Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

Tang, Chufeng; Chen, Hang; Xiao, Li; Li, Jianmin; Zhang, Zhaoxiang; Hu, Xiaolin

doi:10.48550/arxiv.2104.05239

Cited by 2 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detection of objects in natural scenes can be hindered by their wide range of scales, and many methods use multi-scale feature fusions, such as feature pyramids [41], and multi-level prediction to improve detection for objects of varying sizes. However, the use of multi-level pyramidal features can result in increased computational load, particularly for detectors that use heavy heads [42], [43]. Additionally, this approach may produce duplicate predictions.…”

Section: ) Instance Context Encodermentioning

confidence: 99%

“…On the other hand, a novel method for faster inference utilizes single-level prediction by reconstructing the feature pyramid networks and incorporating an instance context encoder, as depicted in Fig. 5 [43]. To overcome the limitations of single-level features for objects of varying scales, the instance context encoder adopts a pyramid pooling module [44] after C5 (Convolution) to increase the receptive fields.…”

Section: ) Instance Context Encodermentioning

confidence: 99%

See 1 more Smart Citation

MonoIS3DLoc: Simulation to Reality Learning Based Monocular Instance Segmentation to 3D Objects Localization From Aerial View

Tran

Nguyen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

3D object detection and localization based on only a monocular camera always faces its fundamental ill-posed issue to estimate 3D information. In combination with deep neural networks, recent researches have shown encouraging results to tackle this issue. However, most of them are only applied to street-view cameras based on several available small-size datasets and the 3D prediction accuracy of these methods is still low in comparison to traditional estimation methods using stereo-cameras. With the development of drone delivery applications in city spaces, it is also necessary to have a similar method to detect objects and estimate their 3D position from an aerial view. We proposed a novel Simulation to Reality approach to predict the object's 3D position from an aerial view. An instance segmentation of an object is used as an intermediate representation not only to create a very large dataset for training by simulation but also to minimize the gap between simulation and reality. We designed a feed-forward neural network to predict the 3D position from instance segmentation and integrated it with a range-attention classification to improve accuracy, especially for 3D object detection at far distances. To evaluate our methods, we created two simulation datasets: one for cross-validation with other state-of-the-art methods and the other one for practical experiments on a real drone with a monocular camera. The experiment's results demonstrate that we not only achieve better accuracy than the state-of-the-art methods using the monocular camera by testing on the same KITTI-3D dataset but also reach close to the accuracy of a stereo-based technique. Since our model is lightweight, we successfully deployed it on a companion computer on the real drone and the results of practical experiences are promising.

show abstract

Section: ) Instance Context Encodermentioning

confidence: 99%

Section: ) Instance Context Encodermentioning

confidence: 99%

MonoIS3DLoc: Simulation to Reality Learning Based Monocular Instance Segmentation to 3D Objects Localization From Aerial View

Tran

Nguyen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

Mask Transfiner for High-Quality Instance Segmentation

Ke¹,

Danelljan²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Two-stage and query-based instance segmentation methods have achieved remarkable results. However, their segmented masks are still very coarse. In this paper, we present Mask Transfiner for high-quality and efficient instance segmentation. Instead of operating on regular dense tensors, our Mask Transfiner decomposes and represents the image regions as a quadtree. Our transformer-based approach only processes detected error-prone tree nodes and selfcorrects their errors in parallel. While these sparse pixels only constitute a small proportion of the total number, they are critical to the final mask quality. This allows Mask Transfiner to predict highly accurate instance masks, at a low computational cost. Extensive experiments demonstrate that Mask Transfiner outperforms current instance segmentation methods on three popular benchmarks, significantly improving both two-stage and query-based frameworks by a large margin of +3.0 mask AP on COCO and BDD100K, and +6.6 boundary AP on Cityscapes. Our code and trained models will be available at http://vis. xyz/pub/transfiner.

show abstract

Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

Cited by 2 publications

References 42 publications

MonoIS3DLoc: Simulation to Reality Learning Based Monocular Instance Segmentation to 3D Objects Localization From Aerial View

MonoIS3DLoc: Simulation to Reality Learning Based Monocular Instance Segmentation to 3D Objects Localization From Aerial View

Mask Transfiner for High-Quality Instance Segmentation

Contact Info

Product

Resources

About