Papers › What, How, and When Should Object Detectors Update in Continually Changing Test Domains?

What, How, and When Should Object Detectors Update in Continually Changing Test Domains?

12 Dec 2023arXiv:2312.08875archive 2025-07-28

Jayeon Yoo, Dongkwan Lee, Inseop Chung, Donghyun Kim, Nojun Kwak

It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have been proposed to adapt the model online while inferring test data. However, existing research predominantly focuses on classification tasks through the optimization of batch normalization layers or classification heads, but this approach limits its applicability to various model architectures like Transformers and makes it challenging to apply to other tasks, such as object detection. In this paper, we propose a novel online adaption approach for object detection in continually changing test domains, considering which part of the model to update, how to update it, and when to perform the update. By introducing architecture-agnostic and lightweight adaptor modules and only updating these while leaving the pre-trained backbone unchanged, we can rapidly adapt to new test domains in an efficient way and prevent catastrophic forgetting. Furthermore, we present a practical and straightforward class-wise feature aligning method for object detection to resolve domain shifts. Additionally, we enhance efficiency by determining when the model is sufficiently adapted or when additional adaptation is needed due to changes in the test distribution. Our approach surpasses baselines on widely used benchmarks, achieving improvements of up to 4.9%p and 7.9%p in mAP for COCO → COCO-corrupted and SHIFT, respectively, while maintaining about 20 FPS or higher.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 1 repository, 8 ran (2 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

natureyoo/continualtta_objectdetection mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 8 ran (6 instrument-failed) · 4 unverified 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

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
2ran; the contract check could not run
2ran
4unverified

Licence: 7 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from natureyoo/continualtta_objectdetection. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

natureyoo/continualtta_objectdetection community (archive-listed) 12 samples, 8 ran (6 instrument-failed) · 4 unverified
batched_nms in 29 papers detectron2/layers/nms.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · d7527a665dfb8f27 · report fixture: signature boxes:Tensor/2/float, scores:Tensor/1/float, idxs:Tensor/1/int, iou_threshold:float/0/float · returned Tensor · level recorded 2026-09-24
ciou_loss in 6 papers detectron2/layers/losses.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · cee8870d4fbccc39 · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float, reduction:str/0/str, eps:float/0/float · returned Tensor · level recorded 2026-09-22
convert_basic_c2_names in 46 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 (permissive) · e8526a516b4f9206 · report fixture: signature original_keys:list/1/str · returned list · level recorded 2026-09-24
convert_c2_detectron_names in 45 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 (permissive) · e36f87059208bb7e · report fixture: signature weights:dict/0/? · returned tuple · level recorded 2026-09-24
diou_loss in 5 papers detectron2/layers/losses.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 26f3066ead0d2eec · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float, reduction:str/0/str, eps:float/0/float · returned Tensor · level recorded 2026-09-22
pad_masks in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 406f84cf799ed34d · report fixture: signature masks:Tensor/3/float, padding:int/0/int · returned tuple · level recorded 2026-09-24
paste_mask_in_image_old in 23 papers detectron2/layers/mask_ops.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · d03592674030077f · report fixture: signature mask:Tensor/2/float, box:Tensor/1/float, img_h:int/0/int, img_w:int/0/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-24
paste_masks_in_image in 20 papers detectron2/layers/mask_ops.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · c0eac7dcd1335fa1 · report fixture: signature masks:Tensor/3/float, boxes:Tensor/2/float, image_shape:tuple/1/int, threshold:float/0/float · returned Tensor · level recorded 2026-09-24
align_and_update_state_dicts in 21 papers detectron2/checkpoint/c2_model_loading.py unverified Apache-2.0 (permissive) · 12ac3169b5ff0207 · report
batched_nms_rotated in 22 papers detectron2/layers/nms.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · df39d2e76b0bb6d2 · report
nms_rotated in 22 papers detectron2/layers/nms.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · ecfd01cc7b6523f8 · report
pairwise_iou_rotated detectron2/layers/rotated_boxes.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · df40c33628d29275 · report

Tasks

Object DetectionTest-time Adaptationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch Normalization

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