InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

@article{Fang2019InstaBoostBI,
  title={InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting},
  author={Haoshu Fang and Jianhua Sun and Runzhong Wang and Minghao Gou and Yong-Lu Li and Cewu Lu},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={682-691}
}
Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated using data annotation from other domain (e.g. bbox, point) in a weakly supervised mechanism. In this paper, we present a simple, efficient and effective method to augment the training set using the existing instance mask annotations. Exploiting the pixel… Expand
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
TLDR
A fast single-stage instance segmentation method that preserves instance-specific spatial information by separating mask prediction of an instance to different sub-regions of a detected bounding-box, leading to improved mask predictions and a mask alignment weighting loss and a feature alignment scheme to better correlate mask prediction with object detection. Expand
Learning Object Placement by Inpainting for Compositional Data Augmentation
TLDR
This work proposes a self-learning framework that automatically generates the necessary training data without any manual labeling by detecting, cutting, and inpainting objects from an image by proposing a PlaceNet that predicts a diverse distribution of common sense locations when given a foreground object and a background scene. Expand
RandAugment: Practical data augmentation with no separate search
TLDR
RandAugment can be used uniformly across different tasks and datasets and works out of the box, matching or surpassing all previous learned augmentation approaches on CIFAR-10, CIFar-100, SVHN, and ImageNet. Expand
Scale-aware Automatic Augmentation for Object Detection
TLDR
Scale-aware AutoAug is proposed to learn data augmentation policies for object detection, where both image and box-level augmentations are designed for maintaining scale invariance, and a new search metric is proposed, termed Pareto Scale Balance, to facilitate search with high efficiency. Expand
A novel data augmentation scheme for pedestrian detection with attribute preserving GAN
TLDR
An efficient data augmentation scheme by transferring pedestrians from other datasets into the target scene with a novel Attribute Preserving Generative Adversarial Networks (APGAN), which pursues both good visual quality and attribute preserving after style transfer. Expand
TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
TLDR
TumorCP, a simple but effective object-level data augmentation method tailored for tumor segmentation, is proposed, motivated by the recently revived “Copy-Paste” augmentation, providing unlimited augmentation possibilities for tumors’ subjects, locations, appearances, as well as morphologies. Expand
Does Data Augmentation Benefit from Split BatchNorms
TLDR
A recently proposed training paradigm is explored using an auxiliary BatchNorm for the potentially out-of-distribution, strongly augmented images, and this method significantly improves the performance of common image classification benchmarks such as CIFar-10, CIFAR-100, and ImageNet. Expand
Randaugment: Practical automated data augmentation with a reduced search space
TLDR
This work proposes a simplified search space that vastly reduces the computational expense of automated augmentation, and permits the removal of a separate proxy task. Expand
Accurate Scene Text Detection via Scale-Aware Data Augmentation and Shape Similarity Constraint
TLDR
An arbitrary-shape scene text detection method that can achieve better generalization ability and more accurate localization, and a Scale-Aware Data Augmentation technique to increase the diversity of training samples is proposed. Expand
Accurate Scene Text Detection via Scale-Aware Data Augmentation and Shape Similarity Constraint
Scene text detection has attracted increasing concerns with the rapid development of deep neural networks in recent years. However, existing scene text detectors may overfit on the public datasetsExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
TLDR
This paper proposes a method that achieves competitive accuracy but only requires easily obtained bounding box annotations, and yields state-of-the-art results on PASCAL VOC 2012 and PASCal-CONTEXT. Expand
SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain Adaptation
TLDR
This work introduces a novel pipeline named SRDA, which can achieve decent instance segmentation performance given very low human labor cost and is well-suited to scenes that can be scanned, i.e. most indoor and some outdoor scenarios. Expand
Instance-Sensitive Fully Convolutional Networks
TLDR
This paper develops FCNs that are capable of proposing instance-level segment candidates that do not have any high-dimensional layer related to the mask resolution, but instead exploits image local coherence for estimating instances. Expand
Instance-Aware Semantic Segmentation via Multi-task Network Cascades
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This paper presents Multitask Network Cascades for instance-aware semantic segmentation, which consists of three networks, respectively differentiating instances, estimating masks, and categorizing objects, and develops an algorithm for the nontrivial end-to-end training of this causal, cascaded structure. Expand
Modeling Visual Context is Key to Augmenting Object Detection Datasets
TLDR
This work leverages segmentation annotations to increase the number of object instances present on training data and shows that modeling appropriately the visual context surrounding objects is crucial to place them in the right environment. Expand
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
TLDR
This paper proposes a simple approach to generate large annotated instance datasets with minimal effort and outperforms existing synthesis approaches and when combined with real images improves relative performance by more than 21% on benchmark datasets. Expand
MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
TLDR
This work presents a model, called MaskLab, which produces three outputs: box detection, semantic segmentation, and direction prediction, which is evaluated on the COCO instance segmentation benchmark and shows comparable performance with other state-of-art models. Expand
Learning Segmentation Masks with the Independence Prior
TLDR
Results are appealing in both tasks, which shows the independence prior is useful for instance segmentation and it is possible to unsupervisedly learn instance masks with only one image of homogeneous object cluster (HOC). Expand
Learning to Segment Object Candidates
TLDR
A new way to generate object proposals is proposed, introducing an approach based on a discriminative convolutional network that obtains substantially higher object recall using fewer proposals and is able to generalize to unseen categories it has not seen during training. Expand
What's the Point: Semantic Segmentation with Point Supervision
TLDR
This work takes a natural step from image-level annotation towards stronger supervision: it asks annotators to point to an object if one exists, and incorporates this point supervision along with a novel objectness potential in the training loss function of a CNN model. Expand
...
1
2
3
4
5
...