mlsanityData to 7 Oct 2026

Cross Modal Distillation for Supervision Transfer

arXiv 1507.00448 ↗First posted 2 Jul 2015cs.CVcited by 173

Not on the map. Why?

Abstract (arXiv)

In this work we propose a technique that transfers supervision between images from different modalities. We use learned representations from a large labeled modality as a supervisory signal for training representations for a new unlabeled paired modality. Our method enables learning of rich representations for unlabeled modalities and can be used as a pre-training procedure for new modalities with limited labeled data. We show experimental results where we transfer supervision from labeled RGB images to unlabeled depth and optical flow images and demonstrate large improvements for both these cross modal supervision transfers. Code, data and pre-trained models are available at https://github.com/s-gupta/fast-rcnn/tree/distillation

Key facts. Cited by 173 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 26; 2023: 29; 2024: 27; 2025: 21; 2026: 32.

173 papers.

Sort:

By area:

  1. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  2. 2021What Makes Multi-modal Learning Better than Single (Provably)cited by 151
  3. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  4. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  5. 2022Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)cited by 115
  6. 2021Ego-Exo: Transferring Visual Representations from Third-person to First-person Videoscited by 98
  7. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  8. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  9. 2022Membership Inference Attacks by Exploiting Loss Trajectorycited by 93
  10. 2022Learning Audio-Video Modalities from Image Captionscited by 80
  11. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  12. 2023RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Drivingcited by 76
38 more
  1. 2022X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioningcited by 70
  2. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  3. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  4. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  5. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  6. 2021Distilling Audio-Visual Knowledge by Compositional Contrastive Learningcited by 53
  7. 2023On Uni-Modal Feature Learning in Supervised Multi-Modal Learningcited by 53
  8. 20213D-to-2D Distillation for Indoor Scene Parsingcited by 47
  9. 2021EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillationcited by 46
  10. 2022The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillationcited by 44
  11. 2022A Survey on Heterogeneous Federated Learningcited by 42
  12. 2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
  13. 2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36
  14. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  15. 2021Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretrainingcited by 32
  16. 2021Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detectioncited by 32
  17. 2023EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understandingcited by 32
  18. 2021Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translationcited by 31
  19. 2022Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsingcited by 29
  20. 2023Multimodal Distillation for Egocentric Action Recognitioncited by 28
  21. 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalitiescited by 28
  22. 2024DLF: Disentangled-Language-Focused Multimodal Sentiment Analysiscited by 27
  23. 2021Multimodal Knowledge Expansioncited by 26
  24. 2023Teacher-Student Architecture for Knowledge Distillation: A Surveycited by 26
  25. 2022Improving Visual Grounding by Encouraging Consistent Gradient-based Explanationscited by 24
  26. 2023ViLA: Efficient Video-Language Alignment for Video Question Answeringcited by 23
  27. 2024EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognitioncited by 23
  28. 2021VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfercited by 22
  29. 2024OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of Allcited by 20
  30. 2023Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillationcited by 19
  31. 2021Weakly supervised segmentation with cross-modality equivariant constraintscited by 18
  32. 2021Joint Face Image Restoration and Frontalization for Recognitioncited by 18
  33. 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
  34. 2022Cross-Modal Knowledge Transfer Without Task-Relevant Source Datacited by 17
  35. 2023KD-DLGAN: Data Limited Image Generation via Knowledge Distillationcited by 16
  36. 2024Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervisioncited by 16
  37. 2021Improving Human-Object Interaction Detection via Phrase Learning and Label Compositioncited by 15
  38. 2024Wearable Accelerometer Foundation Models for Health via Knowledge Distillationcited by 15

50 most cited of 173 All 173 (JSON)