Home › Code › focal_loss

focal_loss

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

focal_loss appears in the code Syntology harvested for 65 papers, as 46 distinct code bodies found in 66 places (a place is one code body under one paper). Of the 65 papers, 58 with a sample that ran: 33 with a run with no instrument failure, 25 where every run was a failure of Syntology's instrument. 9 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 focal_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; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

The 46 distinct code bodies named focal_loss: 40 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 0 violated, 27 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. One tile per status, in the site's fixed vocabulary, each code body counted once:

2ran · honoured contract
0ran · violated contract
6ran · our draft was wrong
5ran; the contract check could not run
27ran
6unverified
9fingerprinted

Licence is a property of each copy, so it is counted per place: 29 of the 66 places are pointer only (Syntology does not serve that copy's text); at 9 of those this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). 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 “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) 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; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Papers

65 papers shown of 65, newest first; 66 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; 2 papers have no page here and are shown by their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). 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. 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.

PaperDateFileStatus SyntologyLicence
CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels added by Syntology 2026-05 (from id) identical code first harvested elsewhere 4dcf06ba28983266 ran · our draft was wrong fingerprinted licence of this copy not recorded
A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscation added by Syntology 2026-05 (from id) sjmeis/DP-Decompose-Distribute/eval_scripts/adaptive_attacker.py fd41c5fa76336833 ran MIT (permissive)
Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise added by Syntology 2026-04 (from id) YuanjieSh/CMRM/Multi_code_synthetic_noise/train/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants added by Syntology 2026-03 (from id) bhosalems/FairLLaVA/llava/model/language_model/llava_llama.py c48f90c323496675 ran · our draft was wrong licence not identified · pointer only
Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning added by Syntology 2026-03 (from id) doem97/metalora/utils/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs 19 May 2025 case-lab-umd/llm-auditing-coin/3_Block2Answer/train/loss_func.py d00ea9e4c5542ee7 ran MIT (permissive)
Single-Channel EEG Tokenization Through Time-Frequency Modeling 22 Feb 2025 Jathurshan0330/TFM-Tokenizer/utils/utils.py 4156bae98d1b1972 ran MIT (permissive)
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition 28 Oct 2024 Keke921/GNM-PT/loss.py 1b3f82e6c53766e7 ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities 18 Oct 2024 haoosz/BiGR/bae/binarylatent.py 3164da5cbc56c361 ran MIT (permissive)
LTRL: Boosting Long-tail Recognition via Reflective Learning 17 Jul 2024 fistyee/LTRL/model/loss.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted no licence file found · pointer only
Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model 18 Jun 2024 shijxcs/candle/trainers/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted no licence file found · pointer only
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration 10 Jun 2024 yuanjiesh/rc3p/train/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioning 7 Jun 2024 yilinliu77/nvdnet/python/model.py b20bcef51505bcf4 ran GPL-3.0 (copyleft) · pointer only
Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning 20 May 2024 Gank0078/FineSSL/utils/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted no licence file found · pointer only
DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection 3 Apr 2024 tumftm/dpft/src/dprt/training/loss.py abd213a9f852803b ran Apache-2.0 (permissive)
ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning 29 Mar 2024 clovaai/ECLIPSE/continual/method_wrapper/loss.py b9edb542ddeedb32 ran licence not identified · pointer only
