RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features

@article{Zhang2021RefineMaskTH,
  title={RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features},
  author={Gang Zhang and Xin Lu and Jingru Tan and Jianmin Li and Zhaoxiang Zhang and Quanquan Li and Xiaolin Hu},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={6857-6865}
}
  • Gang ZhangXin Lu Xiaolin Hu
  • Published 17 April 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature pyramid and the instance-wise pooling process, especially for large objects. In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process… 
[PDF] Semantic Reader
32 Citations
Highly Influential Citations
2
Background Citations
10
Methods Citations
14
Results Citations
2

32 Citations

Mask Transfiner for High-Quality Instance Segmentation

This paper presents Mask Transfiner, a transformer-based approach to instance segmentation that decomposes and represents the image regions as a quadtree, allowing it to predict highly accurate instance masks, at a low computational cost.

Combine Supervised Edge and Semantic Supplement for Instance Segmentation

It is concluded that the detailed feature information is essential for precise segmentation, and the idea is available for other segmentation tasks.

Partial Atrous Cascade R-CNN

A novel instance segmentation framework named partial atrous cascade R-CNN (PAC), which effectively improves the accuracy of the segmentation boundary by expanding the receptive field of the convolutional layer, multi-scale semantic features are greatly enriched.

Box-supervised Instance Segmentation with Level Set Evolution

A novel single-shot box-supervised instance segmentation approach, which integrates the classical level set model with deep neural network delicately, and iteratively learns a series of level sets through a continuous Chan-Vese energy-based function in an end-to-end fashion.

Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution

This paper presents a novel single-shot instance segmentation approach, namely Box2Mask, which integrates the classical level-set evolution model into deep neural network learning to achieve accurate mask prediction with only bounding box supervision.

Deep Level Set for Box-supervised Instance Segmentation in Aerial Images

This work proposes a novel aerial instance segmentation approach, which drives the network to learn a series of level set functions for the aerial objects with only box annotations in an end-to-end fashion, and demonstrates that the proposed approach outperforms the state-of-the-art box-supervised instances segmentation methods.

Improving Image Segmentation with Boundary Patch Refinement

This work proposes a conceptually simple yet effective post-processing refinement framework, termed BPR, to improve the boundary quality of the prediction of any image segmentation model and extracts and refine a series of small boundary patches along the predicted boundaries.

Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?

This paper constructs a framework for semi-supervised instance segmentation by assigning pixel-level pseudo labels, and proposes a noise-tolerant mask head by leveraging low-resolution features to combat the negative effects of noisy boundaries and enhance the positive impacts.

SGDANet: Gland Instance Segmentation Based on Spatial and Geometric Dual-Path Attention Modules

SGDANet is proposed, a novel and effective geometric module for better capturing geometric features of the cell membrane, cytoplasm and nucleus and designs a parallel spatial-geometric dual-path attention mechanism for better feature extraction.

Active Pointly-Supervised Instance Segmentation

An economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object, which suggests that APIS, inte-grating the advantages of active learning and point-based supervision, is an effective learning paradigm for label-efficient instance segmentsation.

References

SHOWING 1-10 OF 30 REFERENCES

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

The proposed 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, thus being fast in inference.

Conditional Convolutions for Instance Segmentation

A simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed on the COCO dataset, and outperform a few recent methods including well-tuned Mask RCNN baselines, without longer training schedules needed.

Learning to Refine Object Segments

This work proposes to augment feedforward nets for object segmentation with a novel top-down refinement approach that is capable of efficiently generating high-fidelity object masks and is 50 % faster than the original DeepMask network.

SOLO: Segmenting Objects by Locations

A new, embarrassingly simple approach to instance segmentation in images by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location and size thus nicely converting instance mask segmentation into a classification-solvable problem.

Hybrid Task Cascade for Instance Segmentation

This work proposes a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background.

Boundary-preserving Mask R-CNN

A conceptually simple yet effective Boundary-preserving Mask R-CNN (BMask R- CNN) to leverage object boundary information to improve mask localization accuracy in instance segmentation.

Panoptic Feature Pyramid Networks

This work endsow Mask R-CNN, a popular instance segmentation method, with a semantic segmentation branch using a shared Feature Pyramid Network (FPN) backbone, and shows it is a robust and accurate baseline for both tasks.

LVIS: A Dataset for Large Vocabulary Instance Segmentation

This work introduces LVIS (pronounced ‘el-vis’): a new dataset for Large Vocabulary Instance Segmentation, which has a long tail of categories with few training samples due to the Zipfian distribution of categories in natural images.

Boundary-Aware Instance Segmentation

This paper introduces a novel object segment representation based on the distance transform of the object masks, and designs an object mask network (OMN) with a new residual-deconvolution architecture that infers such a representation and decodes it into the final binary object mask.

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade

A novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation and is an end-to-end trainable framework, allowing joint learning of all sub-models.