Methods › General › Self-Supervised Learning › Jigsaw
Jigsaw
Introduced by Mehdi Noroozi et al. in Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Jigsaw is a self-supervision approach that relies on jigsaw-like puzzles as the pretext task in order to learn image representations.
In Syntology about another paper, arXiv:2305.17975: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: mentioned on GitHub). About another paper: this answer is about arXiv:2305.17975, while the archive credits arXiv:1603.09246.
From the lookup's note on this name: The same name also belongs to the paper “Jigsaw: Large Language Models meet Program Synthesis” (arXiv:2112.02969, 262 citations), which the lookup finds cited far more than the paper this answer is about (41 citations), so this answer may be about a different sense of the name. For arXiv:2112.02969: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2305.17975 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 140 · with a code link: 55 · where Syntology ran a sample: 13 (13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (13 of 140 tagged: 13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 140, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Learning Distributions over Permutations and Rankings with Factorized Representations 30 May 2025 · 0 repositories · arXiv:2505.24664
-
Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles 29 May 2025 · 1 repository · arXiv:2505.23590
-
ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations 20 May 2025 · 0 repositories · arXiv:2505.14404
-
LLM-based Semantic Augmentation for Harmful Content Detection 22 Apr 2025 · 0 repositories · arXiv:2504.15548
-
ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps 13 Apr 2025 · 0 repositories · arXiv:2504.09608
-
Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTM 14 Mar 2025 · 0 repositories · arXiv:2503.11084
-
A Generic Hybrid Framework for 2D Visual Reconstruction 31 Jan 2025 · 0 repositories · arXiv:2501.19325
-
HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation 25 Dec 2024 · 1 repository · arXiv:2412.18738
-
Enhancing Visual Reasoning with Autonomous Imagination in Multimodal Large Language Models 27 Nov 2024 · 0 repositories · arXiv:2411.18142
-
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation 22 Oct 2024 · 1 repository · arXiv:2410.16606
-
Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models 15 Oct 2024 · 1 repository · arXiv:2410.11459
-
SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups 3 Oct 2024 · 2 repositories · arXiv:2410.02942Syntology community repositories only · 44 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 34 where Syntology's instrument failed) · 3 unverified (of 47 harvested samples) · 47 pointer-only (licence)
-
Tiny-Toxic-Detector: A compact transformer-based model for toxic content detection 29 Aug 2024 · 0 repositories · arXiv:2409.02114
-
Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervision 1 Jul 2024 · 1 repository · arXiv:2407.01518Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition 28 Jun 2024 · 1 repository · arXiv:2406.19931Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
Enhancing Precision in Tactile Internet-Enabled Remote Robotic Surgery: Kalman Filter Approach 6 Jun 2024 · 0 repositories · arXiv:2406.04503
-
Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence 5 Jun 2024 · 0 repositories · arXiv:2406.10242
-
Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers 10 Apr 2024 · 1 repository · arXiv:2404.07292Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation 8 Apr 2024 · 0 repositories · arXiv:2404.05143
-
Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection 18 Mar 2024 · 0 repositories · arXiv:2403.12172
-
Self-Supervision in Time for Satellite Images(S3-TSS): A novel method of SSL technique in Satellite images 7 Mar 2024 · 1 repository · arXiv:2403.04859
-
Collaborative Learning with Artificial Intelligence Speakers (CLAIS): Pre-Service Elementary Science Teachers' Responses to the Prototype 20 Dec 2023 · 0 repositories · arXiv:2401.05400
-
Rethinking Model Inversion Attacks With Patch-Wise Reconstruction 12 Dec 2023 · 0 repositories · arXiv:2312.07040
-
Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation 4 Dec 2023 · 1 repository · arXiv:2312.01648Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models 29 Nov 2023 · 0 repositories · arXiv:2311.17919
-
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models 19 Nov 2023 · 1 repository · arXiv:2311.11202Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified (of 17 harvested samples) · 17 pointer-only (licence)
