GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild

Michieli, Umberto; Borsato, Edoardo; Rossi, Luca; Zanuttigh, Pietro

doi:10.1007/978-3-030-58598-3_24

Cited by 32 publications

(18 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coarse-to-Fine Learning: hierarchical composition of semantic representations has been explored in few previous work for part-based regularization [13,14] and coarse-to-fine approaches where coarse-level classes are refined into finer categories [15,16,17,18]. In particular, coarse-to-fine learning in semantic segmentation can be addressed by resorting either to a direct concatenation of features [15] or using a semantic embedding network to transfer object-level predictions during part-level training [18]. However, approaches for this task all assume that the domain distribution remains unaltered at subsequent refinement stages and they are comprised of one single refinement stage.…”

Section: Related Workmentioning

confidence: 99%

Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation

Shenaj,

Barbato,

Michieli

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Deep neural networks are typically trained in a single shot for a specific task and data distribution, but in real world settings both the task and the domain of application can change. The problem becomes even more challenging in dense predictive tasks, such as semantic segmentation, and furthermore most approaches tackle the two problems separately. In this paper we introduce the novel task of coarse-to-fine learning of semantic segmentation architectures in presence of domain shift. We consider subsequent learning stages progressively refining the task at the semantic level; i.e., the finer set of semantic labels at each learning step is hierarchically derived from the coarser set of the previous step. We propose a new approach (CCDA) to tackle this scenario. First, we employ the maximum squares loss to align source and target domains and, at the same time, to balance the gradients between well-classified and harder samples. Second, we introduce a novel coarse-to-fine knowledge distillation constraint to transfer network capabilities acquired on a coarser set of labels to a set of finer labels. Finally, we design a coarse-to-fine weight initialization rule to spread the importance from each coarse class to the respective finer classes. To evaluate our approach, we design two benchmarks where source knowledge is extracted from the GTA5 dataset and it is transferred to either the Cityscapes or the IDD datasets, and we show how it outperforms the main competitors.

show abstract

Section: Related Workmentioning

confidence: 99%

Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation

Shenaj,

Barbato,

Michieli

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, dense part-level segmentation remained for a long time instance-agnostic, as it is usually treated as a semantic segmentation problem [17,22,23,30,36,41,43,44,45,64]. In the trend of coming to more holistic tasks, a dense pose task was introduced in [1] and a unification of pose estimation and part segmentation is provided in [14].…”

Section: Part Parsingmentioning

confidence: 99%

“…Most research has focused on part segmentation for humans [15,18,26,28,29,35,34,38,51,56,63], but other parts have also received attention, e.g., facial parts [37], and animal parts [6,54]. A limited amount of papers have addressed multi-class part segmentation [45,64], but so far these methods are not instance-aware. As a result, instance-aware part segmentation on a more general dataset, consisting of a wider range of classes and parts, remains unaddressed.…”

Section: Part Parsingmentioning

confidence: 99%

See 1 more Smart Citation

Part-aware Panoptic Segmentation

Geus

Meletis

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

In this work, we introduce the new scene understanding task of Part-aware Panoptic Segmentation (PPS), which aims to understand a scene at multiple levels of abstraction, and unifies the tasks of scene parsing and part parsing. For this novel task, we provide consistent annotations on two commonly used datasets: Cityscapes and Pascal VOC. Moreover, we present a single metric to evaluate PPS, called Part-aware Panoptic Quality (PartPQ). For this new task, using the metric and annotations, we set multiple baselines by merging results of existing state-of-the-art methods for panoptic segmentation and part segmentation. Finally, we conduct several experiments that evaluate the importance of the different levels of abstraction in this single task.

show abstract

“…The problem of segmenting the target part in an image is one of the important issues that has been studied. GMNet [8], one of the most recently published semantic part segmentation methods, proposed a method of part segmentation by combining CNN and graph methods. The proposed model is trained and evaluated with PASCAL VOC Part [7] dataset (based on 108 Part) and the average accuracy intersection of union (IOU) is about 50%.…”

Section: Semantic Part Segmentationmentioning

confidence: 99%

Interactive Part Segmentation Using Edge Images

Park

2021

Applied Sciences

View full text Add to dashboard Cite

As more and more fields utilize deep learning, there is an increasing demand to make suitable training data for each field. The existing interactive object segmentation models can easily make the mask label data because these can accurately segment the area of the target object through user interaction. However, it is difficult to accurately segment the target part in the object using the existing models. We propose a method to increase the accuracy of part segmentation by using the proposed interactive object segmentation model trained only with edge images instead of color images. The results evaluated with the PASCAL VOC Part dataset show that the proposed method can accurately segment the target part compared to the existing interactive object segmentation model and the semantic part-segmentation model.

show abstract

GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild

Cited by 32 publications

References 46 publications

Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation

Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation

Part-aware Panoptic Segmentation

Interactive Part Segmentation Using Edge Images

Contact Info

Product

Resources

About