SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.02285 · CVPR · 2024

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

Jose Dolz, Ismail Ayed, Malik Boudiaf, Yunshi Huang, Fereshteh Shakeri, Houda Bahig

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.02285.json · badge: /api/ran/2404.02285.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
fereshteshakeri/fewshot-clip-strong-baseline marked official in Papers with Code
Papers with Code archive
3 ran · 2 no recorded run
FunctionStatusWhere it lives
calculate_init_alpha Ran
ran on a synthesized input
fereshteshakeri/fewshot-clip-strong-baseline/methods/linear_probe_p2.py
pointer only (licence: NONE) · get_code("125167fed5528830")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fereshteshakeri/fewshot-clip-strong-baseline when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_lr_alpha Ran
ran; our contract draft was wrong, not the code
fereshteshakeri/fewshot-clip-strong-baseline/methods/linear_probe_p2.py
pointer only (licence: NONE) · get_code("48942a689e418355")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fereshteshakeri/fewshot-clip-strong-baseline when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_lr_w Ran
ran; our contract draft was wrong, not the code
fereshteshakeri/fewshot-clip-strong-baseline/methods/linear_probe_p2.py
pointer only (licence: NONE) · get_code("662226092e740295")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fereshteshakeri/fewshot-clip-strong-baseline when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

FSCLIPmethod Not yet run
unverified (harvested, no recorded run)
fereshteshakeri/fewshot-clip-strong-baseline/methods/linear_probe_p2.py
pointer only (licence: NONE) · get_code("24f6f1cb251562bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fereshteshakeri/fewshot-clip-strong-baseline when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LinearProbe_P2 Not yet run
unverified (harvested, no recorded run)
fereshteshakeri/fewshot-clip-strong-baseline/methods/linear_probe_p2.py
pointer only (licence: NONE) · get_code("b74ce93f84e80112")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fereshteshakeri/fewshot-clip-strong-baseline when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 imagelanguage 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 fewshot CLIP adaptation methods. Our code is available at: https://github.com/FereshteShakeri/ FewShot-CLIP-Strong-Baseline.git.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.02285")
get_code_for_paper("2404.02285")
have("2404.02285")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.02285.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.02285.svg)](https://syntology.ai/paper/2404.02285)

Connect an agent — have() is free.