Papers › Frustratingly Simple Few-Shot Object Detection

Frustratingly Simple Few-Shot Object Detection

16 Mar 2020ICML 2020 1arXiv:2003.06957archive 2025-07-28

Xin Wang, Thomas E. Huang, Trevor Darrell, Joseph E. Gonzalez, Fisher Yu

Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the evaluation protocols by sampling multiple groups of training examples to obtain stable comparisons and build new benchmarks based on three datasets: PASCAL VOC, COCO and LVIS. Again, our fine-tuning approach establishes a new state of the art on the revised benchmarks. The code as well as the pretrained models are available at https://github.com/ucbdrive/few-shot-object-detection.

PaperPDFConference PDFCodeCode 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 11 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 8 samples from 1 repository, 5 ran (3 with no instrument failure; 2 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ucbdrive/few-shot-object-detection officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 0 ran · 3 unverified report
MegviiDetection/FSCE mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (arXiv:2103.05950; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
fsna2022/fsna mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 5 ran (2 instrument-failed) · 3 unverified report
lexisnexis-risk-open-source/ledetection mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
megvii-research/fsce mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 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.

2ran · our draft was wrong
3ran
6unverified

Licence: 11 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

ucbdrive/few-shot-object-detection official repository 3 samples, 0 ran · 3 unverified
get_checkpoint_url in 7 papers fsdet/model_zoo/model_zoo.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4d2207f311202a82 · report
get_config_file in 13 papers fsdet/model_zoo/model_zoo.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 2556b24697336491 · report
get_save_path_seeds in 5 papers datasets/prepare_coco_few_shot.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 3bcacfe0d4442213 · report
fsna2022/fsna community (archive-listed) 8 samples, 5 ran (2 instrument-failed) · 3 unverified
batched_nms in 29 papers fsdet/layers/nms.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 0df9d3b583fbc6cb · 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
convert_basic_c2_names in 46 papers fsdet/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · e8526a516b4f9206 · report fixture: signature original_keys:list/1/str · returned list · level recorded 2026-09-24
convert_c2_detectron_names in 45 papers fsdet/checkpoint/c2_model_loading.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · 52810b504f0d1066 · report fixture: signature weights:dict/0/? · returned tuple · level recorded 2026-09-24
get_last_conv_name demo/demo_cam.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 38620a135673712c · report fixture: signature net:callable/0/? · returned str · level recorded 2026-09-25
norm_image demo/demo_cam.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 98c9585c74cb0160 · report fixture: signature image:ndarray/3/float · returned ndarray · level recorded 2026-09-25
batched_nms_rotated in 22 papers fsdet/layers/nms.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4f2e083714266b7f · report
get_save_path_seeds in 5 papers datasets/prepare_coco_few_shot.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · aad0696f7f4b3825 · report
nms_rotated in 22 papers fsdet/layers/nms.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 1c319eab8e23735d · report

Tasks

Cross-Domain Few-Shot Object DetectionFew-Shot Object DetectionMeta-LearningObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Domain Few-Shot Object Detection Artaxor TFA w/cos mAP 14.8 #12 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR TFA w/cos mAP 20.5 #10 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD TFA w/cos mAP 11.8 #11 of 16 Archive leaderboard report
Few-Shot Object Detection MS-COCO (10-shot) TFA(w/cos) AP 10.0 #27 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (10-shot) TFA(w/fc) AP 10.0 #28 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) TFA w/ cos AP 13.7 #20 of 25 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) TFA w/ fc AP 13.4 #21 of 25 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.

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