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model 28 Mar 2024 zhicaiwww/diff-mix/downstream_tasks/losses.py 8770a72903df63a4 ran · our draft was wrong fingerprinted MIT (permissive)
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss 8 Feb 2024 ml-stat-sustech/convexconcaveloss/source/defenses/membership_inference/loss_function.py b6c954a2933604c5 ran · our draft was wrong no licence file found · pointer only
BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos 30 Nov 2023 Pilhyeon/BAM-DETR/bam_detr/misc.py fd215ad1001ab061 ran licence not identified · pointer only
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources 6 Nov 2023 tmlr-group/atol/utils/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted no licence file found · pointer only
Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection 4 Oct 2023 xydong127/rqgnn/lossfunc.py 128bf43313aa9f8a unverified no licence file found · pointer only
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts 18 Sep 2023 shijxcs/LIFT/utils/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted no licence file found · pointer only
Referring Image Segmentation Using Text Supervision 28 Aug 2023 fawnliu/tris/model/model_stage1.py cb29cf6c7fa94676 ran fingerprinted MIT (permissive)
Class-Imbalanced Graph Learning without Class Rebalancing 27 Aug 2023 zhiningliu1998/bat/baselines/renode.py 6ccd040c4ef8720b ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive)
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition 19 Aug 2023 fistyee/mdcs/model/loss.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted no licence file found · pointer only
On the Transition from Neural Representation to Symbolic Knowledge 3 Aug 2023 chengjunyan1/TDL/TAE.py c1900ff852f0930d ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive)
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration 7 Jun 2023 emasa/balpoe-calibratedlt/model/loss.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
OVO: Open-Vocabulary Occupancy 25 May 2023 dzcgaara/OVO/ovo/loss/mask_matching_loss.py 3a8c2b6651437097 ran Apache-2.0 (permissive)
Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment 19 May 2023 identical code first harvested elsewhere 1b3f82e6c53766e7 ran · honoured contract fingerprinted licence of this copy not recorded
Feature-Balanced Loss for Long-Tailed Visual Recognition 18 May 2023 juyongjiang/fbl/loss.py 1b3f82e6c53766e7 ran · honoured contract fingerprinted no licence file found · pointer only
Decoupled Training for Long-Tailed Classification With Stochastic Representations 19 Apr 2023 kaidic/LDAM-DRW/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation 3 Apr 2023 identical code first harvested elsewhere 1b3f82e6c53766e7 ran · honoured contract fingerprinted licence of this copy not recorded
TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation 17 Mar 2023 devavratTomar/TeSLA/losses/seg_losses.py 0748e29a637d95ec ran MIT (permissive)
Revisiting adversarial training for the worst-performing class 17 Feb 2023 lions-epfl/class-focused-online-learning-code/cfol/focal_loss.py 4bebda9ddfdffe0a unverified MIT (permissive)
MovieCLIP: Visual Scene Recognition in Movies 20 Oct 2022 usc-sail/mica-MovieCLIP/losses/loss_functions.py 4bebda9ddfdffe0a unverified MIT (permissive)
Behavior Transformers: Cloning $k$ modes with one stone 22 Jun 2022 notmahi/bet/models/libraries/loss_fn.py f840d01c761c3844 ran MIT (permissive)
Masked-attention Mask Transformer for Universal Image Segmentation 2 Dec 2021 DdeGeus/Mask2Former-IBS/mask2former/modeling/criterion.py 2bb4c1887f16e1ba ran fingerprinted MIT (permissive)
Topology-Imbalance Learning for Semi-Supervised Node Classification 8 Oct 2021 victorchen96/renode/transductive/imb_loss.py 6ccd040c4ef8720b ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive)
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition 20 Jul 2021 Vanint/TADE-AgnosticLT/model/loss.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation 12 May 2021 L-A-Sandhu/Swin-Unet-/src/swin_transformer/AUC_LOSS.py dc39ed696312e230 ran MIT (permissive)
DeepI2P: Image-to-Point Cloud Registration via Deep Classification 8 Apr 2021 lijx10/DeepI2P/models/focal_loss.py 36d967d4eb8179d5 ran MIT (permissive)
