Papers › DePT: Decoupled Prompt Tuning

DePT: Decoupled Prompt Tuning

14 Sep 2023CVPR 2024 1arXiv:2309.07439archive 2025-07-28

Ji Zhang, Shihan Wu, Lianli Gao, Heng Tao Shen, Jingkuan Song

This work breaks through the Base-New Tradeoff (BNT)dilemma in prompt tuning, i.e., the better the tuned model generalizes to the base (or target) task, the worse it generalizes to new tasks, and vice versa. Specifically, through an in-depth analysis of the learned features of the base and new tasks, we observe that the BNT stems from a channel bias issue, i.e., the vast majority of feature channels are occupied by base-specific knowledge, resulting in the collapse of taskshared knowledge important to new tasks. To address this, we propose the Decoupled Prompt Tuning (DePT) framework, which decouples base-specific knowledge from feature channels into an isolated feature space during prompt tuning, so as to maximally preserve task-shared knowledge in the original feature space for achieving better zero-shot generalization on new tasks. Importantly, our DePT is orthogonal to existing prompt tuning methods, hence it can improve all of them. Extensive experiments on 11 datasets show the strong flexibility and effectiveness of DePT. Our code and pretrained models are available at https://github.com/Koorye/DePT.

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="2309.07439")

Code

Syntology Ran 4 of 8 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

koorye/dept officialmentioned in papermentioned on GitHubpytorchGPL-2.0 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

8 samples harvested; 4 ran; 0 honoured the contract we drafted; 4 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.

3ran · our draft was wrong
1ran
4unverified

Licence: 8 of the 8 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 koorye/dept. “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 koorye/dept/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted GPL-2.0 (copyleft) · pointer only · 98f385d847636a3e · report
get_command koorye/dept/templates.py official repository ran GPL-2.0 (copyleft) · pointer only · c736029a62966e42 · report
get_pairs koorye/dept/clip/simple_tokenizer.py official repository ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · d919ae32e5e4e616 · report
whitespace_clean koorye/dept/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted GPL-2.0 (copyleft) · pointer only · 9542161e9640b858 · report
build_model koorye/dept/clip_maple/model.py official repository unverified GPL-2.0 (copyleft) · pointer only · 48ac2bd4dcbfb717 · report
build_model koorye/dept/clip/model.py official repository unverified GPL-2.0 (copyleft) · pointer only · c47aa9e5b049a11d · report
get_config koorye/dept/configs.py official repository unverified GPL-2.0 (copyleft) · pointer only · 4a6d53438b20cd99 · report
load koorye/dept/clip/clip.py official repository unverified GPL-2.0 (copyleft) · pointer only · fbf8c0143d9c48e3 · report

Tasks

Prompt EngineeringZero-shot Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Prompt Engineering Caltech-101 DePT Harmonic mean 96.28 #8 of 14 Archive leaderboard report
Prompt Engineering DTD DePT Harmonic mean 71.09 #9 of 14 Archive leaderboard report
Prompt Engineering EuroSAT DePT Harmonic mean 84.88 #7 of 14 Archive leaderboard report
Prompt Engineering FGVC-Aircraft DePT Harmonic mean 40.73 #5 of 14 Archive leaderboard report
Prompt Engineering Food-101 DePT Harmonic mean 91.22 #6 of 13 Archive leaderboard report
Prompt Engineering ImageNet DePT Harmonic mean 74.02 #10 of 15 Archive leaderboard report
Prompt Engineering Oxford 102 Flower DePT Harmonic mean 86.46 #6 of 14 Archive leaderboard report
Prompt Engineering Oxford-IIIT Pet Dataset DePT Harmonic mean 96.37 #10 of 14 Archive leaderboard report
Prompt Engineering SUN397 DePT Harmonic mean 81.06 #6 of 14 Archive leaderboard report
Prompt Engineering Stanford Cars DePT Harmonic mean 77.79 #4 of 14 Archive leaderboard report
Prompt Engineering UCF101 DePT Harmonic mean 82.46 #9 of 14 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

BASE

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