Paper Reading AI Learner

Detecting Reflections by Combining Semantic and Instance Segmentation

2019-04-30 14:25:43
David Owen, Ping-Lin Chang

Abstract

Reflections in natural images commonly cause false positives in automated detection systems. These false positives can lead to significant impairment of accuracy in the tasks of detection, counting and segmentation. Here, inspired by the recent panoptic approach to segmentation, we show how fusing instance and semantic segmentation can automatically identify reflection false positives, without explicitly needing to have the reflective regions labelled. We explore in detail how state of the art two-stage detectors suffer a loss of broader contextual features, and hence are unable to learn to ignore these reflections. We then present an approach to fuse instance and semantic segmentations for this application, and subsequently show how this reduces false positive detections in a real world surveillance data with a large number of reflective surfaces. This demonstrates how panoptic segmentation and related work, despite being in its infancy, can already be useful in real world computer vision problems.

Abstract (translated)

自然图像中的反射通常会在自动检测系统中导致误报。这些假阳性可能导致检测、计数和分割任务的准确性受到严重损害。在这里,受近来全光分割方法的启发,我们展示了融合实例和语义分割如何自动识别反射误报,而无需明确标记反射区域。我们详细探讨了最先进的两级探测器如何丢失更广泛的上下文特征,因此无法学会忽略这些反射。然后,我们为这个应用程序提供了一种融合实例和语义分段的方法,并随后展示了如何减少具有大量反射面的真实监视数据中的假阳性检测。这说明了泛光分割和相关的工作,尽管在其幼年阶段,可以在现实世界中的计算机视觉问题有用。

URL

https://arxiv.org/abs/1904.13273

PDF

https://arxiv.org/pdf/1904.13273.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot