Home › Code › smooth_l1_loss

smooth_l1_loss

Syntologyentry name in harvested coderead from the graph 2026-09-24

smooth_l1_loss appears in the code Syntology harvested for 28 papers, as 12 distinct code bodies found in 28 places (a place is one code body under one paper). At least one of them ran in 20 of the papers; 1 of the code bodies carries a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named smooth_l1_loss do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 4 of the 12 distinct code bodies named smooth_l1_loss; 8 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
0ran · fixture could not drive it
2ran
8unverified
1fingerprinted

Licence is a property of each copy, so it is counted per place: 12 of the 28 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

28 papers shown of 28, newest first; 28 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 1 papers added by Syntology. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Bonnet: Ultra-Fast Whole-Body Bone Segmentation from CT Scans added by Syntology 2026-01 (from id) HINTLab/Bonnet/src/losses/bbox_loss.py 2d8d6b5c58e10cfc unverified Apache-2.0 (permissive)
Structured 3D Latents for Scalable and Versatile 3D Generation 2 Dec 2024 Microsoft/TRELLIS/trellis/utils/loss_utils.py c6ce2d5852baecaa unverified MIT (permissive)
Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli 3 Nov 2024 mtangemann/motion_energy_segmentation/motion_energy_segmentation/flow_former_plus_plus/_extern/core/loss.py 5464e22d6859392a unverified no licence file found · pointer only
Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection 16 Jul 2024 isee-laboratory/bpf/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT (permissive)
Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment 23 May 2024 msohaildanish/DivAlign/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT (permissive)
HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud 4 Apr 2024 cwc1260/HandDiff/network_handdiff.py f68d8fc37ba13577 ran · our draft was wrong MIT (permissive)
Adaptive Self-training Framework for Fine-grained Scene Graph Generation 18 Jan 2024 rlqja1107/torch-ST-SGG/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran no licence file found · pointer only
Unsupervised Domain Adaptive Detection with Network Stability Analysis 16 Aug 2023 tiankongzhang/nsa/detection/layers/losses.py aadb076657e5223e ran no licence file found · pointer only
Plane Geometry Diagram Parsing 19 May 2022 mingliangzhang2018/PGDP/geo_parse/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT (permissive)
Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling 24 Nov 2021 hbdat/cvpr22_cross_modal_pseudo_labeling/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only
Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity 27 Oct 2021 bcmi/tramas-weak-shot-object-detection/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only
Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection 27 Jul 2021 GXYM/TextBPN/network/Reg_loss.py be7c75a837a110ff unverified MIT (permissive)
Visual Distant Supervision for Scene Graph Generation 29 Mar 2021 thunlp/VisualDS/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT (permissive)
DRG: Dual Relation Graph for Human-Object Interaction Detection 26 Aug 2020 vt-vl-lab/DRG/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only
Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation 21 Jul 2020 SIAAAAAA/MMT-PSM/maskrcnn_benchmark/layers/smooth_l1_loss.py 33cbd9d01ff4d69e unverified MIT recorded; this copy not marked cleared · pointer only
Pillar-based Object Detection for Autonomous Driving 20 Jul 2020 WangYueFt/pillar-od/loss.py cf26f601b7f98582 unverified MIT (permissive)
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer 15 Jul 2020 mikuhatsune/wsod_transfer/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training 13 Apr 2020 hkzhang95/DynamicRCNN/dynamic_rcnn/det_opr/loss.py e261fa29066b37e5 ran MIT (permissive)
Learning to Segment the Tail 2 Apr 2020 JoyHuYY1412/LST_LVIS/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only
Detection in Crowded Scenes: One Proposal, Multiple Predictions 20 Mar 2020 Purkialo/CrowdDet/lib/det_oprs/loss_opr.py 80e2e1c046be957c unverified MIT (permissive)
DSGN: Deep Stereo Geometry Network for 3D Object Detection 10 Jan 2020 chenyilun95/DSGN/dsgn/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT (permissive)
Multiple Anchor Learning for Visual Object Detection 4 Dec 2019 DeLightCMU/MAL/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT (permissive)
FreeAnchor: Learning to Match Anchors for Visual Object Detection 5 Sep 2019 zhangxiaosong18/FreeAnchor/maskrcnn_benchmark/modeling/rpn/free_anchor_loss.py 13099e0dd83850a8 ran · our draft was wrong fingerprinted MIT (permissive)
FCOS: Fully Convolutional One-Stage Object Detection 2 Apr 2019 BIYTC/mobilenet_maskrcnn/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only
Res2Net: A New Multi-scale Backbone Architecture 2 Apr 2019 Res2Net/Res2Net-maskrcnn/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only
Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection 5 Mar 2019 zhixinwang/frustum-convnet/models/model_util.py ce156beb68c9daa3 unverified MIT (permissive)
Mask Scoring R-CNN 1 Mar 2019 zjhuang22/maskscoring_rcnn/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT (permissive)
Mask R-CNN 20 Mar 2017 facebookresearch/maskrcnn-benchmark/maskrcnn_benchmark/layers/smooth_l1_loss.py e261fa29066b37e5 ran MIT recorded; this copy not marked cleared · pointer only

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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