MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation

• URL: http://arxiv.org/abs/2008.12094v1
• Date: Thu, 27 Aug 2020 13:04:27 GMT
• Title: MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation
• Authors: Benlin Liu, Yongming Rao, Jiwen Lu, Jie Zhou, Cho-jui Hsieh
• Abstract summary: 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.
• Score: 153.56211546576978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge Distillation (KD) has been one of the most popu-lar methods to learn a compact model. However, it still suffers from highdemand in time and computational resources caused by sequential train-ing pipeline. Furthermore, the soft targets from deeper models do notoften serve as good cues for the shallower models due to the gap of com-patibility. In this work, we consider these two problems at the same time.Specifically, we propose that better soft targets with higher compatibil-ity can be generated by using a label generator to fuse the feature mapsfrom deeper stages in a top-down manner, and we can employ the meta-learning technique to optimize this label generator. Utilizing the softtargets learned from the intermediate feature maps of the model, we canachieve better self-boosting of the network in comparison with the state-of-the-art. The experiments are conducted on two standard classificationbenchmarks, namely CIFAR-100 and ILSVRC2012. We test various net-work architectures to show the generalizability of our MetaDistiller. Theexperiments results on two datasets strongly demonstrate the effective-ness of our method.

Related papers

• Improving Knowledge Distillation via Regularizing Feature Norm and Direction [16.98806338782858]
  Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train student by aligning its features with the teacher's, e.g., by minimizing the KL-divergence between their logits or L2 distance between their intermediate features. While it is natural to believe that better alignment of student features to the teacher better distills teacher knowledge, simply forcing this alignment does not directly contribute to the student's performance, e.g.
  arXiv  Detail & Related papers  (2023-05-26T15:05:19Z)
• Self-Distillation from the Last Mini-Batch for Consistency Regularization [14.388479145440636]
  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.
  arXiv  Detail & Related papers  (2022-03-30T09:50:24Z)
• Online Deep Learning based on Auto-Encoder [4.128388784932455]
  We propose a two-phase Online Deep Learning based on Auto-Encoder (ODLAE) Based on auto-encoder, considering reconstruction loss, we extract abstract hierarchical latent representations of instances. We devise two fusion strategies: the output-level fusion strategy, which is obtained by fusing the classification results of each hidden layer; and feature-level fusion strategy, which is leveraged self-attention mechanism to fusion every hidden layer output.
  arXiv  Detail & Related papers  (2022-01-19T02:14:57Z)
• Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models [10.941519846908697]
  We introduce a new type of teacher model for connectionist temporal classification ( CTC)-based sequence models, namely Oracle Teacher. Since the Oracle Teacher learns a more accurate CTC alignment by referring to the target information, it can provide the student with more optimal guidance. Based on a many-to-one mapping property of the CTC algorithm, we present a training strategy that can effectively prevent the trivial solution.
  arXiv  Detail & Related papers  (2021-11-05T14:14:05Z)
• Adaptive Hierarchical Similarity Metric Learning with Noisy Labels [138.41576366096137]
  We propose an Adaptive Hierarchical Similarity Metric Learning method. It considers two noise-insensitive information, textiti.e., class-wise divergence and sample-wise consistency. Our method achieves state-of-the-art performance compared with current deep metric learning approaches.
  arXiv  Detail & Related papers  (2021-10-29T02:12:18Z)
• Partner-Assisted Learning for Few-Shot Image Classification [54.66864961784989]
  Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation. In this paper, we focus on the design of training strategy to obtain an elemental representation such that the prototype of each novel class can be estimated from a few labeled samples. We propose a two-stage training scheme, which first trains a partner encoder to model pair-wise similarities and extract features serving as soft-anchors, and then trains a main encoder by aligning its outputs with soft-anchors while attempting to maximize classification performance.
  arXiv  Detail & Related papers  (2021-09-15T22:46:19Z)
• Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU [70.44344060176952]
  Intent classification is a major task in spoken language understanding (SLU) Recent works have shown that using extra data and labels can improve the OOD detection performance. This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection.
  arXiv  Detail & Related papers  (2021-06-28T08:27:38Z)
• When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
  We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
  arXiv  Detail & Related papers  (2021-05-27T13:51:42Z)
• Learning to Generate Content-Aware Dynamic Detectors [62.74209921174237]
  We introduce a newpective of designing efficient detectors, which is automatically generating sample-adaptive model architecture. We introduce a course-to-fine strat-egy tailored for object detection to guide the learning of dynamic routing. Experiments on MS-COCO dataset demonstrate that CADDet achieves 1.8 higher mAP with 10% fewer FLOPs compared with vanilla routing.
  arXiv  Detail & Related papers  (2020-12-08T08:05:20Z)

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.