paper-with-me

Papers

Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)

2022-05-03 · Alex Fang, Gabriel Ilharco, Mitchell Wortsman, Yuhao Wan, Vaishaal Shankar, Achal Dave, Ludwig Schmidt

Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts. Since these language-image models differ from previous training approaches in several ways, an important question is what causes the large robustness gains. We answer this question via a systematic experimental investigation. Concretely, we study five different possible causes for the robustness gains: (i) the training set size, (ii) the training distribution, (iii) language supervision at training time, (iv) language supervision at test time, and (v) the contrastive loss function. Our experiments show that the more diverse training distribution is the main cause for the robustness gains, with the other factors contributing little to no robustness. Beyond our experimental results, we also introduce ImageNet-Captions, a version of ImageNet with original text annotations from Flickr, to enable further controlled experiments of language-image training.

📄 PDF Abstract BibTeX arXiv:2205.01397

Code (2)

mlfoundations/imagenet-captions 공식 구현
filipbasara0/simple-clip pytorch

Tasks

Image Classification

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization

2024-11-21 · Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Min Zhang 외

Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degra…

Language ModelingLanguage ModellingLarge Language Model

Exploring The Landscape of Distributional Robustness for Question Answering Models

2022-10-22 · Anas Awadalla, Mitchell Wortsman, Gabriel Ilharco, Sewon Min 외

We conduct a large empirical evaluation to investigate the landscape of distributional robustness in question answering. Our investigation spans over 350 models and 16 question answering datasets, including a diverse set…

In-Context LearningQuestion Answering

Is Self-Supervised Learning More Robust Than Supervised Learning?

2022-06-10 · Yuanyi Zhong, Haoran Tang, Junkun Chen, Jian Peng 외

Self-supervised contrastive learning is a powerful tool to learn visual representation without labels. Prior work has primarily focused on evaluating the recognition accuracy of various pre-training algorithms, but has o…

Contrastive LearningData AugmentationSelf-Supervised Learning

CyCLIP: Cyclic Contrastive Language-Image Pretraining

2022-05-28 · Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan A. Rossi 외

Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness. Suc…

Representation LearningVisual Reasoningzero-shot-classificationZero-Shot Learning

Cross-modality debiasing: using language to mitigate sub-population shifts in imaging

2024-02-02 · Yijiang Pang, Bao Hoang, Jiayu Zhou

Sub-population shift is a specific type of domain shift that highlights changes in data distribution within specific sub-groups or populations between training and testing. Sub-population shift accounts for a significant…

Language ModelingLanguage Modelling