Papers › Detect Everything with Few Examples

Detect Everything with Few Examples

22 Sep 2023arXiv:2309.12969archive 2025-07-28

Xinyu Zhang, YuHan Liu, Yuting Wang, Abdeslam Boularias

Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures that prohibit a wider application. In this paper, we introduce DE-ViT, a few-shot object detector without the need for finetuning. DE-ViT's novel architecture is based on a new region-propagation mechanism for localization. The propagated region masks are transformed into bounding boxes through a learnable spatial integral layer. Instead of training prototype classifiers, we propose to use prototypes to project ViT features into a subspace that is robust to overfitting on base classes. We evaluate DE-ViT on few-shot, and one-shot object detection benchmarks with Pascal VOC, COCO, and LVIS. DE-ViT establishes new state-of-the-art results on all benchmarks. Notably, for COCO, DE-ViT surpasses the few-shot SoTA by 15 mAP on 10-shot and 7.2 mAP on 30-shot and one-shot SoTA by 2.8 AP50. For LVIS, DE-ViT outperforms few-shot SoTA by 17 box APr. Further, we evaluate DE-ViT with a real robot by building a pick-and-place system for sorting novel objects based on example images. The videos of our robot demonstrations, the source code and the models of DE-ViT can be found at https://mlzxy.github.io/devit.

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 20 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 17 ran (11 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mlzxy/devit officialmentioned in papermentioned on GitHubpytorchMITSyntology: 20 samples, 17 ran (6 instrument-failed) · 3 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

20 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 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.

5ran · our draft was wrong
1ran; the contract check could not run
11ran
3unverified

Licence: 1 of the 20 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 mlzxy/devit. “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.

mlzxy/devit official repository 20 samples, 17 ran (6 instrument-failed) · 3 unverified
box_cxcywh_to_xyxy in 60 papers lib/regionprop.py ran · our draft was wrong fingerprinted MIT (permissive) · 009912c75c8c77cf · report fixture: signature bbox:Tensor/2/float · returned Tensor · level recorded 2026-09-24
box_xyxy_clamp lib/regionprop.py ran fingerprinted MIT (permissive) · 88d32e10c27e7a12 · report fixture: signature bbox:Tensor/2/float, h:int/0/int, w:int/0/int · returned Tensor · level recorded 2026-09-24
box_xyxy_to_cxcywh in 37 papers lib/regionprop.py ran · our draft was wrong fingerprinted MIT (permissive) · db78cfc20095f3a8 · report fixture: signature bbox:Tensor/2/float · returned Tensor · level recorded 2026-09-24
convert_basic_c2_names in 46 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong MIT (permissive) · e8526a516b4f9206 · report fixture: signature original_keys:list/1/str · returned list · level recorded 2026-09-24
convert_basic_clip_names in 6 papers detectron2/checkpoint/clip_model_loading.py ran MIT (permissive) · 7b7f6e4aa28b1a69 · report fixture: signature original_keys:list/1/str, add_backbone_prefix:bool/0/bool, use_whole_clip:bool/0/bool, use_fpn_arch:bool/0/bool, regionclip:bool/0/bool · returned tuple · level recorded 2026-09-24
convert_c2_detectron_names in 45 papers detectron2/checkpoint/c2_model_loading.py ran · our draft was wrong MIT (permissive) · e36f87059208bb7e · report fixture: signature weights:dict/0/? · returned tuple · level recorded 2026-09-24
convert_clip_names in 6 papers detectron2/checkpoint/clip_model_loading.py ran MIT (permissive) · 376248f5d186a885 · report fixture: signature weights:dict/0/?, add_backbone_prefix:bool/0/bool, use_whole_clip:bool/0/bool, use_fpn_arch:bool/0/bool, regionclip:bool/0/bool · returned tuple · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
detectron2/modeling/meta_arch/devit_update.py ran · our draft was wrong fingerprinted MIT (permissive) · 89f75e54ff128be0 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
elementwise_box_iou detectron2/modeling/meta_arch/devit.py ran fingerprinted MIT (permissive) · 1bec3241f0f82f89 · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float · returned tuple · level recorded 2026-09-24
generalized_box_iou in 10 papers detectron2/modeling/meta_arch/devit_update.py ran fingerprinted MIT (permissive) · 761e870ed51af37c · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float · returned Tensor · level recorded 2026-09-24
interpolate in 95 papers detectron2/modeling/meta_arch/devit.py ran MIT (permissive) · a38f5f94b0a19b1b · report fixture: signature seq:Tensor/3/float, T:int/0/int, mode:str/0/str, force:bool/0/bool · returned Tensor · level recorded 2026-09-24
mask_sinkhorn lib/prototype_learner.py ran MIT (permissive) · 9d4bd1f443b65407 · report fixture: signature C:Tensor/2/float, mask:Tensor/2/bool, row_group_size:Tensor/1/float, col_group_size:Tensor/1/float, iterations:int/0/int, epsilon:float/0/float, return_cost:bool/0/bool · returned Tensor · level recorded 2026-09-24
parse_rec in 26 papers lib/voc_eval.py ran MIT (permissive) · 2e81e6f4cd544f1b · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-24
sigmoid_ce_loss in 70 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
detectron2/modeling/meta_arch/devit_update.py ran fingerprinted MIT (permissive) · 847c0c0c48d84c9e · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-24
sinkhorn in 47 papers
census: 11 implementations from 11 papers, 11 distinct outputs across 2 buckets, one shared input per bucket
lib/prototype_learner.py ran MIT (permissive) · f8c7f9605872c11b · report fixture: signature C:Tensor/2/float, iterations:int/0/int, epsilon:float/0/float · returned tuple · level recorded 2026-09-24
voc_ap in 44 papers
census: 5 implementations from 10 papers, 2 distinct outputs on one shared input
lib/voc_eval.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 611c47c44c424dba · report fixture: signature rec:ndarray/1/float, prec:ndarray/1/float, use_07_metric:bool/0/bool · returned float64 · level recorded 2026-09-25
voc_eval in 19 papers lib/voc_eval.py ran MIT (permissive) · a6d455c6f04f93d3 · report fixture: signature detpath:str/0/str, annopath:str/0/str, imagesetfile:str/0/str, classname:str/0/str, ovthresh:float/0/float, use_07_metric:bool/0/bool · returned tuple · level recorded 2026-09-24
align_and_update_state_dicts in 21 papers detectron2/checkpoint/c2_model_loading.py unverified MIT (permissive) · ac2638463572c152 · report
align_and_update_state_dicts_for_CLIP in 6 papers detectron2/checkpoint/clip_model_loading.py unverified MIT (permissive) · 0bd7b0a60b4069f9 · report
generalized_box_iou in 10 papers detectron2/modeling/meta_arch/devit.py unverified MIT (permissive) · bfc4e32519b5ef25 · report

