Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models

2024-02-06 · Jianyuan Guo, Hanting Chen, Chengcheng Wang, Kai Han, Chang Xu, Yunhe Wang

Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating and optimizing these abilities, which is called superalignment. In this context, our paper delves into the realm of vision foundation models, focusing on the concept of weak-to-strong generalization, which involves using a weaker model to supervise a stronger one, aiming to enhance the latter's capabilities beyond the former's limits. We introduce a novel and adaptively adjustable loss function for weak-to-strong supervision. Our comprehensive experiments span various scenarios, including few-shot learning, transfer learning, noisy label learning, and common knowledge distillation settings. The results are striking: our approach not only exceeds the performance benchmarks set by strong-to-strong generalization but also surpasses the outcomes of fine-tuning strong models with whole datasets. This compelling evidence underscores the significant potential of weak-to-strong generalization, showcasing its capability to substantially elevate the performance of vision foundation models. The code is available at https://github.com/ggjy/vision_weak_to_strong.

📄 PDF Abstract BibTeX arXiv:2402.03749

Code (1)

ggjy/vision_weak_to_strong 공식 구현 pytorch

Tasks

Few-Shot Learning Knowledge Distillation Transfer Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning

2024-02-01 · Jitao Sang, Yuhang Wang, Jing Zhang, Yanxu Zhu 외

This paper presents a follow-up study to OpenAI's recent superalignment work on Weak-to-Strong Generalization (W2SG). Superalignment focuses on ensuring that high-level AI systems remain consistent with human values and …

Ensemble Learning In-Context Learning

Selective Weak-to-Strong Generalization

2025-11-18 · Hao Lang, Fei Huang, Yongbin Li arxiv

Future superhuman models will surpass the ability of humans and humans will only be able to \textit{weakly} supervise superhuman models. To alleviate the issue of lacking high-quality data for model alignment, some works…

Bayesian WeakS-to-Strong from Text Classification to Generation

2024-05-24 · Ziyun Cui, Ziyang Zhang, Wen Wu, Guangzhi Sun 외

Advances in large language models raise the question of how alignment techniques will adapt as models become increasingly complex and humans will only be able to supervise them weakly. Weak-to-Strong mimics such a scenar…

text-classification Text Classification Text Generation

Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization

2024-06-17 · Wenkai Yang, Shiqi Shen, Guangyao Shen, Wei Yao 외

Superalignment, where humans act as weak supervisors for superhuman models, has become a crucial problem with the rapid development of Large Language Models (LLMs). Recent work has preliminarily studied this problem by u…

The Superalignment of Superhuman Intelligence with Large Language Models

2024-12-15 · Minlie Huang, Yingkang Wang, Shiyao Cui, Pei Ke 외

We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical que…