Using Human Perception to Regularize Transfer Learning

• URL: http://arxiv.org/abs/2211.07885v1
• Date: Tue, 15 Nov 2022 04:18:43 GMT
• Title: Using Human Perception to Regularize Transfer Learning
• Authors: Justin Dulay, Walter J. Scheirer
• Abstract summary: Recent trends in the machine learning community show that models with fidelity toward human perceptual measurements perform strongly on vision tasks. We introduce PERCEP-TL, a methodology for improving transfer learning with the regularization power of psychophysical labels in models. We find that models with high behavioral fidelity -- including vision transformers -- improve the most from this regularization by as much as 1.9% Top@1 accuracy points.
• Score: 12.916638258156953
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recent trends in the machine learning community show that models with fidelity toward human perceptual measurements perform strongly on vision tasks. Likewise, human behavioral measurements have been used to regularize model performance. But can we transfer latent knowledge gained from this across different learning objectives? In this work, we introduce PERCEP-TL (Perceptual Transfer Learning), a methodology for improving transfer learning with the regularization power of psychophysical labels in models. We demonstrate which models are affected the most by perceptual transfer learning and find that models with high behavioral fidelity -- including vision transformers -- improve the most from this regularization by as much as 1.9\% Top@1 accuracy points. These findings suggest that biologically inspired learning agents can benefit from human behavioral measurements as regularizers and psychophysical learned representations can be transferred to independent evaluation tasks.

Related papers

• L-WISE: Boosting Human Image Category Learning Through Model-Based Image Selection And Enhancement [12.524893323311108]
  We propose to augment visual learning in humans in a way that improves human categorization accuracy at test time. Our learning augmentation approach consists of selecting images based on their model-estimated recognition difficulty, and (ii) using image perturbations that aid recognition for novice learners. To the best of our knowledge, this is the first application of ANNs to increase visual learning performance in humans by enhancing category-specific features.
  arXiv  Detail & Related papers  (2024-12-12T23:57:01Z)
• Reciprocal Learning of Intent Inferral with Augmented Visual Feedback for Stroke [2.303526979876375]
  We propose a bidirectional paradigm that facilitates human adaptation to an intent inferral classifier. We demonstrate this paradigm in the context of controlling a robotic hand orthosis for stroke. Our experiments with stroke subjects show reciprocal learning improving performance in a subset of subjects without negatively impacting performance on the others.
  arXiv  Detail & Related papers  (2024-12-10T22:49:36Z)
• The Role of Higher-Order Cognitive Models in Active Learning [8.847360368647752]
  We advocate for a new paradigm for active learning for human feedback. We discuss how increasing level of agency results in qualitatively different forms of rational communication between an active learning system and a teacher.
  arXiv  Detail & Related papers  (2024-01-09T07:39:36Z)
• Benchmarking Continual Learning from Cognitive Perspectives [14.867136605254975]
  Continual learning addresses the problem of continuously acquiring and transferring knowledge without catastrophic forgetting of old concepts. There is a mismatch between cognitive properties and evaluation methods of continual learning models. We propose to integrate model cognitive capacities and evaluation metrics into a unified evaluation paradigm.
  arXiv  Detail & Related papers  (2023-12-06T06:27:27Z)
• Exploring Model Transferability through the Lens of Potential Energy [78.60851825944212]
  Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. Existing methods for measuring the transferability of pre-trained models rely on statistical correlations between encoded static features and task labels. We present an insightful physics-inspired approach named PED to address these challenges.
  arXiv  Detail & Related papers  (2023-08-29T07:15:57Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)
• Learning Theory of Mind via Dynamic Traits Attribution [59.9781556714202]
  We propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories. This trait vector then multiplicatively modulates the prediction mechanism via a fast weights' scheme in the prediction neural network. We empirically show that the fast weights provide a good inductive bias to model the character traits of agents and hence improves mindreading ability.
  arXiv  Detail & Related papers  (2022-04-17T11:21:18Z)
• Performance or Trust? Why Not Both. Deep AUC Maximization with Self-Supervised Learning for COVID-19 Chest X-ray Classifications [72.52228843498193]
  In training deep learning models, a compromise often must be made between performance and trust. In this work, we integrate a new surrogate loss with self-supervised learning for computer-aided screening of COVID-19 patients.
  arXiv  Detail & Related papers  (2021-12-14T21:16:52Z)
• Visual Adversarial Imitation Learning using Variational Models [60.69745540036375]
  Reward function specification remains a major impediment for learning behaviors through deep reinforcement learning. Visual demonstrations of desired behaviors often presents an easier and more natural way to teach agents. We develop a variational model-based adversarial imitation learning algorithm.
  arXiv  Detail & Related papers  (2021-07-16T00:15:18Z)
• Learning to See before Learning to Act: Visual Pre-training for Manipulation [48.731528716324355]
  We find that pre-training on vision tasks significantly improves generalization and sample efficiency for learning to manipulate objects. We explore directly transferring model parameters from vision networks to affordance prediction networks, and show that this can result in successful zero-shot adaptation. With just a small amount of robotic experience, we can further fine-tune the affordance model to achieve better results.
  arXiv  Detail & Related papers  (2021-07-01T17:58:37Z)
• Inter- and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition [2.320417845168326]
  Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models. The technique of pre-training on one task and then retraining on a new one is called transfer learning. In this paper we analyse the effectiveness of using deep transfer learning for character recognition tasks.
  arXiv  Detail & Related papers  (2020-01-02T14:18:25Z)

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.