Tasks

Binary ClassificationCross-Domain Few-Shot Object DetectionFew-Shot Object DetectionObjectObject DetectionOne-Shot Object DetectionOpen Vocabulary Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Domain Few-Shot Object Detection Artaxor DE-ViT-FT mAP 49.2 #6 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Artaxor DE-ViT(w/o FT) mAP 9.2 #15 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Clipark1k DE-ViT-FT mAP 40.8 #5 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Clipark1k DE-ViT(w/o FT) mAP 11.0 #10 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR DE-ViT-FT mAP 25.6 #6 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR DE-ViT(w/o FT) mAP 8.4 #13 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DeepFish DE-ViT-FT mAP 21.3 #6 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DeepFish DE-ViT(w/o FT) mAP 2.1 #9 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection NEU-DET DE-ViT-FT mAP 8.8 #6 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection NEU-DET DE-ViT(w/o FT) mAP 1.8 #9 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD DE-ViT-FT mAP 5.4 #14 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD DE-ViT(w/o FT) mAP 3.1 #15 of 16 Archive leaderboard report
Few-Shot Object Detection MS-COCO (10-shot) DE-ViT AP 34.0 #3 of 33 Archive leaderboard report
Few-Shot Object Detection MS-COCO (30-shot) DE-ViT AP 34 #3 of 25 Archive leaderboard report
One-Shot Object Detection COCO (Common Objects in Context) DE-ViT AP 0.5 28.4 #2 of 4 Archive leaderboard report
Open Vocabulary Object Detection LVIS v1.0 DE-ViT AP novel-LVIS base training 34.3 #7 of 28 Archive leaderboard report
Open Vocabulary Object Detection MSCOCO DE-ViT AP 0.5 50 #2 of 32 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.

Methods

BASEFocus

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