Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Shoumeng, Chen, Jie, Li, Xinrun, Wan, Ru, Xue, Xiangyang, Pu, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917726646173696
author Qiu, Shoumeng
Chen, Jie
Li, Xinrun
Wan, Ru
Xue, Xiangyang
Pu, Jian
author_facet Qiu, Shoumeng
Chen, Jie
Li, Xinrun
Wan, Ru
Xue, Xiangyang
Pu, Jian
contents In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not require complex teacher models or information from extra sensors. Specifically, for the teacher model training, we propose to noise the label and then incorporate it into input to effectively boost the lightweight teacher performance. To ensure the robustness of the teacher model against the introduced noise, we propose a dual-path consistency training strategy featuring a distance loss between the outputs of two paths. For the student model training, we keep it consistent with the standard distillation for simplicity. Our approach not only boosts the efficacy of knowledge distillation but also increases the flexibility in selecting teacher and student models. To demonstrate the advantages of our Label Assisted Distillation (LAD) method, we conduct extensive experiments on five challenging datasets including Cityscapes, ADE20K, PASCAL-VOC, COCO-Stuff 10K, and COCO-Stuff 164K, five popular models: FCN, PSPNet, DeepLabV3, STDC, and OCRNet, and results show the effectiveness and generalization of our approach. We posit that incorporating labels into the input, as demonstrated in our work, will provide valuable insights into related fields. Code is available at https://github.com/skyshoumeng/Label_Assisted_Distillation.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13254
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation
Qiu, Shoumeng
Chen, Jie
Li, Xinrun
Wan, Ru
Xue, Xiangyang
Pu, Jian
Computer Vision and Pattern Recognition
In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not require complex teacher models or information from extra sensors. Specifically, for the teacher model training, we propose to noise the label and then incorporate it into input to effectively boost the lightweight teacher performance. To ensure the robustness of the teacher model against the introduced noise, we propose a dual-path consistency training strategy featuring a distance loss between the outputs of two paths. For the student model training, we keep it consistent with the standard distillation for simplicity. Our approach not only boosts the efficacy of knowledge distillation but also increases the flexibility in selecting teacher and student models. To demonstrate the advantages of our Label Assisted Distillation (LAD) method, we conduct extensive experiments on five challenging datasets including Cityscapes, ADE20K, PASCAL-VOC, COCO-Stuff 10K, and COCO-Stuff 164K, five popular models: FCN, PSPNet, DeepLabV3, STDC, and OCRNet, and results show the effectiveness and generalization of our approach. We posit that incorporating labels into the input, as demonstrated in our work, will provide valuable insights into related fields. Code is available at https://github.com/skyshoumeng/Label_Assisted_Distillation.
title Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.13254