-
The possibility of making $138,000 from shredded banknote pieces using computer vision 17 Nov 2023 · 0 repositories · arXiv:2401.06133
-
SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects 11 Nov 2023 · 1 repository · arXiv:2311.06504
-
Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering 27 Oct 2023 · 0 repositories · arXiv:2310.17869
-
Jigsaw: Supporting Designers to Prototype Multimodal Applications by Chaining AI Foundation Models 12 Oct 2023 · 0 repositories · arXiv:2310.08574
-
How toxic is antisemitism? Potentials and limitations of automated toxicity scoring for antisemitic online content 5 Oct 2023 · 0 repositories · arXiv:2310.04465
-
On the definition of toxicity in NLP 3 Oct 2023 · 0 repositories · arXiv:2310.02357
-
A Survey on Physics Informed Reinforcement Learning: Review and Open Problems 5 Sep 2023 · 0 repositories · arXiv:2309.01909
-
Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image Classification 10 Aug 2023 · 1 repository · arXiv:2308.05770
-
Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks 4 Aug 2023 · 0 repositories · arXiv:2308.02729
-
Mixture of Self-Supervised Learning 27 Jul 2023 · 1 repository · arXiv:2307.14897
-
Fast Full-frame Video Stabilization with Iterative Optimization 24 Jul 2023 · 1 repository · arXiv:2307.12774
-
Digital Twin-Enhanced Wireless Indoor Navigation: Achieving Efficient Environment Sensing with Zero-Shot Reinforcement Learning 11 Jun 2023 · 1 repository · arXiv:2306.06766Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
Human-imperceptible, Machine-recognizable Images 6 Jun 2023 · 1 repository · arXiv:2306.03679
-
Jigsaw: Learning to Assemble Multiple Fractured Objects 29 May 2023 · 1 repository · arXiv:2305.17975Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
Identity-Guided Collaborative Learning for Cloth-Changing Person Reidentification 10 Apr 2023 · 0 repositories · arXiv:2304.04400
-
Multi-Phase Relaxation Labeling for Square Jigsaw Puzzle Solving 26 Mar 2023 · 0 repositories · arXiv:2303.14793
-
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training 23 Mar 2023 · 1 repository · arXiv:2303.13510
-
A Dual-branch Self-supervised Representation Learning Framework for Tumour Segmentation in Whole Slide Images 20 Mar 2023 · 2 repositories · arXiv:2303.11019
-
Analysis of Deep Image Quality Models 26 Feb 2023 · 0 repositories · arXiv:2302.13345
-
Alphazzle: Jigsaw Puzzle Solver with Deep Monte-Carlo Tree Search 1 Feb 2023 · 0 repositories · arXiv:2302.00384
-
Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI 5 Jan 2023 · 1 repository · arXiv:2301.01874
-
Benchmark for Uncertainty & Robustness in Self-Supervised Learning 23 Dec 2022 · 1 repository · arXiv:2212.12411
-
Block Selection Method for Using Feature Norm in Out-of-distribution Detection 5 Dec 2022 · 1 repository · arXiv:2212.02295Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples)
-
Edge2Vec: A High Quality Embedding for the Jigsaw Puzzle Problem 14 Nov 2022 · 0 repositories · arXiv:2211.07771
-
Enhancing Deep Learning Performance of Massive MIMO CSI Feedback 24 Aug 2022 · 1 repository · arXiv:2208.11333
-
Learning Primitive-aware Discriminative Representations for Few-shot Learning 20 Aug 2022 · 0 repositories · arXiv:2208.09717
-
Test-time Training for Data-efficient UCDR 19 Aug 2022 · 1 repository · arXiv:2208.09198
-
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer 25 Jul 2022 · 1 repository · arXiv:2207.11971
-
Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles 20 Jul 2022 · 1 repository · arXiv:2207.10172
-
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection 16 Jul 2022 · 0 repositories · arXiv:2207.08003
-
Which one is more toxic? Findings from Jigsaw Rate Severity of Toxic Comments 27 Jun 2022 · 0 repositories · arXiv:2206.13284
-
JigsawHSI: a network for Hyperspectral Image classification 6 Jun 2022 · 1 repository · arXiv:2206.02327
-
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers 25 May 2022 · 1 repository · arXiv:2205.12551
-
GMSS: Graph-Based Multi-Task Self-Supervised Learning for EEG Emotion Recognition 12 Apr 2022 · 1 repository · arXiv:2205.01030
-
Relaxation Labeling Meets GANs: Solving Jigsaw Puzzles with Missing Borders 28 Mar 2022 · 0 repositories · arXiv:2203.14428
-
Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions 28 Mar 2022 · 1 repository
-
elBERto: Self-supervised Commonsense Learning for Question Answering 17 Mar 2022 · 0 repositories · arXiv:2203.09424
