Feedforward semantic segmentation with zoom-out features
We introduce a purely feed-forward architecture for semantic segmentation. We map small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions of increasing extent. These regions are obtained by "zooming out" from the superpixel all the way to scene-level resolution. This approach exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Instead superpixels are classified by a feedforward multilayer network. Our architecture achieves new state of the art performance in semantic segmentation, obtaining 64.4% average accuracy on the PASCAL VOC 2012 test set.
Code (1)
Tasks
SegmentationSemantic SegmentationStructured PredictionSuperpixelsSimilar Papers 제목 키워드 기반
Learning Rich Representations For Structured Visual Prediction Tasks
We describe an approach to learning rich representations for images, that enables simple and effective predictors in a range of vision tasks involving spatially structured maps. Our key idea is to map small image element…
PredictionSegmentationSemantic SegmentationStructured Prediction+1Learning to Zoom and Unzoom
Many perception systems in mobile computing, autonomous navigation, and AR/VR face strict compute constraints that are particularly challenging for high-resolution input images. Previous works propose nonuniform downsamp…
3D Object DetectionAutonomous NavigationMonocular 3D Object DetectionObject+3Pano3D: Unified 3D Reconstruction and Panoptic Segmentation
Recent advances in 3D feedforward reconstruction neural networks have achieved remarkable success in dense reconstruction from images without any camera parameters. Yet, equipping these models with robust semantic unders…
Panoptic Segmentation3D ReconstructionZoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activat…
Object LocalizationSegmentationSemantic SegmentationWeakly-Supervised Object Localization+2Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation
In contrast to supervised backpropagation-based feature learning in deep neural networks (DNNs), an unsupervised feedforward feature (UFF) learning scheme for joint classification and segmentation of 3D point clouds is p…
ClassificationDecoderGeneral ClassificationPoint Cloud Classification+1