Towards Inadequately Pre-trained Models in Transfer Learning

• URL: http://arxiv.org/abs/2203.04668v3
• Date: Thu, 17 Aug 2023 03:27:39 GMT
• Title: Towards Inadequately Pre-trained Models in Transfer Learning
• Authors: Andong Deng, Xingjian Li, Di Hu, Tianyang Wang, Haoyi Xiong, Chengzhong Xu
• Abstract summary: Better ImageNet pre-trained models have been demonstrated to have better transferability to downstream tasks. In this paper, we found that during the same pre-training process, models at middle epochs, which is inadequately pre-trained, can outperform fully trained models. Our discoveries suggest that, during pre-training, models tend to first learn spectral components corresponding to large singular values.
• Score: 37.66278189011681
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, from the perspective of architecture, by previous research to have better transferability to downstream tasks. However, in this paper, we found that during the same pre-training process, models at middle epochs, which is inadequately pre-trained, can outperform fully trained models when used as feature extractors (FE), while the fine-tuning (FT) performance still grows with the source performance. This reveals that there is not a solid positive correlation between top-1 accuracy on ImageNet and the transferring result on target data. Based on the contradictory phenomenon between FE and FT that better feature extractor fails to be fine-tuned better accordingly, we conduct comprehensive analyses on features before softmax layer to provide insightful explanations. Our discoveries suggest that, during pre-training, models tend to first learn spectral components corresponding to large singular values and the residual components contribute more when fine-tuning.

Related papers

• ImageNet-RIB Benchmark: Large Pre-Training Datasets Don't Guarantee Robustness after Fine-Tuning [30.422932548359952]
  We introduce a new robust fine-tuning benchmark, ImageNet-RIB (Robustness Inheritance Benchmark) The benchmark consists of related but distinct specialized (downstream) tasks. We find that the continual learning methods, EWC and LwF maintain robustness after fine-tuning.
  arXiv  Detail & Related papers  (2024-10-28T22:33:22Z)
• Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models [17.288865972774587]
  We investigate the relationship between pre-training and fine-tuning by fine-tuning multiple intermediate pre-trained model checkpoints. Our results on 18 datasets suggest that pre-training improves the model in a latent way that unveils after fine-tuning.
  arXiv  Detail & Related papers  (2024-08-13T06:28:43Z)
• Learning with Noisy Foundation Models [95.50968225050012]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets. We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• An Emulator for Fine-Tuning Large Language Models using Small Language Models [91.02498576056057]
  We introduce emulated fine-tuning (EFT), a principled and practical method for sampling from a distribution that approximates the result of pre-training and fine-tuning at different scales. We show that EFT enables test-time adjustment of competing behavioral traits like helpfulness and harmlessness without additional training. Finally, a special case of emulated fine-tuning, which we call LM up-scaling, avoids resource-intensive fine-tuning of large pre-trained models by ensembling them with small fine-tuned models.
  arXiv  Detail & Related papers  (2023-10-19T17:57:16Z)
• Examining the Effect of Pre-training on Time Series Classification [21.38211396933795]
  This study investigates the impact of pre-training followed by fine-tuning on the fine-tuning process. We conducted a thorough examination of 150 classification datasets. We find that pre-training can only help improve the optimization process for models that fit the data poorly. Adding more pre-training data does not improve generalization, but it can strengthen the advantage of pre-training on the original data volume.
  arXiv  Detail & Related papers  (2023-09-11T06:26:57Z)
• How Well Do Sparse Imagenet Models Transfer? [75.98123173154605]
  Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" datasets. In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset. We show that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities.
  arXiv  Detail & Related papers  (2021-11-26T11:58:51Z)
• Improved Fine-tuning by Leveraging Pre-training Data: Theory and Practice [52.11183787786718]
  Fine-tuning a pre-trained model on the target data is widely used in many deep learning applications. Recent studies have empirically shown that training from scratch has the final performance that is no worse than this pre-training strategy. We propose a novel selection strategy to select a subset from pre-training data to help improve the generalization on the target task.
  arXiv  Detail & Related papers  (2021-11-24T06:18:32Z)
• End-to-End Weak Supervision [15.125993628007972]
  We propose an end-to-end approach for directly learning the downstream model. We show improved performance over prior work in terms of end model performance on downstream test sets.
  arXiv  Detail & Related papers  (2021-07-05T19:10:11Z)
• Self-Supervised Pretraining Improves Self-Supervised Pretraining [83.1423204498361]
  Self-supervised pretraining requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. This paper explores Hierarchical PreTraining (HPT), which decreases convergence time and improves accuracy by initializing the pretraining process with an existing pretrained model. We show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pretraining data.
  arXiv  Detail & Related papers  (2021-03-23T17:37:51Z)
• Do Adversarially Robust ImageNet Models Transfer Better? [102.09335596483695]
  adversarially robust models often perform better than their standard-trained counterparts when used for transfer learning. Our results are consistent with (and in fact, add to) recent hypotheses stating that robustness leads to improved feature representations.
  arXiv  Detail & Related papers  (2020-07-16T17:42:40Z)

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.