-
Measuring Fairness of Text Classifiers via Prediction Sensitivity 16 Mar 2022 · 0 repositories · arXiv:2203.08670
-
TEN: Twin Embedding Networks for the Jigsaw Puzzle Problem with Eroded Boundaries 12 Mar 2022 · 0 repositories · arXiv:2203.06488
-
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers 22 Feb 2022 · 0 repositories · arXiv:2202.11176
-
Beyond NaN: Resiliency of Optimization Layers in The Face of Infeasibility 13 Feb 2022 · 1 repository · arXiv:2202.06242
-
Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers 11 Feb 2022 · 0 repositories · arXiv:2202.05470
-
Self Semi Supervised Neural Architecture Search for Semantic Segmentation 29 Jan 2022 · 0 repositories · arXiv:2201.12646
-
Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions 1 Dec 2021 · 0 repositories
-
Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models 25 Nov 2021 · 0 repositories · arXiv:2111.13259
-
Efficient Anomaly Detection Using Self-Supervised Multi-Cue Tasks 24 Nov 2021 · 0 repositories · arXiv:2111.12379
-
Doing More by Doing Less: How Structured Partial Backpropagation Improves Deep Learning Clusters 20 Nov 2021 · 1 repository · arXiv:2111.10672
-
Measuring Fairness of Text Classifiers via Prediction Sensitivity 16 Nov 2021 · 0 repositories
-
Structure-Preserving Image Super-Resolution 26 Sep 2021 · 1 repository · arXiv:2109.12530
-
Model Bias in NLP -- Application to Hate Speech Classification using transfer learning techniques 20 Sep 2021 · 0 repositories · arXiv:2109.09725
-
ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets 31 Aug 2021 · 1 repository · arXiv:2108.13939
-
How Self-Supervised Learning Can be Used for Fine-Grained Head Pose Estimation? 10 Aug 2021 · 0 repositories · arXiv:2108.04893
-
P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening 9 Aug 2021 · 1 repository · arXiv:2108.03815
-
Self-Supervised Learning for Fine-Grained Image Classification 29 Jul 2021 · 1 repository · arXiv:2107.13973
-
Amodal segmentation just like doing a jigsaw 15 Jul 2021 · 0 repositories · arXiv:2107.07464
-
Graph Jigsaw Learning for Cartoon Face Recognition 14 Jul 2021 · 1 repository · arXiv:2107.06532
-
Crossing Cuts Polygonal Puzzles: Models and Solvers 19 Jun 2021 · 0 repositories
-
Self-Supervised Learning for Fine-Grained Visual Categorization 18 May 2021 · 1 repository · arXiv:2105.08788
-
Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation 13 May 2021 · 0 repositories · arXiv:2105.06421
-
Distill on the Go: Online knowledge distillation in self-supervised learning 20 Apr 2021 · 1 repository · arXiv:2104.09866Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
A recipe for annotating grounded clarifications 18 Apr 2021 · 0 repositories · arXiv:2104.08964
-
UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detection 17 Apr 2021 · 0 repositories · arXiv:2104.08635
-
Jigsaw Clustering for Unsupervised Visual Representation Learning 1 Apr 2021 · 1 repository · arXiv:2104.00323
-
A Neighbourhood Framework for Resource-Lean Content Flagging 31 Mar 2021 · 0 repositories · arXiv:2103.17055
-
TransReID: Transformer-based Object Re-Identification 8 Feb 2021 · 4 repositories · arXiv:2102.04378
-
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution 6 Feb 2021 · 0 repositories · arXiv:2102.03671
-
JigsawGAN: Auxiliary Learning for Solving Jigsaw Puzzles with Generative Adversarial Networks 19 Jan 2021 · 0 repositories · arXiv:2101.07555
-
Data-Free Universal Adversarial Perturbation and Black-Box Attack 1 Jan 2021 · 0 repositories
-
Self-Supervised Video Representation Learning with Constrained Spatiotemporal Jigsaw 1 Jan 2021 · 0 repositories
-
Self-supervised Learning with Fully Convolutional Networks 18 Dec 2020 · 0 repositories · arXiv:2012.10017
-
Learning Heatmap-Style Jigsaw Puzzles Provides Good Pretraining for 2D Human Pose Estimation 13 Dec 2020 · 0 repositories · arXiv:2012.07101
-
Real-time Surgical Environment Enhancement for Robot-Assisted Minimally Invasive Surgery Based on Super-Resolution 8 Nov 2020 · 0 repositories · arXiv:2011.04003
-
Learning Visual Representations for Transfer Learning by Suppressing Texture 3 Nov 2020 · 1 repository · arXiv:2011.01901
-
Improving Classification through Weak Supervision in Context-specific Conversational Agent Development for Teacher Education 23 Oct 2020 · 0 repositories · arXiv:2010.12710
Tasks archive 2025-07-28
20 shown of 160 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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