Papers › ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models

ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models

1 Jul 2023ICCV 2023 1arXiv:2307.00398archive 2025-07-28

Uddeshya Upadhyay, Shyamgopal Karthik, Massimiliano Mancini, Zeynep Akata

Large-scale vision-language models (VLMs) like CLIP successfully find correspondences between images and text. Through the standard deterministic mapping process, an image or a text sample is mapped to a single vector in the embedding space. This is problematic: as multiple samples (images or text) can abstract the same concept in the physical world, deterministic embeddings do not reflect the inherent ambiguity in the embedding space. We propose ProbVLM, a probabilistic adapter that estimates probability distributions for the embeddings of pre-trained VLMs via inter/intra-modal alignment in a post-hoc manner without needing large-scale datasets or computing. On four challenging datasets, i.e., COCO, Flickr, CUB, and Oxford-flowers, we estimate the multi-modal embedding uncertainties for two VLMs, i.e., CLIP and BLIP, quantify the calibration of embedding uncertainties in retrieval tasks and show that ProbVLM outperforms other methods. Furthermore, we propose active learning and model selection as two real-world downstream tasks for VLMs and show that the estimated uncertainty aids both tasks. Lastly, we present a novel technique for visualizing the embedding distributions using a large-scale pre-trained latent diffusion model. Code is available at https://github.com/ExplainableML/ProbVLM.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

explainableml/probvlm officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 8 ran (3 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
5ran
7unverified

Licence: 2 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from explainableml/probvlm. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

explainableml/probvlm official repository 15 samples, 8 ran (3 instrument-failed) · 7 unverified
basic_clean in 217 papers src/clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
caption_transform src/ds/_transforms.py ran MIT (permissive) · aee2e1c6decd89e9 · report fixture: signature vocab:callable/0/?, caption_drop_prob:float/0/float · returned Compose · level recorded 2026-09-26
get_pairs in 260 papers src/clip/simple_tokenizer.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
get_recall in 7 papers src/utils.py ran MIT (permissive) · 9e65d0d94b1c84fe · report fixture: signature pred_ranks_all:ndarray/2/int, recall_ks:tuple/1/int, n_gallery_per_query:int/0/int · returned list · level recorded 2026-09-26
image_to_caption_collate_fn src/ds/_dataloader.py ran MIT (permissive) · 9e22cc211ad25fe0 · report fixture: signature data:list/1/tuple · returned tuple · level recorded 2026-09-26
imagenet_transform src/ds/_transforms.py ran MIT (permissive) · d245fdedffda5d4f · report fixture: signature resize_size:int/0/int, crop_size:int/0/int, random_resize_crop:bool/0/bool, random_erasing_prob:float/0/float, custom_transforms:NoneType/0/? · returned Compose · level recorded 2026-09-26
imagenet_transform_fn src/ds/_dataloader.py ran MIT (permissive) · 071ac72cc5321a2e · report fixture: signature resize_size:int/0/int, crop_size:int/0/int, random_resize_crop:bool/0/bool, random_erasing_prob:float/0/float, custom_transforms:list/1/callable · returned Compose · level recorded 2026-09-26
whitespace_clean in 230 papers src/clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
build_model in 469 papers src/clip/model.py unverified MIT (permissive) · 259eff225d89cc48 · report
eval_ProbVLM src/train_probVLM.py unverified MIT (permissive) · a37694f28caa41e1 · report
eval_ProbVLM_HF src/train_probVLM.py unverified MIT (permissive) · 9c748a328db870d6 · report
get_pred_ranks src/utils.py unverified MIT (permissive) · d621259cb2503f6f · report
get_recall_COCOFLICKR src/utils.py unverified MIT (permissive) · cdb3b6f67b14988a · report
load in 392 papers src/clip/clip.py unverified MIT (permissive) · 9da6e7e7a1c0f8f6 · report
tokenize in 176 papers src/ds/_transforms.py unverified MIT (permissive) · 841979de2ba28e2f · report

Tasks

Active LearningModel SelectionRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterBLIPCLIPDiffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections