DCD: Discriminative and Consistent Representation Distillation

• URL: http://arxiv.org/abs/2407.11802v3
• Date: Fri, 15 Nov 2024 14:54:58 GMT
• Title: DCD: Discriminative and Consistent Representation Distillation
• Authors: Nikolaos Giakoumoglou, Tania Stathaki,
• Abstract summary: We propose Discriminative and Consistent Distillation (DCD) to transfer knowledge from a large teacher model to a smaller student model. DCD employs a contrastive loss along with a consistency regularization to minimize the discrepancy between the distributions of teacher and student representations. We show that DCD achieves state-of-the-art performance, with the student model sometimes surpassing the teacher's accuracy.
• Score: 6.24302896438145
• License:
• Abstract: Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its application in knowledge distillation remains limited and focuses primarily on discrimination, neglecting the structural relationships captured by the teacher model. To address this limitation, we propose Discriminative and Consistent Distillation (DCD), which employs a contrastive loss along with a consistency regularization to minimize the discrepancy between the distributions of teacher and student representations. Our method introduces learnable temperature and bias parameters that adapt during training to balance these complementary objectives, replacing the fixed hyperparameters commonly used in contrastive learning approaches. Through extensive experiments on CIFAR-100 and ImageNet ILSVRC-2012, we demonstrate that DCD achieves state-of-the-art performance, with the student model sometimes surpassing the teacher's accuracy. Furthermore, we show that DCD's learned representations exhibit superior cross-dataset generalization when transferred to Tiny ImageNet and STL-10. Code is available at https://github.com/giakoumoglou/distillers.

Related papers

• Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling [81.00825302340984]
  We introduce Speculative Knowledge Distillation (SKD) to generate high-quality training data on-the-fly. In SKD, the student proposes tokens, and the teacher replaces poorly ranked ones based on its own distribution. We evaluate SKD on various text generation tasks, including translation, summarization, math, and instruction following.
  arXiv  Detail & Related papers  (2024-10-15T06:51:25Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge [17.382306203152943]
  Dynamic Guidance Adversarial Distillation (DGAD) framework tackles the challenge of differential sample importance. DGAD employs Misclassification-Aware Partitioning (MAP) to dynamically tailor the distillation focus. Error-corrective Label Swapping (ELS) corrects misclassifications of the teacher on both clean and adversarially perturbed inputs.
  arXiv  Detail & Related papers  (2024-09-03T05:52:37Z)
• Relative Difficulty Distillation for Semantic Segmentation [54.76143187709987]
  We propose a pixel-level KD paradigm for semantic segmentation named Relative Difficulty Distillation (RDD) RDD allows the teacher network to provide effective guidance on learning focus without additional optimization goals. Our research showcases that RDD can integrate with existing KD methods to improve their upper performance bound.
  arXiv  Detail & Related papers  (2024-07-04T08:08:25Z)
• Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning [3.1423836318272773]
  Knowledge distillation (KD) improves the performance of efficient and lightweight models. Most existing KD techniques rely on Kullback-Leibler (KL) divergence. We propose a Robustness-Reinforced Knowledge Distillation (R2KD) that leverages correlation distance and network pruning.
  arXiv  Detail & Related papers  (2023-11-23T11:34:48Z)
• Comparative Knowledge Distillation [102.35425896967791]
  Traditional Knowledge Distillation (KD) assumes readily available access to teacher models for frequent inference. We propose Comparative Knowledge Distillation (CKD), which encourages student models to understand the nuanced differences in a teacher model's interpretations of samples. CKD consistently outperforms state of the art data augmentation and KD techniques.
  arXiv  Detail & Related papers  (2023-11-03T21:55:33Z)
• Data Upcycling Knowledge Distillation for Image Super-Resolution [25.753554952896096]
  Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from pre-trained teacher models to compact student models. We present the Data Upcycling Knowledge Distillation (DUKD) to transfer the teacher model's knowledge to the student model through the upcycled in-domain data derived from training data.
  arXiv  Detail & Related papers  (2023-09-25T14:13:26Z)
• Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification [75.27973258196934]
  We propose a novel Categorical Relation-preserving Contrastive Knowledge Distillation (CRCKD) algorithm, which takes the commonly used mean-teacher model as the supervisor. With this regularization, the feature distribution of the student model shows higher intra-class similarity and inter-class variance. With the contribution of the CCD and CRP, our CRCKD algorithm can distill the relational knowledge more comprehensively.
  arXiv  Detail & Related papers  (2021-07-07T13:56:38Z)
• Wasserstein Contrastive Representation Distillation [114.24609306495456]
  We propose Wasserstein Contrastive Representation Distillation (WCoRD), which leverages both primal and dual forms of Wasserstein distance for knowledge distillation. The dual form is used for global knowledge transfer, yielding a contrastive learning objective that maximizes the lower bound of mutual information between the teacher and the student networks. Experiments demonstrate that the proposed WCoRD method outperforms state-of-the-art approaches on privileged information distillation, model compression and cross-modal transfer.
  arXiv  Detail & Related papers  (2020-12-15T23:43:28Z)

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.