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 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="2003.06957")

Code

Syntology Ran 3 of 11 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 0 ran; community (archive-listed): 8 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ucbdrive/few-shot-object-detection officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
MegviiDetection/FSCE mentioned on GitHubpytorch report
fsna2022/fsna mentioned on GitHubpytorchApache-2.0 report
lexisnexis-risk-open-source/ledetection mentioned on GitHubpytorchApache-2.0 report
megvii-research/fsce mentioned 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

11 samples harvested; 3 ran; 0 honoured the contract we drafted; 8 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
8unverified

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; each sample names its own and says which. “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.

get_checkpoint_url ucbdrive/few-shot-object-detection/fsdet/model_zoo/model_zoo.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4d2207f311202a82 · report
get_config_file ucbdrive/few-shot-object-detection/fsdet/model_zoo/model_zoo.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 2556b24697336491 · report
get_save_path_seeds ucbdrive/few-shot-object-detection/datasets/prepare_coco_few_shot.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 3bcacfe0d4442213 · report
batched_nms fsna2022/fsna/fsdet/layers/nms.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 0df9d3b583fbc6cb · report
convert_basic_c2_names fsna2022/fsna/fsdet/checkpoint/c2_model_loading.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e8526a516b4f9206 · report
convert_c2_detectron_names fsna2022/fsna/fsdet/checkpoint/c2_model_loading.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 52810b504f0d1066 · report
batched_nms_rotated fsna2022/fsna/fsdet/layers/nms.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4f2e083714266b7f · report
get_last_conv_name fsna2022/fsna/demo/demo_cam.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 38620a135673712c · report
get_save_path_seeds fsna2022/fsna/datasets/prepare_coco_few_shot.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · aad0696f7f4b3825 · report
nms_rotated fsna2022/fsna/fsdet/layers/nms.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 1c319eab8e23735d · report
norm_image fsna2022/fsna/demo/demo_cam.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 98c9585c74cb0160 · 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