One-Shot Medical Landmark Detection 8 Mar 2021 Curli-quan/oneshot-medical-landmark/scripts/self_train.py eb19c575ed458088 ran · honoured contract fingerprinted Apache-2.0 (permissive)
Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data 3 Nov 2020 Mvrjustid/IMWUT-Hierarchical-HAR-PBD/code/utils.py 6853f6c77c17fc20 ran MIT (permissive)
Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection 22 Oct 2020 lucastabelini/LaneATT/lib/focal_loss.py 2e1fffb767af25e4 ran MIT (permissive)
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model 10 Jun 2020 BoPang1996/TubeTK/network/focal_loss.py 0d548c0e307771fa ran MIT (permissive)
SEKD: Self-Evolving Keypoint Detection and Description 9 Jun 2020 aliyun/Self-Evolving-Keypoint-Demo/loss/loss_focal.py deb13554676659ec ran MIT recorded; this copy not marked cleared · pointer only
Single-Stage Semantic Segmentation from Image Labels 16 May 2020 visinf/1-stage-wseg/models/stage_net.py cb29cf6c7fa94676 ran fingerprinted Apache-2.0 (permissive)
UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation 19 Apr 2020 hamidriasat/UNet-3-Plus/losses/loss.py 7b23f6df494f23b1 ran MIT (permissive)
Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data 11 Apr 2020 EIDOSlab/unveiling-covid19-from-cxr/train-covid-classifier.py 04198a019f317705 ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only
End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning 21 Mar 2020 cjy1992/detect-loc-map/perception_driving/networks/sequential_latent_pixor_network.py 67e87c930497a29b ran MIT (permissive)
Detection in Crowded Scenes: One Proposal, Multiple Predictions 20 Mar 2020 Purkialo/CrowdDet/lib/det_oprs/loss_opr.py f2466bea04ccb88b unverified MIT (permissive)
Learning Modulated Loss for Rotated Object Detection 19 Nov 2019 Mrqianduoduo/RSDet-8P-4R/libs/losses/losses.py e57f95591345ae49 ran Apache-2.0 (permissive)
FreeAnchor: Learning to Match Anchors for Visual Object Detection 5 Sep 2019 zhangxiaosong18/FreeAnchor/maskrcnn_benchmark/modeling/rpn/free_anchor_loss.py b4392a86bb773ddd ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive)
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss 18 Jun 2019 ihaeyong/maximum-margin-ldam/losses.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Objects as Points 16 Apr 2019 xuannianz/keras-CenterNet/losses.py ca7ad1a4c7d4631d unverified Apache-2.0 (permissive)
FCOS: Fully Convolutional One-Stage Object Detection 2 Apr 2019 srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/models/fcos/losses.py fce50f2fda34fc22 ran Apache-2.0 (permissive)
Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression 20 Mar 2019 mauriceqch/pcc_geo_cnn/src/focal_loss.py 427c81f065a9770a ran MIT (permissive)
ParticleNet: Jet Tagging via Particle Clouds 22 Feb 2019 hqucms/weaver-core/weaver/nn/loss/focal.py 22cdb78ad8aed2f6 ran MIT (permissive)
Class-Balanced Loss Based on Effective Number of Samples 16 Jan 2019 vandit15/Class-balanced-loss-pytorch/class_balanced_loss.py c32ccdb4e101c470 unverified MIT (permissive)
Representation Learning with Contrastive Predictive Coding 10 Jul 2018 ex4sperans/freesound-classification/networks/losses.py 25b22350f74af590 ran fingerprinted Apache-2.0 (permissive)
Learning a Discriminative Feature Network for Semantic Segmentation 25 Apr 2018 YuhuiMa/DFN-tensorflow/losses.py 8acbd47e113d2681 unverified Apache-2.0 (permissive)
Focal Loss for Dense Object Detection 7 Aug 2017 daveboat/pytorch_focal_loss/focalloss.py 6f5a902a2510561a ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only
Focal Loss for Dense Object Detection 7 Aug 2017 AdeelH/pytorch-multi-class-focal-loss/focal_loss.py aa6467d64911f0e4 ran · our draft was wrong MIT (permissive)
U-Net: Convolutional Networks for Biomedical Image Segmentation 18 May 2015 Jo-dsa/SemanticSeg/src/model.py 3c8319d0c4370678 ran · our draft was wrong fingerprinted no licence file found · pointer only
OpenReview id openreview_mJr1VDMOf2 Nebulae411/DGG-HMR/models/criterion.py a7e2bec8d2a4e3cf ran Apache-2.0 (permissive)
CVF open access id Aimar_Balanced_Product_of_Calibrated_Experts_for_Long-Tailed_Recognition_CVPR_2023_paper emasa/BalPoE-CalibratedLT/model/loss.py 4dcf06ba28983266 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is 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 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 under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. 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