CoMAD: A Multiple-Teacher Self-Supervised Distillation Framework

• URL: http://arxiv.org/abs/2508.04816v1
• Date: Wed, 06 Aug 2025 18:55:14 GMT
• Title: CoMAD: A Multiple-Teacher Self-Supervised Distillation Framework
• Authors: Sriram Mandalika, Lalitha V,
• Abstract summary: We introduce Consensus-oriented Masked Distillation (CoMAD)<n>It unifies knowledge from self-supervised Vision Transformers into a compact student network.<n>On ImageNet-1K, CoMAD's ViT-Tiny achieves 75.4 percent Top-1, an increment of 0.4 percent over the previous state-of-the-art.
• Score: 1.2172320168050466
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, learn powerful representations from unlabeled data but are typically pretrained in isolation, overlooking complementary insights and yielding large models that are impractical for resource-constrained deployment. To overcome these challenges, we introduce Consensus-oriented Masked Distillation (CoMAD), a lightweight, parameter-free framework that unifies knowledge from multiple current state-of-the-art self-supervised Vision Transformers into a compact student network. CoMAD distills from three pretrained ViT-Base teachers, MAE, MoCo v3, and iBOT, each offering distinct semantic and contextual priors. Rather than naively averaging teacher outputs, we apply asymmetric masking: the student sees only 25 percent of patches while each teacher receives a progressively lighter, unique mask, forcing the student to interpolate missing features under richer contexts. Teacher embeddings are aligned to the student's space via a linear adapter and layer normalization, then fused through our joint consensus gating, which weights each token by combining cosine affinity with inter-teacher agreement. The student is trained with dual-level KL divergence on visible tokens and reconstructed feature maps, capturing both local and global structure. On ImageNet-1K, CoMAD's ViT-Tiny achieves 75.4 percent Top-1, an increment of 0.4 percent over the previous state-of-the-art. In dense-prediction transfers, it attains 47.3 percent mIoU on ADE20K, and 44.5 percent box average precision and 40.5 percent mask average precision on MS-COCO, establishing a new state-of-the-art in compact SSL distillation.

Related papers

• CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation [7.478518822890964]
  We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pretrained vision foundation models (VFM) into compact experts.<n>Cast unfolds in three stages: (1) domain adaptation of the VFM teacher(s) via self-training with contrastive pixel calibration, (2) distillation into a compact student via a unified multi-objective loss.<n>On Cityscapes and ADE20K, our 11X smaller student surpasses its adapted VFM teacher(s) by +3.4 AP (33.9 vs. 30.5) and +1.5 AP (16.7 vs. 15.2) and outperforms state-
  arXiv  Detail & Related papers  (2025-05-28T02:45:42Z)
• Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning [116.75939193785143]
  Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. In 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant.
  arXiv  Detail & Related papers  (2024-07-08T12:28:56Z)
• Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation [56.053397775016755]
  We propose a sequential approach to knowledge distillation that progressively transfers the knowledge of a set of teacher detectors to a given lightweight student. To the best of our knowledge, we are the first to successfully distill knowledge from Transformer-based teacher detectors to convolution-based students.
  arXiv  Detail & Related papers  (2023-08-17T17:17:08Z)
• Mixed Autoencoder for Self-supervised Visual Representation Learning [95.98114940999653]
  Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. This paper studies the prevailing mixing augmentation for MAE.
  arXiv  Detail & Related papers  (2023-03-30T05:19:43Z)
• A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation [35.233203757760066]
  We propose a learnable nonlinear channel-wise transformation to align the features of the student and the teacher model. Our method achieves significant performance improvements in various computer vision tasks.
  arXiv  Detail & Related papers  (2023-03-23T12:13:29Z)
• MOMA:Distill from Self-Supervised Teachers [6.737710830712818]
  We propose MOMA to distill from pre-trained MoCo and MAE in a self-supervised manner to collaborate the knowledge from both paradigms. Experiments show MOMA delivers compact student models with comparable performance to existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-02-04T04:23:52Z)
• SdAE: Self-distillated Masked Autoencoder [95.3684955370897]
  Self-distillated masked AutoEncoder network SdAE is proposed in this paper. With only 300 epochs pre-training, a vanilla ViT-Base model achieves an 84.1% fine-tuning accuracy on ImageNet-1k classification.
  arXiv  Detail & Related papers  (2022-07-31T15:07:25Z)
• mc-BEiT: Multi-choice Discretization for Image BERT Pre-training [52.04866462439979]
  Image BERT pre-training with masked image modeling (MIM) is a popular practice to cope with self-supervised representation learning. We introduce an improved BERT-style image pre-training method, namely mc-BEiT, which performs MIM proxy tasks towards eased and refined multi-choice training objectives.
  arXiv  Detail & Related papers  (2022-03-29T09:08:18Z)
• G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation [49.421099172544196]
  We propose a novel semantic-guided feature imitation technique, which automatically performs soft matching between feature pairs across all pyramid levels. We also introduce contrastive distillation to effectively capture the information encoded in the relationship between different feature regions. Our method consistently outperforms the existing detection KD techniques, and works when (1) components in the framework are used separately and in conjunction.
  arXiv  Detail & Related papers  (2021-08-17T07:44:27Z)

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.