mlsanityData to 7 Oct 2026

Distilling Inter-Class Distance for Semantic Segmentation

arXiv 2205.03650 ↗First posted 7 May 2022cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation distillation, neglecting to transfer the knowledge of the inter-class distance in the feature space, which is important for semantic segmentation. To address this issue, we propose an Inter-class Distance Distillation (IDD) method to transfer the inter-class distance in the feature space from the teacher network to the student network. Furthermore, semantic segmentation is a position-dependent task,thus we exploit a position information distillation module to help the student network encode more position information. Extensive experiments on three popular datasets: Cityscapes, Pascal VOC and ADE20K show that our method is helpful to improve the accuracy of semantic segmentation models and achieves the state-of-the-art performance. E.g. it boosts the benchmark model("PSPNet+ResNet18") by 7.50% in accuracy on the Cityscapes dataset.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 26 of its 32 references that are in the map. First posted on arXiv 7 May 2022.

Builds on

26 of 32 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2016Pyramid Scene Parsing Networkcited by 2,472
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  10. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  11. 2019Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challengescited by 313
  12. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
14 more
  1. 2018Context Encoding for Semantic Segmentationcited by 289
  2. 2019Structured Knowledge Distillation for Dense Predictioncited by 277
  3. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  4. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 260
  5. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  6. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 171
  7. 2020Channel-wise Knowledge Distillation for Dense Predictioncited by 161
  8. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  9. 2018ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentationcited by 133
  10. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  11. 2019Knowledge Adaptation for Efficient Semantic Segmentationcited by 105
  12. 2017Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learningcited by 37
  13. 2018Improving Fast Segmentation With Teacher-student Learningcited by 34
  14. 2020Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenescited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 5; 2025: 2; 2026: 3.

16 papers.

Sort:

By area:

  1. 2024Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackerscited by 24
  2. 2024Learning to Unlearn for Robust Machine Unlearningcited by 19
  3. 2025From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevancecited by 7
  4. 2023Foreground Object Search by Distilling Composite Image Featurecited by 6
  5. 2023Towards Activated Muscle Group Estimation in the Wildcited by 4
  6. 2024SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentationcited by 4
  7. 2025Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samplescited by 4
  8. 2023UniParser: Multi-Human Parsing with Unified Correlation Representation Learningcited by 3
  9. 2024Instance Temperature Knowledge Distillationcited by 3
  10. 2026EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagerycited by 3
  11. 2023CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decodercited by 2
  12. 2023Single-stage Multi-human Parsing via Point Sets and Center-based Offsetscited by 2
4 more
  1. 2026Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognitioncited by 2
  2. 2023Towards Comparable Knowledge Distillation in Semantic Image Segmentationcited by 1
  3. 2024FADE: A Dataset for Detecting Falling Objects around Buildings in Videocited by 1
  4. 2026Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Renderingcited by 1