Papers › Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection

Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection

14 Feb 2022arXiv:2202.06934archive 2025-07-28

Fatih Cagatay Akyon, Sinan Onur Altinuc, Alptekin Temizel

Detection of small objects and objects far away in the scene is a major challenge in surveillance applications. Such objects are represented by small number of pixels in the image and lack sufficient details, making them difficult to detect using conventional detectors. In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection. The proposed technique is generic in the sense that it can be applied on top of any available object detector without any fine-tuning. Experimental evaluations, using object detection baselines on the Visdrone and xView aerial object detection datasets show that the proposed inference method can increase object detection AP by 6.8%, 5.1% and 5.3% for FCOS, VFNet and TOOD detectors, respectively. Moreover, the detection accuracy can be further increased with a slicing aided fine-tuning, resulting in a cumulative increase of 12.7%, 13.4% and 14.5% AP in the same order. Proposed technique has been integrated with Detectron2, MMDetection and YOLOv5 models and it is publicly available at https://github.com/obss/sahi.git .

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 19 code samples harvested from 3 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 2 repositories, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 16 samples from 1 repository, 16 ran (16 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

fcakyon/sahi-benchmark officialmentioned in papermentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
obss/sahi officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
Kazuhito00/sahi-yolox-onnx-sample Syntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
Resham-Sundar/sahi-yolox MITSyntology: 16 samples, 16 ran (0 instrument-failed) · 0 unverified report
airctic/icevision pytorchApache-2.0Syntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

19 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran; the contract check could not run
17ran
1unverified

Licence: 0 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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.

fcakyon/sahi-benchmark official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_ordered_image_name_list xview/xview_to_coco.py ran MIT (permissive) · d0520a0e6473e8cc · report fixture: signature image_name_to_annotation_ind:dict/0/? · returned list · level recorded 2026-09-24
obss/sahi official repository 2 samples, 1 ran (1 instrument-failed) · 1 unverified
annotation_inside_slice sahi/slicing.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 52989f234436027c · report fixture: signature annotation:dict/0/?, slice_bbox:list/1/int · returned bool · level recorded 2026-09-22
get_slice_bboxes sahi/slicing.py unverified MIT (permissive) · 7fc4f6b132018cc2 · report
Resham-Sundar/sahi-yolox community (archive-listed) 16 samples, 16 ran (0 instrument-failed) · 0 unverified
annotation_inside_slice sahi/slicing.py ran MIT (permissive) · e257047ab1fda46c · report fixture: signature annotation:dict/0/?, slice_bbox:list/1/int · returned bool · level recorded 2026-09-24
batched_greedy_nmm sahi/postprocess/combine.py ran MIT (permissive) · b54053e66ee738d8 · report fixture: signature object_predictions_as_tensor:Tensor/2/float, match_metric:str/0/str, match_threshold:float/0/float · returned dict · level recorded 2026-09-24
batched_nms in 29 papers sahi/postprocess/combine.py ran MIT (permissive) · 8ed0517756dd1b38 · report fixture: signature predictions:Tensor/2/float, match_metric:str/0/str, match_threshold:float/0/float · returned list · level recorded 2026-09-24
calculate_box_union sahi/postprocess/utils.py ran MIT (permissive) · 686cde694bfeddb7 · report fixture: signature box1:list/1/int, box2:list/1/int · returned list · level recorded 2026-09-24
fix_full_shape_list sahi/utils/compatibility.py ran MIT (permissive) · 4b5d7326bb4f1646 · report fixture: signature full_shape_list:list/1/int · returned list · level recorded 2026-09-24
fix_shift_amount_list sahi/utils/compatibility.py ran MIT (permissive) · abc6663a9ae9fce0 · report fixture: signature shift_amount_list:list/1/float · returned list · level recorded 2026-09-24
get_slice_bboxes sahi/slicing.py ran MIT (permissive) · 0e3c82c0dee22fd7 · report fixture: signature image_height:int/0/int, image_width:int/0/int, slice_height:int/0/int, slice_width:int/0/int, overlap_height_ratio:float/0/float, overlap_width_ratio:float/0/float · returned list · level recorded 2026-09-24
merge in 85 papers sahi/utils/coco.py ran MIT (permissive) · 4d47f766c74c1466 · report fixture: signature coco_dict1:dict/0/?, coco_dict2:dict/0/?, desired_name2id:dict/0/? · returned dict · level recorded 2026-09-24
merge_from_list sahi/utils/coco.py ran MIT (permissive) · 4ab401060d4dd491 · report fixture: signature coco_dict_list:list/1/dict, desired_name2id:dict/0/?, verbose:int/0/int · returned dict · level recorded 2026-09-24
nms in 65 papers sahi/postprocess/combine.py ran MIT (permissive) · 272238bc5ffeef61 · report fixture: signature predictions:Tensor/2/float, match_metric:str/0/str, match_threshold:float/0/float · returned list · level recorded 2026-09-24
object_prediction_list_to_numpy sahi/postprocess/utils.py ran MIT (permissive) · 1c10c8ef13619529 · report fixture: signature object_prediction_list:ObjectPredictionList/0/? · returned ndarray · level recorded 2026-09-24
object_prediction_list_to_torch sahi/postprocess/utils.py ran MIT (permissive) · 2de419bb83449d6e · report fixture: signature object_prediction_list:ObjectPredictionList/0/? · returned Tensor · level recorded 2026-09-24
read_image in 73 papers sahi/utils/cv.py ran MIT (permissive) · 7a2ae5c4bf39dd82 · report fixture: signature image_path:str/0/str · returned ndarray · level recorded 2026-09-24
read_image_as_pil sahi/utils/cv.py ran MIT (permissive) · c8c3e5a8345b053a · report fixture: signature image:Image/0/?, exif_fix:bool/0/bool · returned Image · level recorded 2026-09-24
read_large_image sahi/utils/cv.py ran MIT (permissive) · 91ba8065c40815aa · report fixture: signature image_path:str/0/str · returned tuple · level recorded 2026-09-24
update_categories sahi/utils/coco.py ran MIT (permissive) · ece1ba05d166226f · report fixture: signature desired_name2id:dict/0/?, coco_dict:dict/0/? · returned dict · level recorded 2026-09-24

Tasks

ObjectObject DetectionSmall Object Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionFCOSFPNNon Maximum SuppressionVFNetVarifocal Loss

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