Papers › Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion

Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion

11 Aug 2021arXiv:2108.05009archive 2025-07-28

Yikai Wang, Fuchun Sun, Ming Lu, Anbang Yao

We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. The framework consists of two innovative fusion schemes. Firstly, unlike existing multimodal methods that necessitate individual encoders for different modalities, we verify that multimodal features can be learnt within a shared single network by merely maintaining modality-specific batch normalization layers in the encoder, which also enables implicit fusion via joint feature representation learning. Secondly, we propose a bidirectional multi-layer fusion scheme, where multimodal features can be exploited progressively. To take advantage of such scheme, we introduce two asymmetric fusion operations including channel shuffle and pixel shift, which learn different fused features with respect to different fusion directions. These two operations are parameter-free and strengthen the multimodal feature interactions across channels as well as enhance the spatial feature discrimination within channels. We conduct extensive experiments on semantic segmentation and image translation tasks, based on three publicly available datasets covering diverse modalities. Results indicate that our proposed framework is general, compact and is superior to state-of-the-art fusion frameworks.

PaperPDFCodeCode 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="2108.05009")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: official repository: 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yikaiw/AsymFusion officialpytorchMIT 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

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 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.

11unverified

Licence: 0 of the 11 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 yikaiw/AsymFusion. “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.

compute_params yikaiw/AsymFusion/utils/meter.py official repository unverified MIT (permissive) · f8a8c9728d1e4d18 · report
confusion_matrix yikaiw/AsymFusion/utils/meter.py official repository unverified MIT (permissive) · be06fe01faab93f9 · report
conv1x1 yikaiw/AsymFusion/models/model.py official repository unverified MIT (permissive) · ee58726ccfd1a5c8 · report
conv3x3 yikaiw/AsymFusion/models/model.py official repository unverified MIT (permissive) · 7c930e46d06bfa25 · report
getScores yikaiw/AsymFusion/utils/meter.py official repository unverified MIT (permissive) · 7cb6905948e4acb0 · report
line_to_paths_fn_nyudv2 yikaiw/AsymFusion/utils/datasets.py official repository unverified MIT (permissive) · e4fefad569c9bb5c · report
make_list yikaiw/AsymFusion/utils/transforms.py official repository unverified MIT (permissive) · b61821ce9e53818d · report
make_validation_img yikaiw/AsymFusion/utils/helpers.py official repository unverified MIT (permissive) · 14fa05652664a293 · report
maybe_download yikaiw/AsymFusion/utils/helpers.py official repository unverified MIT (permissive) · 5d35d232de98d91d · report
prepare_img yikaiw/AsymFusion/utils/helpers.py official repository unverified MIT (permissive) · 0414c633729593df · report
refinenet yikaiw/AsymFusion/models/model.py official repository unverified MIT (permissive) · 1bc30127718ac5ec · report

Tasks

Representation LearningSemantic SegmentationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation NYU Depth v2 AsymFusion (ResNet-152) Mean IoU 51.2% #54 of 121 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Batch NormalizationChannel Shuffle

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