SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.08798 · 2020

Incremental Object Detection via Meta-Learning

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 6 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2003.08798.json · badge: /api/ran/2003.08798.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
JosephKJ/iOD canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
batched_nms Ran
ran; our contract draft was wrong, not the code
JosephKJ/iOD/detectron2/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, JosephKJ/iOD, 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.

combine_semantic_and_instance_outputs Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from cjrd/self-supervised-pretraining
pointer only; the stored copy get_code serves, from cjrd/self-supervised-pretraining, is pointer only (licence: NONE) · get_code("312f7f3ac838717a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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
JosephKJ/iOD/detectron2/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, JosephKJ/iOD, 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
JosephKJ/iOD/detectron2/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, JosephKJ/iOD, 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.

pad_masks Ran
ran; our contract draft was wrong, not the code
JosephKJ/iOD/detectron2/layers/mask_ops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from thinklab-sjtu/bench2drivezoo, is pointer only (licence: NOASSERTION) · get_code("406f84cf799ed34d")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JosephKJ/iOD, 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.

paste_mask_in_image_old Ran
ran; our contract draft was wrong, not the code
JosephKJ/iOD/detectron2/layers/mask_ops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from thinklab-sjtu/bench2drivezoo, is pointer only (licence: NOASSERTION) · get_code("d03592674030077f")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JosephKJ/iOD, 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.

paste_masks_in_image Ran
ran on a synthesized input
JosephKJ/iOD/detectron2/layers/mask_ops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from airsplay/py-bottom-up-attention, is pointer only (licence: Apache-2.0) · get_code("f74abd7e1355f8cd")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JosephKJ/iOD, 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)
JosephKJ/iOD/detectron2/layers/nms.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from nvakhoa/superclass-fsis, is pointer only (licence: Apache-2.0) · get_code("4845964b76bba6c5")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JosephKJ/iOD, 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)
JosephKJ/iOD/detectron2/layers/nms.py
pointer only (licence: Apache-2.0) · get_code("d3fa37a000ad294d")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JosephKJ/iOD, 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 7 the same month, 9 later) and 0 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
pad_masks 22 other papers
3 dated earlier, 1 the same month, 18 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 19 more not named here
paste_mask_in_image_old 22 other papers
3 dated earlier, 1 the same month, 18 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 19 more not named here
nms_rotated 14 other papers
3 dated earlier, 1 the same month, 10 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 11 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
paste_masks_in_image 5 other papers
2 dated earlier, 3 later
1703.06870 (2017-03)
Mask R-CNN
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
2004.13248 (2020-04)
R 3 : Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge
and 2 more not named here
combine_semantic_and_instance_outputs 1 other paper
1 later
2103.12718 (2021-03)
Self-Supervised Pretraining Improves Self-Supervised Pretraining

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 2026-11-21.

Repositories linked to this paper

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

Abstract

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few efforts have been reported to address this limitation, all of which apply variants of knowledge distillation to avoid catastrophic forgetting. We note that although distillation helps to retain previous learning, it obstructs fast adaptability to new tasks, which is a critical requirement for incremental learning. In this pursuit, we propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. This ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection. We evaluate our approach on a variety of incremental learning settings defined on PASCAL-VOC and MS COCO datasets, where our approach performs favourably well against state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2003.08798")
get_code_for_paper("2003.08798")
have("2003.08798")

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

curl https://syntology.ai/api/ran/2003.08798.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.08798.svg)](https://syntology.ai/paper/2003.08798)

Connect an agent — have() is free.