Open AccessPosted Content
Domain Adaptive Knowledge Distillation for Driving Scene Semantic Segmentation
Reads0
Chats0
TLDR
This paper presents a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the model with the ability to deal with these issues in a comprehensive manner and introduces a novel cross entropy loss that leverages pseudo labels from the teacher.Abstract:
Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the model with the ability to deal with these issues in a comprehensive manner. We term this as "Domain Adaptive Knowledge Distillation" and address the same in the context of unsupervised domain-adaptive semantic segmentation by proposing a multi-level distillation strategy to effectively distil knowledge at different levels. Further, we introduce a novel cross entropy loss that leverages pseudo labels from the teacher. These pseudo teacher labels play a multifaceted role towards: (i) knowledge distillation from the teacher network to the student network & (ii) serving as a proxy for the ground truth for target domain images, where the problem is completely unsupervised. We introduce four paradigms for distilling domain adaptive knowledge and carry out extensive experiments and ablation studies on real-to-real as well as synthetic-to-real scenarios. Our experiments demonstrate the profound success of our proposed method.read more
Citations
More filters
UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation
TL;DR: This paper proposes UM-Adapt - a unified framework to effectively perform unsupervised domain adaptation for spatially-structured prediction tasks, simultaneously maintaining a balanced performance across individual tasks in a multi-task setting.
Journal ArticleDOI
Adaptive Perspective Distillation for Semantic Segmentation
Zhuotao Tian,Pengguang Chen,Xin Lai,Li Jiang,Shu Liu,Hengshuang Zhao,Bei Yu,Ming-Xue Yang,Jiaya Jia +8 more
TL;DR: Adaptive Perspective Distillation (APD) is proposed that creates an adaptive local perspective for each individual training sample that extracts detailed contextual information from each training sample specifically, mining more details from the teacher and thus achieving better knowledge distillation results on the student.
Journal ArticleDOI
DistillAdapt: Source-Free Active Visual Domain Adaptation
TL;DR: The source-free approach, DistillAdapt, results in an improvement of 0 .
Journal ArticleDOI
Entropy-weighted reconstruction adversary and curriculum pseudo labeling for domain adaptation in semantic segmentation
TL;DR: In this article , an entropy-weighted adversarial framework is designed to enhance the discriminativeness and transferability of the presented model to the target domain via an autoencoder-based discriminator.
Proceedings ArticleDOI
SALAD : Source-free Active Label-Agnostic Domain Adaptation for Classification, Segmentation and Detection
TL;DR: The source-free approach, SALAD, is presented, which results in an improvement of 0.5% − 31 .
References
More filters
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Posted Content
Distilling the Knowledge in a Neural Network
TL;DR: This work shows that it can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model and introduces a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse.
Journal ArticleDOI
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TL;DR: This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.
Proceedings ArticleDOI
Pyramid Scene Parsing Network
TL;DR: This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.