Semi-convolutional Operators for Instance Segmentation
Object detection and instance segmentation are dominated by region-based methods such as Mask RCNN. However, there is a growing interest in reducing these problems to pixel labeling tasks, as the latter could be more efficient, could be integrated seamlessly in image-to-image network architectures as used in many other tasks, and could be more accurate for objects that are not well approximated by bounding boxes. In this paper we show theoretically and empirically that constructing dense pixel embeddings that can separate object instances cannot be easily achieved using convolutional operators. At the same time, we show that simple modifications, which we call semi-convolutional, have a much better chance of succeeding at this task. We use the latter to show a connection to Hough voting as well as to a variant of the bilateral kernel that is spatially steered by a convolutional network. We demonstrate that these operators can also be used to improve approaches such as Mask RCNN, demonstrating better segmentation of complex biological shapes and PASCAL VOC categories than achievable by Mask RCNN alone.
Code (0)
등록된 구현이 없습니다.
Tasks
Instance Segmentationobject-detectionObject DetectionSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
ConsInstancy: Learning Instance Representations for Semi-Supervised Panoptic Segmentation of Concrete Aggregate Particles
We present a semi-supervised method for panoptic segmentation based on ConsInstancy regularisation, a novel strategy for semi-supervised learning. It leverages completely unlabelled data by enforcing consistency between …
Panoptic SegmentationSegmentationPixel Consensus Voting for Panoptic Segmentation
The core of our approach, Pixel Consensus Voting, is a framework for instance segmentation based on the Generalized Hough transform. Pixels cast discretized, probabilistic votes for the likely regions that contain instan…
Instance SegmentationPanoptic SegmentationSegmentationSemantic SegmentationSemi Supervised Deep Quick Instance Detection and Segmentation
In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally lea…
ARCClass-agnostic Object Detectionobject-detectionObject Detection+1Semiring Activation in Neural Networks
We introduce a class of trainable nonlinear operators based on semirings that are suitable for use in neural networks. These operators generalize the traditional alternation of linear operators with activation functions …
Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds
We develop a novel learning scheme named Self-Prediction for 3D instance and semantic segmentation of point clouds. Distinct from most existing methods that focus on designing convolutional operators, our method designs …
Instance SegmentationPredictionSegmentationSemantic Segmentation