Conditional Convolutions for Instance Segmentation

• URL: http://arxiv.org/abs/2003.05664v4
• Date: Sun, 26 Jul 2020 02:18:32 GMT
• Title: Conditional Convolutions for Instance Segmentation
• Authors: Zhi Tian and Chunhua Shen and Hao Chen
• Abstract summary: We propose a simple yet effective instance segmentation framework, termed CondInst. We employ dynamic instance-aware networks, conditioned on instances. We demonstrate a simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed.
• Score: 109.2706837177222
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation). Top-performing instance segmentation methods such as Mask R-CNN rely on ROI operations (typically ROIPool or ROIAlign) to obtain the final instance masks. In contrast, we propose to solve instance segmentation from a new perspective. Instead of using instance-wise ROIs as inputs to a network of fixed weights, we employ dynamic instance-aware networks, conditioned on instances. CondInst enjoys two advantages: 1) Instance segmentation is solved by a fully convolutional network, eliminating the need for ROI cropping and feature alignment. 2) Due to the much improved capacity of dynamically-generated conditional convolutions, the mask head can be very compact (e.g., 3 conv. layers, each having only 8 channels), leading to significantly faster inference. We demonstrate a simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed. On the COCO dataset, we outperform a few recent methods including well-tuned Mask RCNN baselines, without longer training schedules needed. Code is available: https://github.com/aim-uofa/adet

Related papers

• Implicit Feature Refinement for Instance Segmentation [20.34804959340334]
  We propose a novel implicit feature refinement module for high-quality instance segmentation. Our IFR achieves improved performance on state-of-the-art image/video instance segmentation frameworks.
  arXiv  Detail & Related papers  (2021-12-09T05:36:04Z)
• SOLO: A Simple Framework for Instance Segmentation [84.00519148562606]
  "instance categories" assigns categories to each pixel within an instance according to the instance's location. "SOLO" is a simple, direct, and fast framework for instance segmentation with strong performance. Our approach achieves state-of-the-art results for instance segmentation in terms of both speed and accuracy.
  arXiv  Detail & Related papers  (2021-06-30T09:56:54Z)
• Instance and Panoptic Segmentation Using Conditional Convolutions [96.7275593916409]
  We propose a simple yet effective framework for instance and panoptic segmentation, termed CondInst. We show that CondInst can achieve improved accuracy and inference speed on both instance and panoptic segmentation tasks.
  arXiv  Detail & Related papers  (2021-02-05T06:57:02Z)
• Unifying Instance and Panoptic Segmentation with Dynamic Rank-1 Convolutions [109.2706837177222]
  DR1Mask is the first panoptic segmentation framework that exploits a shared feature map for both instance and semantic segmentation. As a byproduct, DR1Mask is 10% faster and 1 point in mAP more accurate than previous state-of-the-art instance segmentation network BlendMask.
  arXiv  Detail & Related papers  (2020-11-19T12:42:10Z)
• PointINS: Point-based Instance Segmentation [117.38579097923052]
  Mask representation in instance segmentation with Point-of-Interest (PoI) features is challenging because learning a high-dimensional mask feature for each instance requires a heavy computing burden. We propose an instance-aware convolution, which decomposes this mask representation learning task into two tractable modules. Along with instance-aware convolution, we propose PointINS, a simple and practical instance segmentation approach.
  arXiv  Detail & Related papers  (2020-03-13T08:24:58Z)
• BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation [103.74690082121079]
  In this work, we achieve improved mask prediction by effectively combining instance-level information with semantic information with lower-level fine-granularity. Our main contribution is a blender module which draws inspiration from both top-down and bottom-up instance segmentation approaches. BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer.
  arXiv  Detail & Related papers  (2020-01-02T03:30:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.