Rethinking Evaluation Protocols of Visual Representations Learned via Self-supervised Learning

• URL: http://arxiv.org/abs/2304.03456v1
• Date: Fri, 7 Apr 2023 03:03:19 GMT
• Title: Rethinking Evaluation Protocols of Visual Representations Learned via Self-supervised Learning
• Authors: Jae-Hun Lee, Doyoung Yoon, ByeongMoon Ji, Kyungyul Kim, Sangheum Hwang
• Abstract summary: Self-supervised learning (SSL) is used to evaluate the quality of visual representations learned via self-supervised learning (SSL) Existing SSL methods have shown good performances under those evaluation protocols. We try to figure out the cause of performance sensitivity by conducting extensive experiments with state-of-the-art SSL methods.
• Score: 1.0499611180329804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Linear probing (LP) (and $k$-NN) on the upstream dataset with labels (e.g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate the quality of visual representations learned via self-supervised learning (SSL). Although existing SSL methods have shown good performances under those evaluation protocols, we observe that the performances are very sensitive to the hyperparameters involved in LP and TL. We argue that this is an undesirable behavior since truly generic representations should be easily adapted to any other visual recognition task, i.e., the learned representations should be robust to the settings of LP and TL hyperparameters. In this work, we try to figure out the cause of performance sensitivity by conducting extensive experiments with state-of-the-art SSL methods. First, we find that input normalization for LP is crucial to eliminate performance variations according to the hyperparameters. Specifically, batch normalization before feeding inputs to a linear classifier considerably improves the stability of evaluation, and also resolves inconsistency of $k$-NN and LP metrics. Second, for TL, we demonstrate that a weight decay parameter in SSL significantly affects the transferability of learned representations, which cannot be identified by LP or $k$-NN evaluations on the upstream dataset. We believe that the findings of this study will be beneficial for the community by drawing attention to the shortcomings in the current SSL evaluation schemes and underscoring the need to reconsider them.

Related papers

• A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification [51.35500308126506]
  Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. We study how classification-based evaluation protocols for SSL correlate and how well they predict downstream performance on different dataset types.
  arXiv  Detail & Related papers  (2024-07-16T23:17:36Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Boosting Transformer's Robustness and Efficacy in PPG Signal Artifact Detection with Self-Supervised Learning [0.0]
  This study addresses the underutilization of abundant unlabeled data by employing self-supervised learning (SSL) to extract latent features from this data. Our experiments demonstrate that SSL significantly enhances the Transformer model's ability to learn representations. This approach holds promise for broader applications in PICU environments, where annotated data is often limited.
  arXiv  Detail & Related papers  (2024-01-02T04:00:48Z)
• Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling [26.444935219428036]
  Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. In real-world settings, spurious correlations between some attributes (e.g. race, gender and age) and labels for downstream tasks often exist. We propose a learning-speed aware SSL (LA-SSL) approach, in which we sample each training data with a probability that is inversely related to its learning speed.
  arXiv  Detail & Related papers  (2023-11-27T22:52:45Z)
• An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization [52.44068740462729]
  We present an information-theoretic perspective on the VICReg objective. We derive a generalization bound for VICReg, revealing its inherent advantages for downstream tasks. We introduce a family of SSL methods derived from information-theoretic principles that outperform existing SSL techniques.
  arXiv  Detail & Related papers  (2023-03-01T16:36:25Z)
• Benchmark for Uncertainty & Robustness in Self-Supervised Learning [0.0]
  Self-Supervised Learning is crucial for real-world applications, especially in data-hungry domains such as healthcare and self-driving cars. In this paper, we explore variants of SSL methods, including Jigsaw Puzzles, Context, Rotation, Geometric Transformations Prediction for vision, as well as BERT and GPT for language tasks. Our goal is to create a benchmark with outputs from experiments, providing a starting point for new SSL methods in Reliable Machine Learning.
  arXiv  Detail & Related papers  (2022-12-23T15:46:23Z)
• Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability [3.8036939971290007]
  We propose a Self-Supervised Learning (SSL) method with a pretext task of signal reconstruction to learn an informative generalized PPG representation. Results show that in a very limited label data setting (10 samples per class or less), using SSL is beneficial. SSL may pave the way for the broader use of machine learning models on PPG data in label-scarce regimes.
  arXiv  Detail & Related papers  (2022-12-07T19:02:45Z)
• Improving Self-Supervised Learning by Characterizing Idealized Representations [155.1457170539049]
  We prove necessary and sufficient conditions for any task invariant to given data augmentations. For contrastive learning, our framework prescribes simple but significant improvements to previous methods. For non-contrastive learning, we use our framework to derive a simple and novel objective.
  arXiv  Detail & Related papers  (2022-09-13T18:01:03Z)
• Self-supervised Learning is More Robust to Dataset Imbalance [65.84339596595383]
  We investigate self-supervised learning under dataset imbalance. Off-the-shelf self-supervised representations are already more robust to class imbalance than supervised representations. We devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets.
  arXiv  Detail & Related papers  (2021-10-11T06:29:56Z)
• Prototypical Contrastive Learning of Unsupervised Representations [171.3046900127166]
  Prototypical Contrastive Learning (PCL) is an unsupervised representation learning method. PCL implicitly encodes semantic structures of the data into the learned embedding space. PCL outperforms state-of-the-art instance-wise contrastive learning methods on multiple benchmarks.
  arXiv  Detail & Related papers  (2020-05-11T09:53:36Z)

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.