Papers › Unsupervised Domain Adaptive Detection with Network Stability Analysis

Unsupervised Domain Adaptive Detection with Network Stability Analysis

16 Aug 2023ICCV 2023 1arXiv:2308.08182archive 2025-07-28

Wenzhang Zhou, Heng Fan, Tiejian Luo, Libo Zhang

Domain adaptive detection aims to improve the generality of a detector, learned from the labeled source domain, on the unlabeled target domain. In this work, drawing inspiration from the concept of stability from the control theory that a robust system requires to remain consistent both externally and internally regardless of disturbances, we propose a novel framework that achieves unsupervised domain adaptive detection through stability analysis. In specific, we treat discrepancies between images and regions from different domains as disturbances, and introduce a novel simple but effective Network Stability Analysis (NSA) framework that considers various disturbances for domain adaptation. Particularly, we explore three types of perturbations including heavy and light image-level disturbances and instancelevel disturbance. For each type, NSA performs external consistency analysis on the outputs from raw and perturbed images and/or internal consistency analysis on their features, using teacher-student models. By integrating NSA into Faster R-CNN, we immediately achieve state-of-the-art results. In particular, we set a new record of 52.7% mAP on Cityscapes-to-FoggyCityscapes, showing the potential of NSA for domain adaptive detection. It is worth noticing, our NSA is designed for general purpose, and thus applicable to one-stage detection model (e.g., FCOS) besides the adopted one, as shown by experiments. https://github.com/tiankongzhang/NSA.

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="2308.08182")

Code

Syntology Ran 14 of 16 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · fixture could not drive it; 12 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tiankongzhang/nsa officialmentioned in papermentioned on GitHubpytorch 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

16 samples harvested; 14 ran; 0 honoured the contract we drafted; 2 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.

2ran · fixture could not drive it
12ran
2unverified

Licence: 16 of the 16 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 tiankongzhang/NSA. “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.

StylePool2d tiankongzhang/NSA/detection/layers/style_pool2d.py official repository ran fingerprinted no licence file found · pointer only · 5e6a1b228a7b1cae · report
bbox_iou tiankongzhang/nsa/detection/modeling/giou.py official repository ran fingerprinted no licence file found · pointer only · 4813f83190c76310 · report
box_c tiankongzhang/nsa/detection/modeling/giou.py official repository ran no licence file found · pointer only · fce1a3ca70feb408 · report
box_to_centers tiankongzhang/nsa/dis_test-nsa.py official repository ran fingerprinted no licence file found · pointer only · 7aa6079431a1c07e · report
box_union tiankongzhang/nsa/detection/modeling/giou.py official repository ran fingerprinted no licence file found · pointer only · 9587668c2592ebd1 · report
cat tiankongzhang/nsa/detection/layers/misc.py official repository ran · fixture could not drive it no licence file found · pointer only · 6cbf46794989b731 · report
expand_boxes tiankongzhang/nsa/detection/layers/mask_ops.py official repository ran fingerprinted no licence file found · pointer only · 5362c4106bc79217 · report
expand_masks tiankongzhang/nsa/detection/layers/mask_ops.py official repository ran fingerprinted no licence file found · pointer only · 483e9180a343e7a4 · report
interpolate tiankongzhang/nsa/detection/layers/wrappers.py official repository ran no licence file found · pointer only · e93234ba78934297 · report
sigmoid_focal_loss tiankongzhang/nsa/detection/layers/losses.py official repository ran no licence file found · pointer only · b4ba161af9015512 · report
smooth_l1_loss tiankongzhang/nsa/detection/layers/losses.py official repository ran no licence file found · pointer only · aadb076657e5223e · report
softmax_focal_loss tiankongzhang/nsa/detection/layers/losses.py official repository ran no licence file found · pointer only · 824189b8bd30a2c5 · report
style_pool2d tiankongzhang/NSA/detection/layers/style_pool2d.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 1dc003f9fcdf7dd0 · report
warmup_lr_scheduler tiankongzhang/nsa/dis_test-nsa.py official repository ran no licence file found · pointer only · 18e46d40adcc7912 · report
cosine_scheduler tiankongzhang/nsa/dis_test-nsa.py official repository unverified no licence file found · pointer only · 772973990857342d · report
paste_mask_in_image tiankongzhang/nsa/detection/layers/mask_ops.py official repository unverified no licence file found · pointer only · d59acf8d4cc00e8d · report

Tasks

Domain Adaptation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionFaster R-CNNRPNRoIPoolSoftmax

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