Hypercolumns for Object Segmentation and Fine-grained Localization
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation. However, the information in this layer may be too coarse to allow precise localization. On the contrary, earlier layers may be precise in localization but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hypercolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation[22], where we improve state-of-the-art from 49.7[22] mean AP^r to 60.0, keypoint localization, where we get a 3.3 point boost over[20] and part labeling, where we show a 6.6 point gain over a strong baseline.
Code (6)
Tasks
ObjectSemantic SegmentationSimilar Papers 제목 키워드 기반
Ensemble Learning with Sparse Hypercolumns
Directly inspired by findings in biological vision, high-dimensional hypercolumns are feature vectors built by concatenating multi-scale activations of convolutional neural networks for a single image pixel location. Tog…
Image SegmentationEnsemble LearningSegmentation of Instances by Hashing
We propose a novel approach to address the Simultaneous Detection and Segmentation problem. Using hierarchical structures we use an efficient and accurate procedure that exploits the hierarchy feature information using L…
SegmentationFashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-grained visual attribute categorization (recog…
AttributeFine-Grained Visual CategorizationFine-Grained Visual RecognitionInstance Segmentation+3Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
Long-term visual localization is the problem of estimating the camera pose of a given query image in a scene whose appearance changes over time. It is an important problem in practice, for example, encountered in autonom…
Autonomous DrivingSegmentationVisual LocalizationFine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization
Long-term visual localization is the problem of estimating the camera pose of a given query image in a scene whose appearance changes over time. It is an important problem in practice that is, for example, encountered in…
Autonomous DrivingSegmentationVisual Localization