paper-with-me

홈 › Papers

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

2019-10-01 · arXiv 2020 2 · Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, Lucas Beyer, Olivier Bachem, Michael Tschannen, Marcin Michalski, Olivier Bousquet, Sylvain Gelly, Neil Houlsby

Representation learning promises to unlock deep learning for the long tail of vision tasks without expensive labelled datasets. Yet, the absence of a unified evaluation for general visual representations hinders progress. Popular protocols are often too constrained (linear classification), limited in diversity (ImageNet, CIFAR, Pascal-VOC), or only weakly related to representation quality (ELBO, reconstruction error). We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples. With VTAB, we conduct a large-scale study of many popular publicly-available representation learning algorithms. We carefully control confounders such as architecture and tuning budget. We address questions like: How effective are ImageNet representations beyond standard natural datasets? How do representations trained via generative and discriminative models compare? To what extent can self-supervision replace labels? And, how close are we to general visual representations?

📄 PDF Abstract BibTeX arXiv:1910.04867

Code (2)

google-research/task_adaptation 공식 구현 tf
facebookresearch/vissl pytorch

Tasks

DiversityImage ClassificationRepresentation Learning

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Residual Connection 설명 없음
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…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations

2021-08-12 · Josh Beal, Hao-Yu Wu, Dong Huk Park, Andrew Zhai 외

Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems…

Image ClassificationMulti-Task LearningRepresentation LearningRetrieval

Revisiting Self-Supervised Visual Representation Learning

2019-01-25 · CVPR 2019 6 · Alexander Kolesnikov, Xiaohua Zhai, Lucas Beyer

Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of…

Representation LearningSelf-Supervised Image ClassificationSelf-Supervised Learning

ScaleNet: An Unsupervised Representation Learning Method for Limited Information

2023-10-03 · Huili Huang, M. Mahdi Roozbahani

Although large-scale labeled data are essential for deep convolutional neural networks (ConvNets) to learn high-level semantic visual representations, it is time-consuming and impractical to collect and annotate large-sc…

Representation Learning

What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?

2023-10-03 · Sneha Silwal, Karmesh Yadav, Tingfan Wu, Jay Vakil 외

We present a large empirical investigation on the use of pre-trained visual representations (PVRs) for training downstream policies that execute real-world tasks. Our study involves five different PVRs, each trained for …

Data Augmentation

Learning to Navigate Using Mid-Level Visual Priors

2019-12-23 · Alexander Sax, Jeffrey O. Zhang, Bradley Emi, Amir Zamir 외

How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utili…

Navigatereinforcement-learningReinforcement LearningReinforcement Learning (RL)+1