Some like it tough: Improving model generalization via progressively increasing the training difficulty

• URL: http://arxiv.org/abs/2110.13058v1
• Date: Mon, 25 Oct 2021 15:54:21 GMT
• Title: Some like it tough: Improving model generalization via progressively increasing the training difficulty
• Abstract summary: We propose to progressively increase the training difficulty during learning a neural network model via a novel strategy. This strategy makes sure that the puts its focus in the later training stages on the more difficult samples. Experiments on several image classification problems show that mini-batch trimming is able to increase the generalization ability.
• Score: 3.04585143845864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the later training stages on the more difficult samples, which we identify as the ones with the highest loss in the current mini-batch. The strategy is very easy to integrate into an existing training pipeline and does not necessitate a change of the network model. Experiments on several image classification problems show that mini-batch trimming is able to increase the generalization ability (measured via final test error) of the trained model.

Related papers

• GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning [23.582549876926432]
  GUI-D identifies training-worthy samples by proper testing and assigns difficulty scores to guide subsequent training weights.<n>At the strategy level, we propose GUI-C$2$, which employs an area-gated coarse-to-fine refinement mechanism.<n>Our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-05-29T06:17:53Z)
• Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks [69.54774045493227]
  A drawback of adversarial training is the computational overhead introduced by the generation of adversarial examples. We propose to exploit the interior building blocks of the model to improve efficiency. Compared with previous methods, our method not only reduces the training cost but also achieves better model robustness.
  arXiv  Detail & Related papers  (2023-10-24T01:36:20Z)
• Domain Generalization via Balancing Training Difficulty and Model Capability [61.053202176230904]
  Domain generalization (DG) aims to learn domain-generalizable models from one or multiple source domains that can perform well in unseen target domains. Despite its recent progress, most existing work suffers from the misalignment between the difficulty level of training samples and the capability of contemporarily trained models. We design MoDify, a Momentum Difficulty framework that tackles the misalignment by balancing the seesaw between the model's capability and the samples' difficulties.
  arXiv  Detail & Related papers  (2023-09-02T07:09:23Z)
• Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks [55.431048995662714]
  We create a small model for a new task from the pruned models of similar tasks. We show that a few fine-tuning steps on this model suffice to produce a promising pruned-model for the new task. We develop a simple but effective ''Meta-Vote Pruning (MVP)'' method that significantly reduces the pruning iterations for a new task.
  arXiv  Detail & Related papers  (2023-01-27T06:49:47Z)
• On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training [70.82725772926949]
  Adversarial training is a popular method to robustify models against adversarial attacks. In this work, we investigate this phenomenon from the perspective of training instances. We show that the decay in generalization performance of adversarial training is a result of fitting hard adversarial instances.
  arXiv  Detail & Related papers  (2021-12-14T12:19:24Z)
• MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption [69.76837484008033]
  An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time. We combine meta-learning, self-supervision and test-time training to learn to adapt to unseen test distributions. Our approach significantly improves the state-of-the-art results on the CIFAR-10-Corrupted image classification benchmark.
  arXiv  Detail & Related papers  (2021-03-30T09:33:38Z)
• Few-Shot Image Classification via Contrastive Self-Supervised Learning [5.878021051195956]
  We propose a new paradigm of unsupervised few-shot learning to repair the deficiencies. We solve the few-shot tasks in two phases: meta-training a transferable feature extractor via contrastive self-supervised learning. Our method achieves state of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification datasets.
  arXiv  Detail & Related papers  (2020-08-23T02:24:31Z)
• Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification [62.10696018098057]
  We propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly. A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task. Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.
  arXiv  Detail & Related papers  (2020-07-13T08:49:00Z)
• Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification [8.998976678920236]
  We propose a tAsk-auGmented actIve meta-LEarning (AGILE) method to efficiently adapt Deep Neural Networks to new tasks. AGILE combines a meta-learning algorithm with a novel task augmentation technique which we use to generate an initial adaptive model. We show that the proposed task-augmented meta-learning framework can learn to classify new cell types after a single gradient step.
  arXiv  Detail & Related papers  (2020-07-09T18:03:12Z)
• Dynamic Sampling for Deep Metric Learning [7.010669841466896]
  Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. A dynamic sampling strategy is proposed to organize the training pairs in an easy-to-hard order to feed into the network. It allows the network to learn general boundaries between categories from the easy training pairs at its early stages and finalize the details of the model mainly relying on the hard training samples in the later.
  arXiv  Detail & Related papers  (2020-04-24T09:47:23Z)
• Regularizing Meta-Learning via Gradient Dropout [102.29924160341572]
  meta-learning models are prone to overfitting when there are no sufficient training tasks for the meta-learners to generalize. We introduce a simple yet effective method to alleviate the risk of overfitting for gradient-based meta-learning.
  arXiv  Detail & Related papers  (2020-04-13T10:47:02Z)
• Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning [21.3564383157159]
  Few-shot learning aims to classify unseen classes with a few training examples. We propose self-augmentation that consolidates self-mix and self-distillation. We present a local learner representation to further exploit a few training examples for unseen classes.
  arXiv  Detail & Related papers  (2020-04-01T06:39:08Z)

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.