Multi-Granularity Distillation Scheme Towards Lightweight
Semi-Supervised Semantic Segmentation
- URL: http://arxiv.org/abs/2208.10169v1
- Date: Mon, 22 Aug 2022 09:32:06 GMT
- Title: Multi-Granularity Distillation Scheme Towards Lightweight
Semi-Supervised Semantic Segmentation
- Authors: Jie Qin, Jie Wu, Ming Li, Xuefeng Xiao, Min Zheng, Xingang Wang
- Abstract summary: We offer the first attempt to provide lightweight Semi-Supervised Semantics (SSSS) models via a novel multi-granularity distillation scheme (MGD)
MGD is formulated as a labeled-unlabeled data cooperative distillation scheme, which helps to take full advantage of diverse data characteristics.
Experimental results on PASCAL2012 and Cityscapes reveal that MGD can outperform the competitive approaches by a large margin under diverse partition protocols.
- Score: 33.36652973690884
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Albeit with varying degrees of progress in the field of Semi-Supervised
Semantic Segmentation, most of its recent successes are involved in unwieldy
models and the lightweight solution is still not yet explored. We find that
existing knowledge distillation techniques pay more attention to pixel-level
concepts from labeled data, which fails to take more informative cues within
unlabeled data into account. Consequently, we offer the first attempt to
provide lightweight SSSS models via a novel multi-granularity distillation
(MGD) scheme, where multi-granularity is captured from three aspects: i)
complementary teacher structure; ii) labeled-unlabeled data cooperative
distillation; iii) hierarchical and multi-levels loss setting. Specifically,
MGD is formulated as a labeled-unlabeled data cooperative distillation scheme,
which helps to take full advantage of diverse data characteristics that are
essential in the semi-supervised setting. Image-level semantic-sensitive loss,
region-level content-aware loss, and pixel-level consistency loss are set up to
enrich hierarchical distillation abstraction via structurally complementary
teachers. Experimental results on PASCAL VOC2012 and Cityscapes reveal that MGD
can outperform the competitive approaches by a large margin under diverse
partition protocols. For example, the performance of ResNet-18 and MobileNet-v2
backbone is boosted by 11.5% and 4.6% respectively under 1/16 partition
protocol on Cityscapes. Although the FLOPs of the model backbone is compressed
by 3.4-5.3x (ResNet-18) and 38.7-59.6x (MobileNetv2), the model manages to
achieve satisfactory segmentation results.
Related papers
- 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic
Segmentation [92.17700318483745]
We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network.
IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
arXiv Detail & Related papers (2023-11-27T07:57:29Z) - Hierarchical Point-based Active Learning for Semi-supervised Point Cloud
Semantic Segmentation [48.40853126077237]
It is labour-intensive to acquire large-scale point cloud data with point-wise labels.
Active learning is one of the effective strategies to achieve this purpose but is still under-explored.
This paper develops a hierarchical point-based active learning strategy.
arXiv Detail & Related papers (2023-08-22T03:52:05Z) - Coupling Global Context and Local Contents for Weakly-Supervised
Semantic Segmentation [54.419401869108846]
We propose a single-stage WeaklySupervised Semantic (WSSS) model with only the image-level class label supervisions.
A flexible context aggregation module is proposed to capture the global object context in different granular spaces.
A semantically consistent feature fusion module is proposed in a bottom-up parameter-learnable fashion to aggregate the fine-grained local contents.
arXiv Detail & Related papers (2023-04-18T15:29:23Z) - Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation
for autonomous vehicles [63.20765930558542]
3D semantic data are useful for core perception tasks such as obstacle detection and ego-vehicle localization.
We propose a new dataset, Navya 3D (Navya3DSeg), with a diverse label space corresponding to a large scale production grade operational domain.
It contains 23 labeled sequences and 25 supplementary sequences without labels, designed to explore self-supervised and semi-supervised semantic segmentation benchmarks on point clouds.
arXiv Detail & Related papers (2023-02-16T13:41:19Z) - Dual Adaptive Transformations for Weakly Supervised Point Cloud
Segmentation [78.6612285236938]
We propose a novel DAT (textbfDual textbfAdaptive textbfTransformations) model for weakly supervised point cloud segmentation.
We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets.
arXiv Detail & Related papers (2022-07-19T05:43:14Z) - Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation [74.67594286008317]
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation.
We propose the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level.
arXiv Detail & Related papers (2022-06-05T05:28:32Z) - Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19
Lung Infection Segmentation on CT Images [1.898617934078969]
In this paper, a novel segmentation scheme is proposed for the infections of COVID-19 on CT images.
A deep collaborative supervision scheme is proposed to guide the network learning the features of edges and semantics.
The effectiveness of the proposed scheme is demonstrated on four various COVID-19 CT datasets.
arXiv Detail & Related papers (2021-12-20T07:32:39Z) - Double Similarity Distillation for Semantic Image Segmentation [18.397968199629215]
We propose a knowledge distillation framework called double similarity distillation (DSD) to improve the classification accuracy of all existing compact networks.
Specifically, we propose a pixel-wise similarity distillation (PSD) module that utilizes residual attention maps to capture more detailed spatial dependencies.
Considering the differences in characteristics between semantic segmentation task and other computer vision tasks, we propose a category-wise similarity distillation (CSD) module.
arXiv Detail & Related papers (2021-07-19T02:45:13Z) - Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for
Semantic Segmentation [34.790169990156684]
We focus on a more practical setting of semi-supervised domain adaptation (SSDA) where both a small set of labeled target data and large amounts of labeled source data are available.
Two kinds of data mixing methods are proposed to reduce domain gap in both region-level and sample-level respectively.
We can obtain two complementary domain-mixed teachers based on dual-level mixed data from holistic and partial views respectively.
arXiv Detail & Related papers (2021-03-08T12:33:17Z)
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.