paper-with-me

홈 › Papers

Is Large-Scale Pretraining the Secret to Good Domain Generalization?

2024-12-03 · Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis, Bryan A. Plummer, Kate Saenko

Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods combine robust features from web-scale pretrained backbones with new features learned from source data, and this has dramatically improved benchmark results. However, it remains unclear if DG finetuning methods are becoming better over time, or if improved benchmark performance is simply an artifact of stronger pre-training. Prior studies have shown that perceptual similarity to pre-training data correlates with zero-shot performance, but we find the effect limited in the DG setting. Instead, we posit that having perceptually similar data in pretraining is not enough; and that it is how well these data were learned that determines performance. This leads us to introduce the Alignment Hypothesis, which states that the final DG performance will be high if and only if alignment of image and class label text embeddings is high. Our experiments confirm the Alignment Hypothesis is true, and we use it as an analysis tool of existing DG methods evaluated on DomainBed datasets by splitting evaluation data into In-pretraining (IP) and Out-of-pretraining (OOP). We show that all evaluated DG methods struggle on DomainBed-OOP, while recent methods excel on DomainBed-IP. Put together, our findings highlight the need for DG methods which can generalize beyond pretraining alignment.

📄 PDF Abstract BibTeX arXiv:2412.02856

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

Why does my medical AI look at pictures of birds? Exploring the efficacy of transfer learning across domain boundaries

2023-06-30 · Frederic Jonske, Moon Kim, Enrico Nasca, Janis Evers 외

It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit tha…

Computed Tomography (CT)Linear evaluationTransfer Learning

Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining

2020-11-17 · Zijun Sun, Chun Fan, Xiaofei Sun, Yuxian Meng 외

The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make …

General ClassificationLanguage ModellingPseudo Labeltext-classification+1

Joint adjustment image steganography networks

2023-07-15 · Signal Processing: Image Communication 2023 7 · Le Zhang, Yao Lu, Tong Li, Guangming Lu

Image steganography aims to achieve covert communication between two partners utilizing stego images generated by hiding secret images within cover images. Existing deep image steganography methods have been rapidly deve…

Image SteganographySteganographics

Video Pretraining Advances 3D Deep Learning on Chest CT Tasks

2023-04-02 · Alexander Ke, Shih-Cheng Huang, Chloe P O'Connell, Michal Klimont 외

Pretraining on large natural image classification datasets such as ImageNet has aided model development on data-scarce 2D medical tasks. 3D medical tasks often have much less data than 2D medical tasks, prompting practit…

Deep Learningimage-classificationImage Classification

Interspecies evolutionary dynamics mediated by public goods in bacterial quorum sensing

2020-08-11

Bacterial quorum sensing is the communication that takes place between bacteria as they secrete certain molecules into the intercellular medium that later get absorbed by the secreting cells themselves and by others. Dep…