Home › Code › batch_sigmoid_ce_loss

batch_sigmoid_ce_loss

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

batch_sigmoid_ce_loss appears in the code Syntology harvested for 48 papers, as 3 distinct code bodies found in 48 places (a place is one code body under one paper). At least one of them ran in 2 of the papers; 0 of the code bodies carry 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 batch_sigmoid_ce_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 1 of the 3 distinct code bodies named batch_sigmoid_ce_loss; 2 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

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

Licence is a property of each copy, so it is counted per place: 10 of the 48 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

48 papers shown of 48, newest first; 48 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; 5 papers have no page here and are shown by arXiv id only. 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
Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation added by Syntology 2025-08 (from id) JiahuaDong/HVPL/hvpl/modeling/vita_matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation 17 Jul 2025 HuangShiqi128/SCORE/score/modeling/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
Disentangling Instance and Scene Contexts for 3D Semantic Scene Completion 11 Jul 2025 Enyu-Liu/DISC/maskdino/models/matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning 27 Jun 2025 geshang777/FOCUS/focus/modeling/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
Towards In-the-wild 3D Plane Reconstruction from a Single Image 3 Jun 2025 jcliu0428/ZeroPlane/ZeroPlane/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation 4 Dec 2024 ruohaoguo/avis/avism/modeling/avism_matcher.py 1edd24985036b0bf unverified MIT (permissive)
A Simple Image Segmentation Framework via In-Context Examples 7 Oct 2024 aim-uofa/SINE/sine/model/matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model 2 Aug 2024 jinyang06/SamGOP/maskGOP/modeling/detr_matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects 23 Jul 2024 ProvenceStar/PartGLEE/projects/PartGLEE/partglee/models/matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Part2Object: Hierarchical Unsupervised 3D Instance Segmentation 14 Jul 2024 chengshiest/part2object/models/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing 14 Jun 2024 slonetime/EBSeg/ebseg/model/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation 23 Apr 2024 abhishekaich27/proscale-pytorch/mask2former/modeling/matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation 4 Apr 2024 heshuting555/DsHmp/dshmp/modeling/vita_matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
PEM: Prototype-based Efficient MaskFormer for Image Segmentation 29 Feb 2024 niccolocavagnero/pem/pem/modeling/matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
UniVS: Unified and Universal Video Segmentation with Prompts as Queries 28 Feb 2024 minghanli/univs/univs/modeling/video_matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Supervised Fine-tuning in turn Improves Visual Foundation Models 18 Jan 2024 tencentarc/visft/mmf/models/visft/segment_matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
ODIN: A Single Model for 2D and 3D Segmentation 4 Jan 2024 ayushjain1144/odin/odin/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Fully Sparse 3D Occupancy Prediction 28 Dec 2023 mcg-nju/sparseocc/models/matcher.py 7e8e2bcfcb2b11e8 ran Apache-2.0 (permissive)
Collaborating Foundation Models for Domain Generalized Semantic Segmentation 15 Dec 2023 yasserben/clouds/clouds/modeling/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
General Object Foundation Model for Images and Videos at Scale 14 Dec 2023 FoundationVision/GLEE/projects/GLEE/glee/models/matcher.py 1edd24985036b0bf unverified MIT (permissive)
TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation 11 Dec 2023 rkzheng99/TMT-VIS/tmt/modeling/tmt_matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Open-Vocabulary Segmentation with Semantic-Assisted Calibration 7 Dec 2023 workforai/scan/scan/modeling/matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Mask Propagation for Efficient Video Semantic Segmentation 29 Oct 2023 ziplab/MPVSS/mask2former/modeling/matcher.py 1edd24985036b0bf unverified no licence file found · pointer only
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation 30 Sep 2023 jiaosiyu1999/MAFT-Plus/maft/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
3D Indoor Instance Segmentation in an Open-World 25 Sep 2023 aminebdj/3D-OWIS/models/matcher.py 1edd24985036b0bf unverified MIT (permissive)
MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions 16 Aug 2023 henghuiding/MeViS/lmpm/modeling/vita_matcher.py 1edd24985036b0bf unverified MIT (permissive)
SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning 12 Aug 2023 aim-uofa/segprompt/mask2former/modeling/matcher.py 1edd24985036b0bf unverified BSD-2-Clause (permissive)
Symphonize 3D Semantic Scene Completion with Contextual Instance Queries 27 Jun 2023 hustvl/symphonies/maskdino/models/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation 19 Jun 2023 heshuting555/PADing/PADing/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models 15 Jun 2023 IDEA-Research/OpenSeeD/openseed/modules/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation 12 Jun 2023 tacju/compositor/Compositor_Mask2Former/compositor/modeling/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
DFormer: Diffusion-guided Transformer for Universal Image Segmentation 6 Jun 2023 cp3wan/dformer/dformer/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Complementary Random Masking for RGB-Thermal Semantic Segmentation 30 Mar 2023 UkcheolShin/CRM_RGBTSeg/models/mask2former/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Mask-Free Video Instance Segmentation 28 Mar 2023 syscv/maskfreevis/mask2former/modeling/matcher.py 0528a6d568ba0384 unverified Apache-2.0 (permissive)
FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation 15 Mar 2023 junjiehe96/fastinst/fastinst/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Side Adapter Network for Open-Vocabulary Semantic Segmentation 23 Feb 2023 blumenstiel/SAN-MESS/san/model/matcher.py 1edd24985036b0bf unverified MIT (permissive)
OneFormer: One Transformer to Rule Universal Image Segmentation 10 Nov 2022 SHI-Labs/OneFormer/oneformer/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation 6 Oct 2022 jonasschult/mask3d/models/matcher.py 1edd24985036b0bf unverified MIT (permissive)
VITA: Video Instance Segmentation via Object Token Association 9 Jun 2022 sukjunhwang/vita/vita/modeling/vita_matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation 8 Mar 2022 facebookresearch/Mask2Former/mask2former/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection 7 Mar 2022 IDEACVR/MaskDINO/maskdino/modeling/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
Mask2Former for Video Instance Segmentation 20 Dec 2021 nihalsid/mask2former/mask2former/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
Masked-attention Mask Transformer for Universal Image Segmentation 2 Dec 2021 DdeGeus/Mask2Former-IBS/mask2former/modeling/matcher.py 1edd24985036b0bf unverified MIT (permissive)
arXiv:Zhang_Uni-3D_A_Universal_Model_for_Panoptic_3D_Scene_Reconstruction_ICCV_2023_paper mlpc-ucsd/Uni-3D/uni_3d/modeling/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
arXiv:Zhang_FreePoint_Unsupervised_Point_Cloud_Instance_Segmentation_CVPR_2024_paper zzk273/FreePoint/models/matcher_freepoint.py 1edd24985036b0bf unverified MIT (permissive)
arXiv:Li_Mask_DINO_Towards_a_Unified_Transformer-Based_Framework_for_Object_Detection_CVPR_2023_paper IDEA-Research/MaskDINO/maskdino/modeling/matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
arXiv:Heo_A_Generalized_Framework_for_Video_Instance_Segmentation_CVPR_2023_paper miranheo/GenVIS/genvis/modeling/genvis_matcher.py 1edd24985036b0bf unverified Apache-2.0 (permissive)
arXiv:03570 MCG-NJU/SparseOcc/models/matcher.py 7e8e2bcfcb2b11e8 ran Apache-2.0 (permissive)

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