Self-Distillation from the Last Mini-Batch for Consistency
Regularization
- URL: http://arxiv.org/abs/2203.16172v1
- Date: Wed, 30 Mar 2022 09:50:24 GMT
- Title: Self-Distillation from the Last Mini-Batch for Consistency
Regularization
- Authors: Yiqing Shen, Liwu Xu, Yuzhe Yang, Yaqian Li, Yandong Guo
- Abstract summary: We propose an efficient and reliable self-distillation framework, named Self-Distillation from Last Mini-Batch (DLB)
Our proposed mechanism guides the training stability and consistency, resulting in robustness to label noise.
Experimental results on three classification benchmarks illustrate that our approach can consistently outperform state-of-the-art self-distillation approaches.
- Score: 14.388479145440636
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Knowledge distillation (KD) shows a bright promise as a powerful
regularization strategy to boost generalization ability by leveraging learned
sample-level soft targets. Yet, employing a complex pre-trained teacher network
or an ensemble of peer students in existing KD is both time-consuming and
computationally costly. Various self KD methods have been proposed to achieve
higher distillation efficiency. However, they either require extra network
architecture modification or are difficult to parallelize. To cope with these
challenges, we propose an efficient and reliable self-distillation framework,
named Self-Distillation from Last Mini-Batch (DLB). Specifically, we rearrange
the sequential sampling by constraining half of each mini-batch coinciding with
the previous iteration. Meanwhile, the rest half will coincide with the
upcoming iteration. Afterwards, the former half mini-batch distills on-the-fly
soft targets generated in the previous iteration. Our proposed mechanism guides
the training stability and consistency, resulting in robustness to label noise.
Moreover, our method is easy to implement, without taking up extra run-time
memory or requiring model structure modification. Experimental results on three
classification benchmarks illustrate that our approach can consistently
outperform state-of-the-art self-distillation approaches with different network
architectures. Additionally, our method shows strong compatibility with
augmentation strategies by gaining additional performance improvement. The code
is available at https://github.com/Meta-knowledge-Lab/DLB.
Related papers
- Densely Distilling Cumulative Knowledge for Continual Learning [14.343655566551213]
Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting.
We propose Dense Knowledge Distillation (DKD) to distill the cumulative knowledge of all the previous tasks.
Our DKD outperforms recent state-of-the-art baselines across diverse benchmarks and scenarios.
arXiv Detail & Related papers (2024-05-16T05:37:06Z) - Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple
Logits Retargeting Approach [102.0769560460338]
We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class.
Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
arXiv Detail & Related papers (2024-03-01T03:27:08Z) - BOOT: Data-free Distillation of Denoising Diffusion Models with
Bootstrapping [64.54271680071373]
Diffusion models have demonstrated excellent potential for generating diverse images.
Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few.
We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
arXiv Detail & Related papers (2023-06-08T20:30:55Z) - DisWOT: Student Architecture Search for Distillation WithOut Training [0.0]
We explore a novel training-free framework to search for the best student architectures for a given teacher.
Our work first empirically show that the optimal model under vanilla training cannot be the winner in distillation.
Our experiments on CIFAR, ImageNet and NAS-Bench-201 demonstrate that our technique achieves state-of-the-art results on different search spaces.
arXiv Detail & Related papers (2023-03-28T01:58:45Z) - FOSTER: Feature Boosting and Compression for Class-Incremental Learning [52.603520403933985]
Deep neural networks suffer from catastrophic forgetting when learning new categories.
We propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively.
arXiv Detail & Related papers (2022-04-10T11:38:33Z) - Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples.
We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment.
We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
arXiv Detail & Related papers (2022-03-23T06:24:31Z) - Two-phase Pseudo Label Densification for Self-training based Domain
Adaptation [93.03265290594278]
We propose a novel Two-phase Pseudo Label Densification framework, referred to as TPLD.
In the first phase, we use sliding window voting to propagate the confident predictions, utilizing intrinsic spatial-correlations in the images.
In the second phase, we perform a confidence-based easy-hard classification.
To ease the training process and avoid noisy predictions, we introduce the bootstrapping mechanism to the original self-training loss.
arXiv Detail & Related papers (2020-12-09T02:35:25Z) - MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down
Distillation [153.56211546576978]
In this work, we propose that better soft targets with higher compatibil-ity can be generated by using a label generator.
We can employ the meta-learning technique to optimize this label generator.
The experiments are conducted on two standard classificationbenchmarks, namely CIFAR-100 and ILSVRC2012.
arXiv Detail & Related papers (2020-08-27T13:04:27Z) - Self-Knowledge Distillation with Progressive Refinement of Targets [1.1470070927586016]
We propose a simple yet effective regularization method named progressive self-knowledge distillation (PS-KD)
PS-KD progressively distills a model's own knowledge to soften hard targets during training.
We show that PS-KD provides an effect of hard example mining by rescaling gradients according to difficulty in classifying examples.
arXiv Detail & Related papers (2020-06-22T04:06:36Z)
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.