Papers › Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

15 Jan 2025arXiv:2501.08580archive 2025-07-28

Jiaqi Huang, Zunnan Xu, Ting Liu, Yong liu, Haonan Han, Kehong Yuan, Xiu Li

In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particularly favored for its effectiveness in large foundation models, as it streamlines transfer learning costs and optimizes hardware utilization. However, the current PET methods are mainly designed for single-modal optimization. While some pioneering studies have undertaken preliminary explorations, they still remain at the level of aligned encoders (e.g., CLIP) and lack exploration of misaligned encoders. These methods show sub-optimal performance with misaligned encoders, as they fail to effectively align the multimodal features during fine-tuning. In this paper, we introduce DETRIS, a parameter-efficient tuning framework designed to enhance low-rank visual feature propagation by establishing dense interconnections between each layer and all preceding layers, which enables effective cross-modal feature interaction and adaptation to misaligned encoders. We also suggest using text adapters to improve textual features. Our simple yet efficient approach greatly surpasses state-of-the-art methods with 0.9% to 1.8% backbone parameter updates, evaluated on challenging benchmarks. Our project is available at \url{https://github.com/jiaqihuang01/DETRIS}.

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="2501.08580")

Code

Syntology Ran 7 of 17 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 17 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.

jiaqihuang01/detris officialmentioned in papermentioned on GitHubpytorchMIT 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

17 samples harvested; 7 ran; 0 honoured the contract we drafted; 10 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.

4ran · our draft was wrong
3ran
10unverified

Licence: 0 of the 17 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 jiaqihuang01/detris. “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.

basic_clean jiaqihuang01/detris/utils/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 98f385d847636a3e · report
conv_layer jiaqihuang01/detris/model/layers.py official repository ran · our draft was wrong MIT (permissive) · dbfe3357dc25ca5f · report
get_pairs jiaqihuang01/detris/utils/simple_tokenizer.py official repository ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report
init_random_seed jiaqihuang01/detris/utils/misc.py official repository ran MIT (permissive) · 539cbfa1328eb51b · report
linear_layer jiaqihuang01/detris/model/layers.py official repository ran MIT (permissive) · 89f9fd49ddec76ba · report
trainMetricGPU jiaqihuang01/detris/utils/misc.py official repository ran MIT (permissive) · 78241a45492d6667 · report
whitespace_clean jiaqihuang01/detris/utils/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9542161e9640b858 · report
adapt_position_encoding jiaqihuang01/detris/model/clip.py official repository unverified MIT (permissive) · 98ab2f374bc768a9 · report
add_residual jiaqihuang01/detris/model/dinov2/layers/block.py official repository unverified MIT (permissive) · 5d16d4d4fc573ac7 · report
build_model jiaqihuang01/detris/model/clip.py official repository unverified MIT (permissive) · fd39a00b70046a6a · report
concat_all_gather jiaqihuang01/detris/utils/misc.py official repository unverified MIT (permissive) · 73cecca9f3575f09 · report
deconv_layer jiaqihuang01/detris/model/layers.py official repository unverified MIT (permissive) · db55fb2ff4ac93bb · report
drop_add_residual_stochastic_depth jiaqihuang01/detris/model/dinov2/layers/block.py official repository unverified MIT (permissive) · 85f7ffc01945bb72 · report
get_branges_scales jiaqihuang01/detris/model/dinov2/layers/block.py official repository unverified MIT (permissive) · 5be3610fa1fee19e · report
load_cfg_from_cfg_file jiaqihuang01/detris/utils/config.py official repository unverified MIT (permissive) · cc23416cff396c39 · report
loads_pyarrow jiaqihuang01/detris/utils/dataset.py official repository unverified MIT (permissive) · b4c154b6f0568b6b · report
merge_cfg_from_list jiaqihuang01/detris/utils/config.py official repository unverified MIT (permissive) · 022883c7911679b3 · report

Tasks

Image SegmentationReferring Expression SegmentationSemantic SegmentationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation RefCOCO DETRIS IoU 81.0 #1 of 4 Archive leaderboard report
Referring Expression Segmentation RefCOCO testA DETRIS Overall IoU 81.9 #6 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO testB DETRIS Overall IoU 79.0 #5 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B DETRIS Overall IoU 70.2 #4 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA DETRIS Overall IoU 78.6 #5 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val DETRIS Overall IoU 75.2 #5 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test DETRIS Overall IoU 75.3 #7 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val DETRIS Overall IoU 74.6 #7 of 23 Archive leaderboard report
Referring Expression Segmentation RefCoCo val DETRIS Overall IoU 81.0 #9 of 37 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

ALIGN

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