Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation

• URL: http://arxiv.org/abs/2505.24361v1
• Date: Fri, 30 May 2025 08:53:35 GMT
• Title: Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation
• Authors: Roger Ferrod, Cássio F. Dantas, Luigi Di Caro, Dino Ienco,
• Abstract summary: We introduce CroDiNo-KD (Cross-Modal Disentanglement: a New Outlook on Knowledge Distillation), a novel cross-modal knowledge distillation framework for RGBD semantic segmentation.<n>Our approach simultaneously learns single-modality RGB and Depth models by exploiting disentanglement representation, contrastive learning and decoupled data augmentation.<n>Our findings illustrate the quality of CroDiNo-KD, and they suggest reconsidering the conventional teacher/student paradigm to distill information from multi-modal data to single-modality neural networks.
• Score: 4.7859023148002215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-modal RGB and Depth (RGBD) data are predominant in many domains such as robotics, autonomous driving and remote sensing. The combination of these multi-modal data enhances environmental perception by providing 3D spatial context, which is absent in standard RGB images. Although RGBD multi-modal data can be available to train computer vision models, accessing all sensor modalities during the inference stage may be infeasible due to sensor failures or resource constraints, leading to a mismatch between data modalities available during training and inference. Traditional Cross-Modal Knowledge Distillation (CMKD) frameworks, developed to address this task, are typically based on a teacher/student paradigm, where a multi-modal teacher distills knowledge into a single-modality student model. However, these approaches face challenges in teacher architecture choices and distillation process selection, thus limiting their adoption in real-world scenarios. To overcome these issues, we introduce CroDiNo-KD (Cross-Modal Disentanglement: a New Outlook on Knowledge Distillation), a novel cross-modal knowledge distillation framework for RGBD semantic segmentation. Our approach simultaneously learns single-modality RGB and Depth models by exploiting disentanglement representation, contrastive learning and decoupled data augmentation with the aim to structure the internal manifolds of neural network models through interaction and collaboration. We evaluated CroDiNo-KD on three RGBD datasets across diverse domains, considering recent CMKD frameworks as competitors. Our findings illustrate the quality of CroDiNo-KD, and they suggest reconsidering the conventional teacher/student paradigm to distill information from multi-modal data to single-modality neural networks.

Related papers

• Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework [58.362064122489166]
  This paper introduces the Cross-modal Few-Shot Learning task, which aims to recognize instances across multiple modalities while relying on scarce labeled data.<n>We propose a Generative Transfer Learning framework by simulating how humans abstract and generalize concepts.<n>We show that the GTL achieves state-of-the-art performance across seven multi-modal datasets across RGB-Sketch, RGB-Infrared, and RGB-Depth.
  arXiv  Detail & Related papers  (2024-10-14T16:09:38Z)
• DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning [3.763772992906958]
  Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch. DisCoM-KD (Disentanglement-learning based Cross-Modal Knowledge Distillation) explicitly models different types of per-modality information.
  arXiv  Detail & Related papers  (2024-08-05T13:44:15Z)
• XTrack: Multimodal Training Boosts RGB-X Video Object Trackers [88.72203975896558]
  It is crucial to ensure that knowledge gained from multimodal sensing is effectively shared.<n>Similar samples across different modalities have more knowledge to share than otherwise.<n>We propose a method for RGB-X tracker during inference, with an average +3% precision improvement over the current SOTA.
  arXiv  Detail & Related papers  (2024-05-28T03:00:58Z)
• Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport [46.91791643660991]
  Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments. These models struggle in the wild because of the unavailability and quality of modalities used for training. In practice, only a subset of the training-time modalities may be available at test time. Learning with privileged information enables models to exploit data from additional modalities that are only available during training.
  arXiv  Detail & Related papers  (2024-01-27T19:44:15Z)
• On Correlated Knowledge Distillation for Monitoring Human Pose with Radios [41.74439665339141]
  We propose and develop a simple experimental testbed to study the feasibility of a novel idea by coupling radio frequency (RF) sensing technology with Correlated Knowledge Distillation (CKD) theory. The proposed CKD framework transfers and fuses pose knowledge from a robust "Teacher" model to a parameterized "Student" model, which can be a promising technique for obtaining accurate yet lightweight pose estimates.
  arXiv  Detail & Related papers  (2023-05-24T07:34:49Z)
• Continual Vision-Language Representation Learning with Off-Diagonal Information [112.39419069447902]
  Multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. This paper discusses the feasibility of continual CLIP training using streaming data.
  arXiv  Detail & Related papers  (2023-05-11T08:04:46Z)
• Motor Imagery Decoding Using Ensemble Curriculum Learning and Collaborative Training [11.157243900163376]
  Multi-subject EEG datasets present several kinds of domain shifts. These domain shifts impede robust cross-subject generalization. We propose a two-stage model ensemble architecture built with multiple feature extractors. We demonstrate that our model ensembling approach combines the powers of curriculum learning and collaborative training.
  arXiv  Detail & Related papers  (2022-11-21T13:45:44Z)
• CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation [130.08432609780374]
  In 3D action recognition, there exists rich complementary information between skeleton modalities. We propose a new Cross-modal Mutual Distillation (CMD) framework with the following designs. Our approach outperforms existing self-supervised methods and sets a series of new records.
  arXiv  Detail & Related papers  (2022-08-26T06:06:09Z)
• Siamese Network for RGB-D Salient Object Detection and Beyond [113.30063105890041]
  A novel framework is proposed to learn from both RGB and depth inputs through a shared network backbone. Comprehensive experiments using five popular metrics show that the designed framework yields a robust RGB-D saliency detector. We also link JL-DCF to the RGB-D semantic segmentation field, showing its capability of outperforming several semantic segmentation models.
  arXiv  Detail & Related papers  (2020-08-26T06:01:05Z)
• Unpaired Multi-modal Segmentation via Knowledge Distillation [77.39798870702174]
  We propose a novel learning scheme for unpaired cross-modality image segmentation. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI. We have extensively validated our approach on two multi-class segmentation problems.
  arXiv  Detail & Related papers  (2020-01-06T20:03:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.