paper-with-me

홈 › Papers

Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features

2022-03-03 · Neha Kalibhat, Kanika Narang, Hamed Firooz, Maziar Sanjabi, Soheil Feizi

Self-supervised learning (SSL) has shown impressive results in downstream classification tasks. However, there is limited work in understanding their failure modes and interpreting their learned representations. In this paper, we study the representation space of state-of-the-art self-supervised models including SimCLR, SwaV, MoCo, BYOL, DINO, SimSiam, VICReg and Barlow Twins. Without the use of class label information, we discover discriminative features that correspond to unique physical attributes in images, present mostly in correctly-classified representations. Using these features, we can compress the representation space by up to 40% without significantly affecting linear classification performance. We then propose Self-Supervised Representation Quality Score (or Q-Score), an unsupervised score that can reliably predict if a given sample is likely to be mis-classified during linear evaluation, achieving AUPRC of 91.45 on ImageNet-100 and 78.78 on ImageNet-1K. Q-Score can also be used as a regularization term on pre-trained encoders to remedy low-quality representations. Fine-tuning with Q-Score regularization can boost the linear probing accuracy of SSL models by up to 5.8% on ImageNet-100 and 3.7% on ImageNet-1K compared to their baselines. Finally, using gradient heatmaps and Salient ImageNet masks, we define a metric to quantify the interpretability of each representation. We show that discriminative features are strongly correlated to core attributes and, enhancing these features through Q-score regularization makes SSL representations more interpretable.

📄 PDF Abstract BibTeX arXiv:2203.01881

Code (0)

등록된 구현이 없습니다.

Tasks

Linear evaluationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Bitcoin Customer Service Number +1-833-534-1729 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Towards Early Prediction of Self-Supervised Speech Model Performance

2025-01-10 · Ryan Whetten, Lucas Maison, Titouan Parcollet, Marco Dinarelli 외

In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well wi…

GPUSelf-Supervised Learning

Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing

2021-09-29 · ICLR 2022 4 · Iro Laina, Yuki M Asano, Andrea Vedaldi

Self-supervised visual representation learning has attracted significant research interest. While the most common way to evaluate self-supervised representations is through transfer to various downstream tasks, we instea…

Image ClassificationRepresentation Learning

Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing

2022-09-07 · Iro Laina, Yuki M. Asano, Andrea Vedaldi

Self-supervised visual representation learning has recently attracted significant research interest. While a common way to evaluate self-supervised representations is through transfer to various downstream tasks, we inst…

Representation Learning

IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation

2024-03-18 · IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024 3 · Sonal Kumar; Anirudh Phukan, Arijit Sur

Self-supervised learning with a contrastive batch approach has become a powerful tool for representation learning in computer vision. The performance of downstream tasks is proportional to the quality of visual features …

Contrastive LearningData Augmentationimage-classificationImage Classification+5

Evaluating self-supervised echocardiographic representations across downstream extraction strategies for left-ventricular segmentation and ejection fraction estimation

2026-06-22 · Sylwia Majchrowska, Philip Teare arxiv

Self-supervised learning (SSL) is increasingly used in medical imaging to reduce annotation requirements, but representation quality is often judged using a single downstream evaluation setting. For dense clinical tasks,…

Self-Supervised Learning