Hybrid Task Cascade for Instance Segmentation

Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 4969 - 4978
Hlavní autori: Chen, Kai, Pang, Jiangmiao, Wang, Jiaqi, Xiong, Yu, Li, Xiaoxiao, Sun, Shuyang, Feng, Wansen, Liu, Ziwei, Shi, Jianping, Ouyang, Wanli, Loy, Chen Change, Lin, Dahua
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2019
Predmet:
Categorization
Computer architecture
Computer vision
Convolutional codes
Instance segmentation
Object detection
Pattern recognition
Recognition: Detection
Retrieval
Semantic segmentation
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Cascade is a classic yet powerful architecture that has boosted performance on various tasks. However, how to introduce cascade to instance segmentation remains an open question. A simple combination of Cascade R-CNN and Mask R-CNN only brings limited gain. In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation. In this work, we propose 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. Overall, this framework can learn more discriminative features progressively while integrating complementary features together in each stage. Without bells and whistles, a single HTC obtains 38.4% and 1.5% improvement over a strong Cascade Mask R-CNN baseline on MSCOCO dataset. Moreover, our overall system achieves 48.6 mask AP on the test-challenge split, ranking 1st in the COCO 2018 Challenge Object Detection Task. Code is available at https://github.com/open-mmlab/mmdetection.
ISSN:1063-6919
DOI:10.1109/CVPR.2019.00511