mlsanityData to 7 Oct 2026

Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting

arXiv 2108.08023 ↗First posted 18 Aug 2021cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc. Thus, for learning a general model, training with data from multiple different datasets might be a remedy and be of great value. In this paper, we resort to the multi-domain joint learning and propose a simple but effective Domain-specific Knowledge Propagating Network (DKPNet)1 for unbiasedly learning the knowledge from multiple diverse data domains at the same time. It is mainly achieved by proposing the novel Variational Attention(VA) technique for explicitly modeling the attention distributions for different domains. And as an extension to VA, Intrinsic Variational Attention(InVA) is proposed to handle the problems of over-lapped domains and sub-domains. Extensive experiments have been conducted to validate the superiority of our DKPNet over several popular datasets, including ShanghaiTech A/B, UCF-QNRF and NWPU.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 41 of its 60 references that are in the map. First posted on arXiv 18 Aug 2021.

Builds on

41 of 60 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  5. 2017Learning multiple visual domains with residual adapterscited by 553
  6. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  7. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  8. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  9. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  10. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
  11. 2019Learning from Synthetic Data for Crowd Counting in the Wildcited by 148
  12. 2020Distribution Matching for Crowd Countingcited by 143
29 more
  1. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  2. 2019Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detectioncited by 73
  3. 2019Point in, Box out: Beyond Counting Persons in Crowdscited by 62
  4. 2018Leveraging Unlabeled Data for Crowd Counting by Learning to Rankcited by 57
  5. 2017Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNscited by 55
  6. 2019Perspective-Guided Convolution Networks for Crowd Countingcited by 54
  7. 2017DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimationcited by 49
  8. 2018Revisiting Perspective Information for Efficient Crowd Countingcited by 49
  9. 2018Iterative Crowd Countingcited by 48
  10. 2019From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquercited by 48
  11. 2019Crowd Counting with Deep Structured Scale Integration Networkcited by 46
  12. 2018ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understandingcited by 45
  13. 2016Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identificationcited by 41
  14. 2019Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Countingcited by 36
  15. 2020NAS-Count: Counting-by-Density with Neural Architecture Searchcited by 36
  16. 2019Counting with Focus for Freecited by 33
  17. 2019HA-CCN: Hierarchical Attention-based Crowd Counting Networkcited by 32
  18. 2020Shallow Feature Based Dense Attention Network for Crowd Countingcited by 28
  19. 2017People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgettingcited by 25
  20. 2017Crowd counting via scale-adaptive convolutional neural networkcited by 23
  21. 2018Crowd Counting using Deep Recurrent Spatial-Aware Networkcited by 21
  22. 2018Multi-Domain Pose Network for Multi-Person Pose Estimation and Trackingcited by 21
  23. 2020Hybrid Graph Neural Networks for Crowd Countingcited by 21
  24. 2019Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrievalcited by 15
  25. 2018Virtual Class Enhanced Discriminative Embedding Learningcited by 13
  26. 2019Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clusteringcited by 10
  27. 2019CODA: Counting Objects via Scale-aware Adversarial Density Adaptioncited by 10
  28. 2020Few-Shot Scene Adaptive Crowd Counting Using Meta-Learningcited by 7
  29. 2019Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillancecited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 7; 2023: 5; 2024: 2.

15 papers.

Sort:

By area:

  1. 2022Rethinking Spatial Invariance of Convolutional Networks for Object Countingcited by 54
  2. 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Modelcited by 47
  3. 2022Domain-General Crowd Counting in Unseen Scenarioscited by 20
  4. 2022Redesigning Multi-Scale Neural Network for Crowd Countingcited by 17
  5. 2023Regressor-Segmenter Mutual Prompt Learning for Crowd Countingcited by 16
  6. 2021Scene-Adaptive Attention Network for Crowd Countingcited by 12
  7. 2022Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Countingcited by 9
  8. 2023RGB-D Indiscernible Object Counting in Underwater Scenescited by 9
  9. 2023Variational Probabilistic Fusion Network for RGB-T Semantic Segmentationcited by 7
  10. 2024The Effectiveness of a Simplified Model Structure for Crowd Countingcited by 3
  11. 2022Counting with Adaptive Auxiliary Learningcited by 1
  12. 2022SSR-HEF: Crowd Counting with Multi-Scale Semantic Refining and Hard Example Focusingcited by 1
3 more
  1. 2023Density Map Distillation for Incremental Object Countingcited by 1
  2. 2024Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Countingcited by 1
  3. 2022Indirect-Instant Attention Optimization for Crowd Counting in Dense Scenescited by 0