Papers › Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild

Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild

23 Jul 2020ECCV 2020 8arXiv:2007.12107archive 2025-07-28

Yang Xiao, Vincent Lepetit, Renaud Marlet

Detecting objects and estimating their viewpoints in images are key tasks of 3D scene understanding. Recent approaches have achieved excellent results on very large benchmarks for object detection and viewpoint estimation. However, performances are still lagging behind for novel object categories with few samples. In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation. We demonstrate on both tasks the benefits of guiding the network prediction with class-representative features extracted from data in different modalities: image patches for object detection, and aligned 3D models for viewpoint estimation. Despite its simplicity, our method outperforms state-of-the-art methods by a large margin on a range of datasets, including PASCAL and COCO for few-shot object detection, and Pascal3D+ and ObjectNet3D for few-shot viewpoint estimation. Furthermore, when the 3D model is not available, we introduce a simple category-agnostic viewpoint estimation method by exploiting geometrical similarities and consistent pose labelling across different classes. While it moderately reduces performance, this approach still obtains better results than previous methods in this setting. Last, for the first time, we tackle the combination of both few-shot tasks, on three challenging benchmarks for viewpoint estimation in the wild, ObjectNet3D, Pascal3D+ and Pix3D, showing very promising results.

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 17 code samples harvested from 2 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 17 samples from 2 repositories, 15 ran (14 with no instrument failure; 1 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 15 samples that ran has no recorded date.

YoungXIAO13/FewShotDetection mentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
YoungXIAO13/PoseContrast mentioned on GitHubpytorchMITSyntology: 10 samples, 10 ran (1 instrument-failed) · 0 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 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.

3ran · honoured contract
1ran · our draft was wrong
11ran
2unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

YoungXIAO13/FewShotDetection community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
parse_rec in 26 papers lib/datasets/custom_eval.py ran MIT (permissive) · acb811bff3bed991 · report fixture: signature df:DataFrame/0/?, filename:str/0/str · returned list · level recorded 2026-09-25
unique_boxes in 21 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · 8a015c012f507631 · report fixture: signature boxes:ndarray/2/float, scale:float/0/float · returned ndarray · level recorded 2026-09-26
voc_ap in 44 papers
census: 5 implementations from 10 papers, 2 distinct outputs on one shared input
lib/datasets/custom_eval.py ran fingerprinted MIT (permissive) · 27f142a9eb53b71c · report fixture: signature rec:ndarray/1/float, prec:ndarray/1/float · returned float64 · level recorded 2026-09-25
xywh_to_xyxy in 24 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · d3e019b11b709edb · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
xyxy_to_xywh in 23 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · a832e5017f504280 · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
custom_eval lib/datasets/custom_eval.py unverified MIT (permissive) · 2a0d3950d39963bd · report
get_imdb in 22 papers lib/datasets/factory.py unverified MIT (permissive) · 3be9228820b46ef3 · report
YoungXIAO13/PoseContrast community (archive-listed) 10 samples, 10 ran (1 instrument-failed) · 0 unverified
adjust_learning_rate in 125 papers src/model/model_utils.py ran MIT (permissive) · a265d6a3a1a77ecf · report fixture: signature optimizer:SGD/0/?, base_lr:float/0/float · returned float · level recorded 2026-09-24
conv3x3 in 1,376 papers src/model/resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
cross_entropy_loss in 58 papers src/model/model_utils.py ran MIT (permissive) · af5785faecdf4e41 · report fixture: signature pred:Tensor/2/float, target:Tensor/1/int, range:int/0/int · returned Tensor · level recorded 2026-09-24
get_logger in 383 papers src/utils/logger.py ran MIT (permissive) · 57069fdc71bccf4c · report fixture: signature log_dir:str/0/str, name:str/0/str · returned Logger · level recorded 2026-09-24
get_pred_from_cls_output src/model/model_utils.py ran MIT (permissive) · 62f21bfe77ba9f57 · report fixture: signature outputs:list/1/Tensor · returned list · level recorded 2026-09-24
process_viewpoint_label src/dataset/data_utils.py ran MIT (permissive) · aa91699e68fcd5c4 · report fixture: signature label:ndarray/1/float, offset:int/0/int · returned Tensor · level recorded 2026-09-24
random_crop in 59 papers src/dataset/data_utils.py ran MIT (permissive) · cc95c0207256a15f · report fixture: signature im:Image/0/?, x:int/0/int, y:int/0/int, w:int/0/int, h:int/0/int · returned Image · level recorded 2026-09-24
resize_pad src/dataset/data_utils.py ran MIT (permissive) · 37944fb141643143 · report fixture: signature im:Image/0/?, dim:int/0/int · returned Image · level recorded 2026-09-24
resnet18 in 432 papers src/model/resnet.py ran MIT (permissive) · 4369c368bb8cfd3b · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers src/model/resnet.py ran MIT (permissive) · 5b6600441e89b9dd · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24

Tasks

Few-Shot Object DetectionMeta-LearningObjectObject DetectionScene UnderstandingViewpoint Estimationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Object Detection MS-COCO (10-shot) FSDetView AP 12.5 #21 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) FsDetView AP 14.7 #17 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