Dense RepPoints: Representing Visual Objects with Dense Point Sets
arXiv:1912.11473
Abstract
We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level. Techniques are proposed to efficiently process these dense points, maintaining near-constant complexity with increasing point numbers. Dense RepPoints is shown to represent and learn object segments well, with the use of a novel distance transform sampling method combined with set-to-set supervision. The distance transform sampling combines the strengths of contour and grid representations, leading to performance that surpasses counterparts based on contours or grids. Code is available at \url{https://github.com/justimyhxu/Dense-RepPoints}.
References in corpus (9)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Deformable Convolutional Networks
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Cascade R-CNN: Delving into High Quality Object Detection
- CenterNet: Keypoint Triplets for Object Detection
- PolarMask: Single Shot Instance Segmentation with Polar Representation
- SOLO: Segmenting Objects by Locations
- Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction
Cited by in corpus (8)
- Probabilistic two-stage detection
- RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
- 3D-LaneNet+: Anchor Free Lane Detection using a Semi-Local Representation
- Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation
- RPT: Learning Point Set Representation for Siamese Visual Tracking
- Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
- TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
- Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression