²,

Parmar³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, to improve the identification effect of psyllids, the first step is to increase the sample number of citrus psyllids in the picture. For this kind of small target, there are many ways to enhance the small target, such as component stitching ( Chen Y. et al, 2020 ), artificial augmentation by copy-pasting the small objects ( Kisantal et al, 2019 ), AdaResampling ( Ghiasi et al, 2020 ), and scale match ( Yu et al, 2020 ). Due to the randomness of the target distribution, the number of targets distributed in each image is inconsistent.…”

Section: Methodsmentioning

confidence: 99%

Detection Method of Citrus Psyllids With Field High-Definition Camera Based on Improved Cascade Region-Based Convolution Neural Networks

et al. 2022

View full text Add to dashboard Cite

Citrus psyllid is the only insect vector of citrus Huanglongbing (HLB), which is the most destructive disease in the citrus industry. There is no effective treatment for HLB, so detecting citrus psyllids as soon as possible is the key prevention measure for citrus HLB. It is time-consuming and laborious to search for citrus psyllids through artificial patrol, which is inconvenient for the management of citrus orchards. With the development of artificial intelligence technology, a computer vision method instead of the artificial patrol can be adopted for orchard management to reduce the cost and time. The citrus psyllid is small in shape and gray in color, similar to the stem, stump, and withered part of the leaves, leading to difficulty for the traditional target detection algorithm to achieve a good recognition effect. In this work, in order to make the model have good generalization ability under outdoor light condition, a high-definition camera to collect data set of citrus psyllids and citrus fruit flies under natural light condition was used, a method to increase the number of small target pests in citrus based on semantic segmentation algorithm was proposed, and the cascade region-based convolution neural networks (R-CNN) (convolutional neural network) algorithm was improved to enhance the recognition effect of small target pests using multiscale training, combining CBAM attention mechanism with high-resolution feature retention network high-resoultion network (HRNet) as feature extraction network, adding sawtooth atrous spatial pyramid pooling (ASPP) structure to fully extract high-resolution features from different scales, and adding feature pyramid networks (FPN) structure for feature fusion at different scales. To mine difficult samples more deeply, an online hard sample mining strategy was adopted in the process of model sampling. The results show that the improved cascade R-CNN algorithm after training has an average recognition accuracy of 88.78% for citrus psyllids. Compared with VGG16, ResNet50, and other common networks, the improved small target recognition algorithm obtains the highest recognition performance. Experimental results also show that the improved cascade R-CNN algorithm not only performs well in citrus psylla identification but also in other small targets such as citrus fruit flies, which makes it possible and feasible to detect small target pests with a field high-definition camera.

show abstract

“…Another class of extensions of MIXUP which has been growing in the vision community attempts to fuse raw input image pairs together into a single input image, rather than improve the continuous interpolation mechanism. Examples of this paradigm include CUTMIX (Yun et al, 2019), CUTOUT (De-Vries and Taylor, 2017) and COPY-PASTE (Ghiasi et al, 2020). For instance, CUTMIX replaces a small sub-region of Image A with a patch sampled from Image B, with the labels mixed in proportion to sub-region sizes.…”

Section: Example Interpolation Techniquesmentioning

confidence: 99%

A Survey of Data Augmentation Approaches for NLP

Feng

Gangal

Wei

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

295

View full text Add to dashboard Cite

Data augmentation has recently seen increased interest in NLP due to more work in lowresource domains, new tasks, and the popularity of large-scale neural networks that require large amounts of training data. Despite this recent upsurge, this area is still relatively underexplored, perhaps due to the challenges posed by the discrete nature of language data. In this paper, we present a comprehensive and unifying survey of data augmentation for NLP by summarizing the literature in a structured manner. We first introduce and motivate data augmentation for NLP, and then discuss major methodologically representative approaches. Next, we highlight techniques that are used for popular NLP applications and tasks. We conclude by outlining current challenges and directions for future research. Overall, our paper aims to clarify the landscape of existing literature in data augmentation for NLP and motivate additional work in this area. We also present a GitHub repository with a paper list that will be continuously updated at https://github.com/styfeng/DataAug4NLP.

show abstract

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

Cited by 745 publications

References 41 publications

Bottleneck Transformers for Visual Recognition

Bottleneck Transformers for Visual Recognition

Detection Method of Citrus Psyllids With Field High-Definition Camera Based on Improved Cascade Region-Based Convolution Neural Networks

A Survey of Data Augmentation Approaches for NLP

Contact Info

Product

Resources

About