Home › Code › iou_loss

iou_loss

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

iou_loss appears in the code Syntology harvested for 17 papers, as 11 distinct code bodies found in 18 places (a place is one code body under one paper). At least one of them ran in 1 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 iou_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 11 distinct code bodies named iou_loss; 10 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
10unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 5 of the 18 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

17 papers shown of 17, newest first; 18 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 5 papers added by Syntology; 1 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
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation added by Syntology 2026-06 (from id) Dmmm1997/VideoSEG-O3/projects/open_r1/trainer/sam_loss.py e40a43378d8a1fb1 ran Apache-2.0 (permissive)
Conformal Risk Control for Non-Monotonic Losses added by Syntology 2026-02 (from id) aangelopoulos/nonmonotonic-crc/iou_tumor/utils.py 16d3e709eafdd6fc unverified no licence file found · pointer only
Towards Integrating Uncertainty for Domain-Agnostic Segmentation added by Syntology 2025-12 (from id) JesseBrouw/UncertSAM/src/loss_fns.py b719420230af3c51 unverified AGPL-3.0 (copyleft) · pointer only
Robust Ego-Exo Correspondence with Long-Term Memory added by Syntology 2025-10 (from id) juneyeeHu/LM-EEC/training/loss_fns.py b8f501ca29e77f1a unverified no licence file found · pointer only
UGround: Towards Unified Visual Grounding with Unrolled Transformers added by Syntology 2025-10 (from id) rui-qian/UGround/model/GSVA.py af6fc3d42a9de09a unverified Apache-2.0 (permissive)
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop 12 Mar 2025 vision-x-nyu/pisa-experiments/sam2/training/loss_fns.py b8f501ca29e77f1a unverified Apache-2.0 (permissive)
A Distractor-Aware Memory for Visual Object Tracking with SAM2 26 Nov 2024 jovanavidenovic/dam4sam/training/loss_fns.py b8f501ca29e77f1a unverified no licence file found · pointer only
Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning 15 Aug 2024 jinlab-imvr/surgical-sam-2/training/loss_fns.py b8f501ca29e77f1a unverified Apache-2.0 (permissive)
SAM 2: Segment Anything in Images and Videos 1 Aug 2024 bowang-lab/medsam2/training/loss_fns.py b8f501ca29e77f1a unverified Apache-2.0 (permissive)
GSVA: Generalized Segmentation via Multimodal Large Language Models 15 Dec 2023 leaplabthu/gsva/model/losses.py af6fc3d42a9de09a unverified Apache-2.0 (permissive)
Practical Deep Dispersed Watermarking with Synchronization and Fusion 23 Oct 2023 bytedance/dwsf/train_seg.py 71bc87e62bf2a521 unverified licence not identified · pointer only
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes 3 Feb 2023 henghuiding/MOSE-api/MOSEv2/sam2_rcms/training/loss_fns.py b8f501ca29e77f1a unverified MIT (permissive)
TALLFormer: Temporal Action Localization with a Long-memory Transformer 4 Apr 2022 klauscc/tallformer/AFSD/anet_video_cls/multisegment_loss.py e1f7c9eb71128188 unverified Apache-2.0 (permissive)
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model 10 Jun 2020 BoPang1996/TubeTK/network/utils.py 1bcb91317c367710 unverified MIT (permissive)
UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation 19 Apr 2020 hamidriasat/UNet-3-Plus/losses/loss.py 013ffa32c7802109 unverified MIT (permissive)
FCOS: Fully Convolutional One-Stage Object Detection 2 Apr 2019 srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/models/fcos/losses.py 5e47641ad906ae7b unverified Apache-2.0 (permissive)
FCOS: Fully Convolutional One-Stage Object Detection 2 Apr 2019 xytpai/fcos/libs/iou_loss.py dbd9612822534e83 unverified MIT (permissive)
arXiv:Xia_GSVA_Generalized_Segmentation_via_Multimodal_Large_Language_Models_CVPR_2024_paper LeapLabTHU/GSVA/model/losses.py af6fc3d42a9de09a unverified 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