Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation
Despite remarkable progress, weakly supervised segmentation methods are still inferior to their fully supervised counterparts. We obverse that the performance gap mainly comes from the inability of producing dense and integral pixel-level object localization for training images only with image-level labels. In this work, we revisit the dilated convolution proposed in [1] and shed light on how it enables the classification network to generate dense object localization. By substantially enlarging the receptive fields of convolutional kernels with different dilation rates, the classification network can localize the object regions even when they are not so discriminative for classification and finally produce reliable object regions for benefiting both weakly- and semi- supervised semantic segmentation. Despite the apparent simplicity of dilated convolution, we are able to obtain superior performance for semantic segmentation tasks. In particular, it achieves 60.8% and 67.6% mean Intersection-over-Union (mIoU) on Pascal VOC 2012 test set in weakly- (only image-level labels are available) and semi- (1,464 segmentation masks are available) settings, which are the new state-of-the-arts.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationObjectObject LocalizationSegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationWeakly supervised segmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produ…
ObjectObject LocalizationSegmentationSemantic Segmentation+2Epileptic Seizure Prediction: A Semi-Dilated Convolutional Neural Network Architecture
Accurate prediction of epileptic seizures has remained elusive, despite the many advances in machine learning and time-series classification. In this work, we develop a convolutional network module that exploits Electroe…
EEGElectroencephalogram (EEG)Seizure predictionTime Series+23D human pose estimation in video with temporal convolutions and semi-supervised training
In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and …
3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationPosition+1Revisiting Embedding Features for Simple Semi-supervised Learning
Smoothed Dilated Convolutions for Improved Dense Prediction
Dilated convolutions, also known as atrous convolutions, have been widely explored in deep convolutional neural networks (DCNNs) for various dense prediction tasks. However, dilated convolutions suffer from the gridding …
Audio GenerationMachine TranslationObject DetectionPrediction+1