# Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models

arXiv: https://arxiv.org/abs/2505.13317 · HTML: https://mlsanity.com/paper/2505.13317/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning](https://mlsanity.com/paper/2007.08844/) (2020)
- [PromptKD: Unsupervised Prompt Distillation for Vision-Language Models](https://mlsanity.com/paper/2403.02781/) (2024)
- [Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts](https://mlsanity.com/paper/2309.10019/) (2023)
- [DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2106.05682/) (2021)
- [Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data](https://mlsanity.com/paper/2303.13664/) (2023)
- [CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2112.04564/) (2021)
- [Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning](https://mlsanity.com/paper/2306.01669/) (2023)
- [Towards Realistic Semi-Supervised Learning](https://mlsanity.com/paper/2207.02269/) (2022)
- [Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data](https://mlsanity.com/paper/2406.10502/) (2024)
- [Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning](https://mlsanity.com/paper/2312.15702/) (2023)
- [CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation](https://mlsanity.com/paper/2503.18244/) (2025)
- [Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition](https://mlsanity.com/paper/2410.06109/) (2024)

## Built on by (most cited first, 3 of 3)

- [Triple Expert Learning from Noisy Labels for Semi-Supervised Vision Foundation Model Adaptation](https://mlsanity.com/paper/2608.09052/) (2026)
- [Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models](https://mlsanity.com/paper/2510.20477/) (2025)
- [MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification](https://mlsanity.com/paper/2608.13463/) (2026)

## Abstract (arXiv)

Semi-supervised learning (SSL) alleviates the cost of data labeling process by exploiting unlabeled data and has achieved promising results. Meanwhile, with the development of large foundation models, exploiting pre-trained models becomes a promising way to address the label scarcity in the downstream tasks, such as various parameter-efficient fine-tuning techniques. This raises a natural yet critical question: When labeled data is limited, should we rely on unlabeled data or pre-trained models? To investigate this issue, we conduct a fair comparison between SSL methods and pre-trained models (e.g., CLIP) on representative image classification tasks under a controlled supervision budget. Experiments reveal that SSL has met its ``Waterloo" in the era of large models, as pre-trained models show both high efficiency and strong performance on widely adopted SSL benchmarks. This underscores the urgent need for SSL researchers to explore new avenues, such as deeper integration between the SSL and pre-trained models. Furthermore, we investigate the potential of Multi-Modal Large Language Models (MLLMs) in image classification tasks. Results show that, despite their massive parameter scales, MLLMs still face significant performance limitations, highlighting that even a seemingly well-studied task remains highly challenging.