# LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP

arXiv: https://arxiv.org/abs/2404.02285 · HTML: https://mlsanity.com/paper/2404.02285/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Placed in Interpreting vision and multimodal models, one of 13 directions in Mechanistic interpretability.
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Placed in

- Mechanistic interpretability / [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/)

## Builds on (most cited first, 16 of 16)

- [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)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [PLOT: Prompt Learning with Optimal Transport for Vision-Language Models](https://mlsanity.com/paper/2210.01253/) (2022)
- [Iteration Complexity Analysis of Block Coordinate Descent Methods](https://mlsanity.com/paper/1310.6957/) (2013)
- [Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models](https://mlsanity.com/paper/2310.13998/) (2023)

## Built on by (most cited first, 30 of 60)

- [Knowledge Composition using Task Vectors with Learned Anisotropic Scaling](https://mlsanity.com/paper/2407.02880/) (2024)
- [BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models](https://mlsanity.com/paper/2411.15232/) (2024)
- [Few-shot Adaptation of Medical Vision-Language Models](https://mlsanity.com/paper/2409.03868/) (2024)
- [Conformal Prediction for Zero-Shot Models](https://mlsanity.com/paper/2505.24693/) (2025)
- [Are foundation models for computer vision good conformal predictors?](https://mlsanity.com/paper/2412.06082/) (2024)
- [ProAPO: Progressively Automatic Prompt Optimization for Visual Classification](https://mlsanity.com/paper/2502.19844/) (2025)
- [Logits DeConfusion with CLIP for Few-Shot Learning](https://mlsanity.com/paper/2504.12104/) (2025)
- [Full Conformal Adaptation of Medical Vision-Language Models](https://mlsanity.com/paper/2506.06076/) (2025)
- [Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction](https://mlsanity.com/paper/2506.17503/) (2025)
- [Approximate Domain Unlearning for Vision-Language Models](https://mlsanity.com/paper/2510.08132/) (2025)
- [ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map](https://mlsanity.com/paper/2407.12315/) (2024)
- [Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation](https://mlsanity.com/paper/2506.17500/) (2025)
- [Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP](https://mlsanity.com/paper/2412.11375/) (2024)
- [A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis](https://mlsanity.com/paper/2503.11101/) (2025)
- [Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2503.22984/) (2025)
- [UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation](https://mlsanity.com/paper/2506.19694/) (2025)
- [MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation](https://mlsanity.com/paper/2602.21397/) (2026)
- [Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2603.05235/) (2026)
- [FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation](https://mlsanity.com/paper/2504.10487/) (2025)
- [FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition](https://mlsanity.com/paper/2505.21571/) (2025)
- [On the rankability of visual embeddings](https://mlsanity.com/paper/2507.03683/) (2025)
- [Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning](https://mlsanity.com/paper/2603.13341/) (2026)
- [Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment](https://mlsanity.com/paper/2603.17655/) (2026)
- [CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values](https://mlsanity.com/paper/2509.03740/) (2025)
- [vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs](https://mlsanity.com/paper/2511.09540/) (2025)
- [IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment](https://mlsanity.com/paper/2603.19862/) (2026)
- [Towards Generative Class Prompt Learning for Fine-grained Visual Recognition](https://mlsanity.com/paper/2409.01835/) (2024)
- [Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning](https://mlsanity.com/paper/2508.03102/) (2025)
- [LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs](https://mlsanity.com/paper/2602.17535/) (2026)
- [CLIP's Visual Embedding Projector is a Few-shot Cornucopia](https://mlsanity.com/paper/2410.05270/) (2024)

## Abstract (arXiv)

In a recent, strongly emergent literature on few-shot CLIP adaptation, Linear Probe (LP) has been often reported as a weak baseline. This has motivated intensive research building convoluted prompt learning or feature adaptation strategies. In this work, we propose and examine from convex-optimization perspectives a generalization of the standard LP baseline, in which the linear classifier weights are learnable functions of the text embedding, with class-wise multipliers blending image and text knowledge. As our objective function depends on two types of variables, i.e., the class visual prototypes and the learnable blending parameters, we propose a computationally efficient block coordinate Majorize-Minimize (MM) descent algorithm. In our full-batch MM optimizer, which we coin LP++, step sizes are implicit, unlike standard gradient descent practices where learning rates are intensively searched over validation sets. By examining the mathematical properties of our loss (e.g., Lipschitz gradient continuity), we build majorizing functions yielding data-driven learning rates and derive approximations of the loss's minima, which provide data-informed initialization of the variables. Our image-language objective function, along with these non-trivial optimization insights and ingredients, yields, surprisingly, highly competitive few-shot CLIP performances. Furthermore, LP++ operates in black-box, relaxes intensive validation searches for the optimization hyper-parameters, and runs orders-of-magnitudes faster than state-of-the-art few-shot CLIP adaptation methods. Our code is available at: urlhttps://github.com/FereshteShakeri/FewShot-CLIP-Strong-Baseline.git.