Related papers: Instance Segmentation Challenge Track Technical Re…
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.…
Instance segmentation is applied widely in image editing, image analysis and autonomous driving, etc. However, insufficient data is a common problem in practical applications. The Visual Inductive Priors(VIPriors) Instance Segmentation…
The Visual Inductive Priors(VIPriors) for Data-Efficient Computer Vision challenges ask competitors to train models from scratch in a data-deficient setting. In this paper, we introduce the technical details of our submission to the…
In this paper, we introduce a data-efficient instance segmentation method we used in the 2021 VIPriors Instance Segmentation Challenge. Our solution is a modified version of Swin Transformer, based on the mmdetection which is a powerful…
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 the segmentation…
Instance segmentation is a fundamental task in computer vision with broad applications across various industries. In recent years, with the proliferation of deep learning and artificial intelligence applications, how to train effective…
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 found no scalable…
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…
Occlusion is a long-standing problem in computer vision, particularly in instance segmentation. ACM MMSports 2023 DeepSportRadar has introduced a dataset that focuses on segmenting human subjects within a basketball context and a…
Collection of massive well-annotated samples is effective in improving object detection performance but is extremely laborious and costly. Instead of data collection and annotation, the recently proposed Cut-Paste methods [12, 15] show the…
The Vision Challenge Track 1 for Data-Effificient Defect Detection requires competitors to instance segment 14 industrial inspection datasets in a data-defificient setting. This report introduces the technical details of the team…
Instance segmentation is a fundamental skill for many robotic applications. We propose a self-supervised method that uses grasp interactions to collect segmentation supervision for an instance segmentation model. When a robot grasps an…
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 approached this…
We introduce a method for simultaneously classifying, segmenting and tracking object instances in a video sequence. Our method, named MaskProp, adapts the popular Mask R-CNN to video by adding a mask propagation branch that propagates…
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature pyramid and the…
Human video instance segmentation plays an important role in computer understanding of human activities and is widely used in video processing, video surveillance, and human modeling in virtual reality. Most current VIS methods are based on…
Instance Segmentation is an interesting yet challenging task in computer vision. In this paper, we conduct a series of refinements with the Hybrid Task Cascade (HTC) Network, and empirically evaluate their impact on the final model…
Collecting and annotating images for the purpose of training segmentation models is often cost prohibitive. In the domain of wildland fire science, this challenge is further compounded by the scarcity of reliable public datasets with…
Instance segmentation is an important problem in computer vision, with applications in autonomous driving, drone navigation and robotic manipulation. However, most existing methods are not real-time, complicating their deployment in…
Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…