A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation

• URL: http://arxiv.org/abs/2304.05369v1
• Date: Tue, 11 Apr 2023 17:24:29 GMT
• Title: A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation
• Authors: Florian Bordes, Samuel Lavoie, Randall Balestriero, Nicolas Ballas, Pascal Vincent
• Abstract summary: Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. We show that merely changing its dimensionality -- by changing only the size of the backbone's very last block -- is a remarkably effective technique to mitigate the pretraining bias.
• Score: 22.866948071297767
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-Supervised Learning (SSL) models rely on a pretext task to learn representations. Because this pretext task differs from the downstream tasks used to evaluate the performance of these models, there is an inherent misalignment or pretraining bias. A commonly used trick in SSL, shown to make deep networks more robust to such bias, is the addition of a small projector (usually a 2 or 3 layer multi-layer perceptron) on top of a backbone network during training. In contrast to previous work that studied the impact of the projector architecture, we here focus on a simpler, yet overlooked lever to control the information in the backbone representation. We show that merely changing its dimensionality -- by changing only the size of the backbone's very last block -- is a remarkably effective technique to mitigate the pretraining bias. It significantly improves downstream transfer performance for both Self-Supervised and Supervised pretrained models.

Related papers

• An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates [11.90029443742706]
  We study the impact of Low-Rank Adaptation (LoRA) rank on the forgetting of the pretraining foundation task and on the plasticity and forgetting of subsequent ones. We also observe that vision transformers finetuned in that way exhibit a sort of contextual'' forgetting, a behaviour that we do not observe for residual networks.
  arXiv  Detail & Related papers  (2024-05-28T11:29:25Z)
• Intra-task Mutual Attention based Vision Transformer for Few-Shot Learning [12.5354658533836]
  Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. For artificial neural network models, determining the most relevant features for distinguishing between two images with limited samples presents a challenge. We propose an intra-task mutual attention method for few-shot learning, that involves splitting the support and query samples into patches.
  arXiv  Detail & Related papers  (2024-05-06T02:02:57Z)
• Investigating the Benefits of Projection Head for Representation Learning [11.20245728716827]
  An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. The pre-projection representations are not directly optimized by the loss function, raising the question: what makes them better? We show that implicit bias of training algorithms leads to layer-wise progressive feature weighting, where features become increasingly unequal as we go deeper into the layers.
  arXiv  Detail & Related papers  (2024-03-18T00:48:58Z)
• Fine-tuning can cripple your foundation model; preserving features may be the solution [87.35911633187204]
  A fine-tuned model's ability to recognize concepts on tasks is reduced significantly compared to its pre-trained counterpart. We propose a new fine-tuning method called $textitLDIFS$ that, while learning new concepts related to the downstream task, allows a model to preserve its pre-trained knowledge as well.
  arXiv  Detail & Related papers  (2023-08-25T11:49:51Z)
• Improved Visual Fine-tuning with Natural Language Supervision [36.250244364023665]
  Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data. The problem of catastrophic forgetting in pre-trained backbone has been extensively studied for fine-tuning. We introduce a reference distribution obtained from a fixed text classifier, which can help regularize the learned vision classifier.
  arXiv  Detail & Related papers  (2023-04-04T03:08:02Z)
• EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones [80.662250618795]
  This paper presents a new curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers) As an off-the-shelf method, it reduces the wall-time training cost of a wide variety of popular models by >1.5x on ImageNet-1K/22K without sacrificing accuracy.
  arXiv  Detail & Related papers  (2022-11-17T17:38:55Z)
• Slimmable Networks for Contrastive Self-supervised Learning [67.21528544724546]
  Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. We present a one-stage solution to obtain pre-trained small models without the need for extra teachers. A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks.
  arXiv  Detail & Related papers  (2022-09-30T15:15:05Z)
• Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning [15.009986848506486]
  Guillotine Regularization (GR) is a generically applicable method that has been used to improve generalization performance in transfer learning scenarios. We identify the underlying reasons behind its success and show that the optimal layer to use might change significantly depending on the training setup, the data or the downstream task.
  arXiv  Detail & Related papers  (2022-06-27T15:37:54Z)
• Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing [76.78772372631623]
  A common practice for self-supervised pre-training is to use as much data as possible. For a specific downstream task, however, involving irrelevant data in pre-training may degenerate the downstream performance. It is burdensome and infeasible to use different downstream-task-customized datasets in pre-training for different tasks.
  arXiv  Detail & Related papers  (2022-05-26T10:49:43Z)
• Reinforcement Learning with Action-Free Pre-Training from Videos [95.25074614579646]
  We introduce a framework that learns representations useful for understanding the dynamics via generative pre-training on videos. Our framework significantly improves both final performances and sample-efficiency of vision-based reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-25T19:44:09Z)
• On Efficient Transformer and Image Pre-training for Low-level Vision [74.22436001426517]
  Pre-training has marked numerous state of the arts in high-level computer vision. We present an in-depth study of image pre-training. We find pre-training plays strikingly different roles in low-level tasks.
  arXiv  Detail & Related papers  (2021-12-19T15:50:48Z)

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.