SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.06957 · 2020

Frustratingly Simple Few-Shot Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

5 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 4 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2003.06957.json · badge: /api/ran/2003.06957.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ucbdrive/few-shot-object-detection canonical (classifier label)
classifier basis: census
0 ran · 3 no recorded run
fsna2022/fsna community (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
FunctionStatusWhere it lives
batched_nms Ran
ran; our contract draft was wrong, not the code
fsna2022/fsna/fsdet/layers/nms.py
pointer only (licence: Apache-2.0) · get_code("0df9d3b583fbc6cb")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_basic_c2_names Ran
ran; our contract draft was wrong, not the code
fsna2022/fsna/fsdet/checkpoint/c2_model_loading.py
pointer only (licence: Apache-2.0) · get_code("e8526a516b4f9206")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_c2_detectron_names Ran
ran; our contract draft was wrong, not the code
fsna2022/fsna/fsdet/checkpoint/c2_model_loading.py
pointer only (licence: Apache-2.0) · get_code("52810b504f0d1066")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_last_conv_name Ran
ran on a synthesized input
fsna2022/fsna/demo/demo_cam.py
pointer only (licence: Apache-2.0) · get_code("38620a135673712c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

norm_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fsna2022/fsna/demo/demo_cam.py
pointer only (licence: Apache-2.0) · get_code("98c9585c74cb0160")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

batched_nms_rotated Not yet run
unverified (harvested, no recorded run)
fsna2022/fsna/fsdet/layers/nms.py
pointer only (licence: Apache-2.0) · get_code("4f2e083714266b7f")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_checkpoint_url Not yet run
unverified (harvested, no recorded run)
ucbdrive/few-shot-object-detection/fsdet/model_zoo/model_zoo.py
pointer only (licence: Apache-2.0) · get_code("4d2207f311202a82")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, ucbdrive/few-shot-object-detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_config_file Not yet run
unverified (harvested, no recorded run)
ucbdrive/few-shot-object-detection/fsdet/model_zoo/model_zoo.py
pointer only (licence: Apache-2.0) · get_code("2556b24697336491")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, ucbdrive/few-shot-object-detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_save_path_seeds Not yet run
unverified (harvested, no recorded run)
ucbdrive/few-shot-object-detection/datasets/prepare_coco_few_shot.py
pointer only (licence: Apache-2.0) · get_code("3bcacfe0d4442213")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, ucbdrive/few-shot-object-detection, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_save_path_seeds Not yet run
unverified (harvested, no recorded run)
fsna2022/fsna/datasets/prepare_coco_few_shot.py
pointer only (licence: Apache-2.0) · get_code("aad0696f7f4b3825")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

nms_rotated Not yet run
unverified (harvested, no recorded run)
fsna2022/fsna/fsdet/layers/nms.py
pointer only (licence: Apache-2.0) · get_code("1c319eab8e23735d")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, fsna2022/fsna, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 4 the same month, 8 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
convert_basic_c2_names 45 other papers
6 dated earlier, 3 the same month, 36 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1901.08164 (2019-01)
Decoupled Greedy Learning of CNNs
and 42 more not named here
convert_c2_detectron_names 29 other papers
5 dated earlier, 3 the same month, 21 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1901.08164 (2019-01)
Decoupled Greedy Learning of CNNs
and 26 more not named here
batched_nms 12 other papers
3 dated earlier, 2 the same month, 7 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 9 more not named here
batched_nms_rotated 12 other papers
3 dated earlier, 2 the same month, 7 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 9 more not named here
norm_image 2 other papers
2 later
136990421 (2022 (year only))
AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
2409.17531 (2024-09)
SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
get_checkpoint_url 1 other paper
1 later
2112.05749 (2021-12)
Label, Verify, Correct: A Simple Few Shot Object Detection Method
get_last_conv_name 1 other paper
1 later
136990421 (2022 (year only))
AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
nms_rotated 1 other paper
1 later
2407.02665 (2024-07)
SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.06957")
get_code_for_paper("2003.06957")
have("2003.06957")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.06957.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.06957.svg)](https://syntology.ai/paper/2003.06957)

Connect an agent — have() is free.