SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09674 · CVPR · 2023

DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection

Yulei Niu, Jiawei Ma, Shiyuan Huang, Guangxing Han, Shih-Fu Chang, Jincheng Xu

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 2 have no contract verdict; 3 failures of our instrument; 0 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/2303.09674.json · badge: /api/ran/2303.09674.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
phoenix-v/digeo canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
inference_on_dataset Ran
ran on a synthesized input
phoenix-v/digeo/fsdet/evaluation/evaluator.py
pointer only (licence: Apache-2.0) · get_code("5efdd727855af1d7")
How it ran

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

parse_rec Ran
ran; our contract draft was wrong, not the code
phoenix-v/digeo/fsdet/evaluation/pascal_voc_evaluation.py
pointer only (licence: Apache-2.0) · get_code("2e81e6f4cd544f1b")
How it ran

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

verify_results Ran
ran on a synthesized input
phoenix-v/digeo/fsdet/evaluation/testing.py
pointer only (licence: Apache-2.0) · get_code("4f63544d758aa862")
How it ran

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

voc_ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
phoenix-v/digeo/fsdet/evaluation/pascal_voc_evaluation.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from amajee11us/CROWD, is pointer only (licence: NONE) · get_code("611c47c44c424dba")
How it ran

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

voc_eval Ran
ran; our contract draft was wrong, not the code
phoenix-v/digeo/fsdet/evaluation/pascal_voc_evaluation.py
pointer only (licence: Apache-2.0) · get_code("a6d455c6f04f93d3")
How it ran

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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
voc_ap 27 other papers
19 dated earlier, 8 later
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1605.06409 (2016-05)
R-FCN: Object Detection via Region-based Fully Convolutional Networks
1609.03605 (2016-09)
Detecting Text in Natural Image with Connectionist Text Proposal Network
and 24 more not named here
parse_rec 2 other papers
2 later
2309.12969 (2023-09)
Detect Everything with Few Examples
Zhou_When_Pixel_Difference_Patterns_Meet_ViT_PiDiViT_for_Few-Shot_Object_ICCV_2025_paper (2025 (year only))
When Pixel Difference Patterns Meet ViT: PiDiViT for Few-Shot Object Detection
voc_eval 2 other papers
2 later
2309.12969 (2023-09)
Detect Everything with Few Examples
Zhou_When_Pixel_Difference_Patterns_Meet_ViT_PiDiViT_for_Few-Shot_Object_ICCV_2025_paper (2025 (year only))
When Pixel Difference Patterns Meet ViT: PiDiViT for Few-Shot Object Detection
inference_on_dataset 1 other paper
1 dated earlier
2112.05749 (2021-12)
Label, Verify, Correct: A Simple Few Shot Object Detection Method

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

Generalized few-shot object detection aims to achieve precise detection on both base classes with abundant annotations and novel classes with limited training data. Existing approaches enhance few-shot generalization with the sacrifice of base-class performance, or maintain high precision in base-class detection with limited improvement in novel-class adaptation. In this paper, we point out the reason is insufficient Discriminative feature learning for all of the classes. As such, we propose a new training framework, DiGeo, to learn Geometry-aware features of interclass separation and intra-class compactness. To guide the separation of feature clusters, we derive an offline simplex equiangular tight frame (ETF) classifier whose weights serve as class centers and are maximally and equally separated. To tighten the cluster for each class, we include adaptive class-specific margins into the classification loss and encourage the features close to the class centers. Experimental studies on two few-shot benchmark datasets (VOC, COCO) and one long-tail dataset (LVIS) demonstrate that, with a single model, our method can effectively improve generalization on novel classes without hurting the detection of base classes. Our code can be found here.

For agents

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

get_harvested_code_for_paper("2303.09674")
get_code_for_paper("2303.09674")
have("2303.09674")

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

curl https://syntology.ai/api/ran/2303.09674.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.09674.svg)](https://syntology.ai/paper/2303.09674)

Connect an agent — have() is free.