Papers › Preserving Modality Structure Improves Multi-Modal Learning

Preserving Modality Structure Improves Multi-Modal Learning

24 Aug 2023ICCV 2023 1arXiv:2308.13077archive 2025-07-28

Swetha Sirnam, Mamshad Nayeem Rizve, Nina Shvetsova, Hilde Kuehne, Mubarak Shah

Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings in a joint multi-modal representation space without relying on human annotations. These joint embeddings enable zero-shot cross-modal tasks like retrieval and classification. However, these methods often struggle to generalize well on out-of-domain data as they ignore the semantic structure present in modality-specific embeddings. In this context, we propose a novel Semantic-Structure-Preserving Consistency approach to improve generalizability by preserving the modality-specific relationships in the joint embedding space. To capture modality-specific semantic relationships between samples, we propose to learn multiple anchors and represent the multifaceted relationship between samples with respect to their relationship with these anchors. To assign multiple anchors to each sample, we propose a novel Multi-Assignment Sinkhorn-Knopp algorithm. Our experimentation demonstrates that our proposed approach learns semantically meaningful anchors in a self-supervised manner. Furthermore, our evaluation on MSR-VTT and YouCook2 datasets demonstrates that our proposed multi-anchor assignment based solution achieves state-of-the-art performance and generalizes to both inand out-of-domain datasets. Code: https://github.com/Swetha5/Multi_Sinkhorn_Knopp

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.13077")

Code

Syntology Ran 7 of 7 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

swetha5/multi_sinkhorn_knopp officialmentioned in paperpytorch 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

7 samples harvested; 7 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran

Licence: 7 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from swetha5/multi_sinkhorn_knopp. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

calculate_cost swetha5/multi_sinkhorn_knopp/everything_at_once/loss/combinatorial_loss.py official repository ran fingerprinted no licence file found · pointer only · c2fec10380b11eb6 · report
check_nan_inf_tensor swetha5/multi_sinkhorn_knopp/everything_at_once/loss/combinatorial_loss.py official repository ran no licence file found · pointer only · da8f9ce1b17bd1ce · report
create_audio_tokens swetha5/multi_sinkhorn_knopp/everything_at_once/model/fusion_model.py official repository ran no licence file found · pointer only · 1d459a664c29e7c8 · report
librosa_samples_to_frames swetha5/multi_sinkhorn_knopp/everything_at_once/dataset/librosa_utils.py official repository ran no licence file found · pointer only · 0ae3da700ed898fc · report
librosa_time_to_frames swetha5/multi_sinkhorn_knopp/everything_at_once/dataset/librosa_utils.py official repository ran no licence file found · pointer only · b423da4cc1d0a48c · report
librosa_time_to_samples swetha5/multi_sinkhorn_knopp/everything_at_once/dataset/librosa_utils.py official repository ran fingerprinted no licence file found · pointer only · a3f6664c598dfe7b · report
replace_inf swetha5/multi_sinkhorn_knopp/everything_at_once/loss/combinatorial_loss.py official repository ran fingerprinted no licence file found · pointer only · d0155452b30b9a6d · report

Tasks

RetrievalSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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