Aligning in a Compact Space: Contrastive Knowledge Distillation between Heterogeneous Architectures
- URL: http://arxiv.org/abs/2405.18524v1
- Date: Tue, 28 May 2024 18:44:42 GMT
- Title: Aligning in a Compact Space: Contrastive Knowledge Distillation between Heterogeneous Architectures
- Authors: Hongjun Wu, Li Xiao, Xingkuo Zhang, Yining Miao,
- Abstract summary: We propose a Low-Frequency Components-based Contrastive Knowledge Distillation (LFCC) framework that significantly enhances the performance of feature-based distillation.
Specifically, we designe a set of multi-scale low-pass filters to extract the low-frequency components of intermediate features from both the teacher and student models.
We show that LFCC achieves superior performance on the challenging benchmarks of ImageNet-1K and CIFAR-100.
- Score: 4.119589507611071
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Knowledge distillation is commonly employed to compress neural networks, reducing the inference costs and memory footprint. In the scenario of homogenous architecture, feature-based methods have been widely validated for their effectiveness. However, in scenarios where the teacher and student models are of heterogeneous architectures, the inherent differences in feature representation significantly degrade the performance of these methods. Recent studies have highlighted that low-frequency components constitute the majority of image features. Motivated by this, we propose a Low-Frequency Components-based Contrastive Knowledge Distillation (LFCC) framework that significantly enhances the performance of feature-based distillation between heterogeneous architectures. Specifically, we designe a set of multi-scale low-pass filters to extract the low-frequency components of intermediate features from both the teacher and student models, aligning them in a compact space to overcome architectural disparities. Moreover, leveraging the intrinsic pairing characteristic of the teacher-student framework, we design an innovative sample-level contrastive learning framework that adeptly restructures the constraints of within-sample feature similarity and between-sample feature divergence into a contrastive learning task. This strategy enables the student model to capitalize on intra-sample feature congruence while simultaneously enhancing the discrimination of features among disparate samples. Consequently, our LFCC framework accurately captures the commonalities in feature representation across heterogeneous architectures. Extensive evaluations and empirical analyses across three architectures (CNNs, Transformers, and MLPs) demonstrate that LFCC achieves superior performance on the challenging benchmarks of ImageNet-1K and CIFAR-100. All codes will be publicly available.
Related papers
- Shortcut Learning Susceptibility in Vision Classifiers [3.004632712148892]
Shortcut learning is where machine learning models exploit spurious correlations in data instead of capturing meaningful features.
This phenomenon is prevalent across various machine learning applications, including vision, natural language processing, and speech recognition.
We systematically evaluate these architectures by introducing deliberate shortcuts into the dataset that are positionally correlated with class labels.
arXiv Detail & Related papers (2025-02-13T10:25:52Z) - Feature-based One-For-All: A Universal Framework for Heterogeneous Knowledge Distillation [28.722795943076306]
Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model.
We introduce a feature-based one-for-all (FOFA) KD framework to enable feature distillation across diverse architecture.
Our framework comprises two key components. First, we design prompt tuning blocks that incorporate student feedback, allowing teacher features to adapt to the student model's learning process.
arXiv Detail & Related papers (2025-01-15T15:56:06Z) - TAS: Distilling Arbitrary Teacher and Student via a Hybrid Assistant [52.0297393822012]
We introduce an assistant model as a bridge to facilitate smooth feature knowledge transfer between heterogeneous teachers and students.
Within our proposed design principle, the assistant model combines the advantages of cross-architecture inductive biases and module functions.
Our proposed method is evaluated across some homogeneous model pairs and arbitrary heterogeneous combinations of CNNs, ViTs, spatial KDs.
arXiv Detail & Related papers (2024-10-16T08:02:49Z) - One-for-All: Bridge the Gap Between Heterogeneous Architectures in
Knowledge Distillation [69.65734716679925]
Knowledge distillation has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme.
Most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family.
We propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures.
arXiv Detail & Related papers (2023-10-30T11:13:02Z) - Enhancing Representations through Heterogeneous Self-Supervised Learning [61.40674648939691]
We propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model.
The HSSL endows the base model with new characteristics in a representation learning way without structural changes.
The HSSL is compatible with various self-supervised methods, achieving superior performances on various downstream tasks.
arXiv Detail & Related papers (2023-10-08T10:44:05Z) - Ultra Sharp : Study of Single Image Super Resolution using Residual
Dense Network [0.15229257192293202]
Single Image Super Resolution (SISR) has been an interesting and ill-posed problem in computer vision.
Traditional super-resolution imaging approaches involve, reconstruction, and learning-based methods.
This study examines the Residual Dense Networks architecture proposed by Yhang et al.
arXiv Detail & Related papers (2023-04-21T10:32:24Z) - Spatio-Temporal Representation Factorization for Video-based Person
Re-Identification [55.01276167336187]
We propose Spatio-Temporal Representation Factorization module (STRF) for re-ID.
STRF is a flexible new computational unit that can be used in conjunction with most existing 3D convolutional neural network architectures for re-ID.
We empirically show that STRF improves performance of various existing baseline architectures while demonstrating new state-of-the-art results.
arXiv Detail & Related papers (2021-07-25T19:29:37Z) - Hierarchical Deep CNN Feature Set-Based Representation Learning for
Robust Cross-Resolution Face Recognition [59.29808528182607]
Cross-resolution face recognition (CRFR) is important in intelligent surveillance and biometric forensics.
Existing shallow learning-based and deep learning-based methods focus on mapping the HR-LR face pairs into a joint feature space.
In this study, we desire to fully exploit the multi-level deep convolutional neural network (CNN) feature set for robust CRFR.
arXiv Detail & Related papers (2021-03-25T14:03:42Z) - Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model.
The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
arXiv Detail & Related papers (2020-07-30T05:48:48Z)
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.