paper-with-me

Papers

DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining

2025-09-02 · Bryan Rodas, Natalie Montesino, Jakob Ambsdorf, David Klindt, Randall Balestriero arxiv

Continued pretraining offers a promising solution for adapting foundation models to a new target domain. However, in specialized domains, available datasets are often very small, limiting the applicability of SSL methods developed for large-scale pretraining and making hyperparameter search infeasible. In addition, pretrained models are usually released as backbone-weights only, lacking important information to continue pretraining. We propose to bridge this gap with DIET-CP, a simple continued pretraining strategy, where any strong foundation model can be steered towards the new data distribution of interest. DIET-CP relies on a very simple objective, requires no labels, and introduces no more hyperparameters than supervised finetuning. It is stable across data modalities and backbone choices, while providing a significant performance boost for state-of-the-art models such as DINOv3 using only 1000 images.

📄 PDF Abstract BibTeX arXiv:2509.06990

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DIET: Lightweight Language Understanding for Dialogue Systems

2020-04-21 · Tanja Bunk, Daksh Varshneya, Vladimir Vlasov, Alan Nichol

Large-scale pre-trained language models have shown impressive results on language understanding benchmarks like GLUE and SuperGLUE, improving considerably over other pre-training methods like distributed representations …

Learning What to Predict: Downstream-Guided Task Design for Continued Pretraining

2026-01-29 · Shuqi Ke, Giulia Fanti arxiv

Continued pretraining is optimized with fixed self-supervised tasks but selected by downstream performance, creating a coarse feedback loop in which practitioners evaluate checkpoints, change data mixtures or objectives,…

Semantic SegmentationDepth Estimation

Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head

2023-02-20 · Randall Balestriero

Costly, noisy, and over-specialized, labels are to be set aside in favor of unsupervised learning if we hope to learn cheap, reliable, and transferable models. To that end, spectral embedding, self-supervised learning, o…

DecoderSelf-Supervised Learning

Clustering Egocentric Images in Passive Dietary Monitoring with Self-Supervised Learning

2022-08-25 · Jiachuan Peng, Peilun Shi, Jianing Qiu, Xinwei Ju 외

In our recent dietary assessment field studies on passive dietary monitoring in Ghana, we have collected over 250k in-the-wild images. The dataset is an ongoing effort to facilitate accurate measurement of individual foo…

ClusteringSelf-Supervised Learning

An Explainable Unsupervised-to-Supervised Machine Learning Framework for Dietary Pattern Discovery Using UK National Dietary Survey Data

2026-05-07 · Wing Yi Yu, Chun Yin Chiu arxiv

Clinical dietary assessment can generate detailed but high-dimensional nutrient and food-group information that is difficult to translate quickly into counselling priorities. This paper proposes an explainable unsupervis…