{"url":"/method/jigsaw","slug":"jigsaw","name":"Jigsaw","full_name":"Jigsaw","full_name_withheld":false,"description_markdown":"**Jigsaw** is a self-supervision approach that relies on jigsaw-like puzzles as the pretext task in order to learn image representations.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","paper":"/paper/unsupervised-learning-of-visual-1","first_author":"Mehdi Noroozi","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/unsupervised-learning-of-visual-1"},"source":{"url":"http://arxiv.org/abs/1603.09246v3","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Self-Supervised Learning","url":"/methods/category/self-supervised-learning","pwc_aliases":[]}],"n_papers_tagged":140,"archive_num_papers":140,"papers_newest_first":[{"paper":null,"title":"Learning Distributions over Permutations and Rankings with Factorized Representations","date":"2025-05-30","arxiv_id":"2505.24664","n_code_links":0,"syntology":null},{"paper":"/paper/jigsaw-r1-a-study-of-rule-based-visual","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","date":"2025-05-29","arxiv_id":"2505.23590","n_code_links":1,"syntology":null},{"paper":null,"title":"ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations","date":"2025-05-20","arxiv_id":"2505.14404","n_code_links":0,"syntology":null},{"paper":null,"title":"LLM-based Semantic Augmentation for Harmful Content Detection","date":"2025-04-22","arxiv_id":"2504.15548","n_code_links":0,"syntology":null},{"paper":null,"title":"ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps","date":"2025-04-13","arxiv_id":"2504.09608","n_code_links":0,"syntology":null},{"paper":null,"title":"Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTM","date":"2025-03-14","arxiv_id":"2503.11084","n_code_links":0,"syntology":null},{"paper":null,"title":"A Generic Hybrid Framework for 2D Visual Reconstruction","date":"2025-01-31","arxiv_id":"2501.19325","n_code_links":0,"syntology":null},{"paper":"/paper/helpnet-hierarchical-perturbations","title":"HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation","date":"2024-12-25","arxiv_id":"2412.18738","n_code_links":1,"syntology":null},{"paper":null,"title":"Enhancing Visual Reasoning with Autonomous Imagination in Multimodal Large Language Models","date":"2024-11-27","arxiv_id":"2411.18142","n_code_links":0,"syntology":null},{"paper":"/paper/gala-graph-diffusion-based-alignment-with","title":"GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation","date":"2024-10-22","arxiv_id":"2410.16606","n_code_links":1,"syntology":null},{"paper":"/paper/jigsaw-puzzles-splitting-harmful-questions-to","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","date":"2024-10-15","arxiv_id":"2410.11459","n_code_links":1,"syntology":null},{"paper":"/paper/symmetricdiffusers-learning-discrete","title":"SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups","date":"2024-10-03","arxiv_id":"2410.02942","n_code_links":2,"syntology":{"ran":44,"of":47,"unverified":3,"pointer_only":47}},{"paper":null,"title":"Tiny-Toxic-Detector: A compact transformer-based model for toxic content detection","date":"2024-08-29","arxiv_id":"2409.02114","n_code_links":0,"syntology":null},{"paper":"/paper/towards-multimodal-open-set-domain","title":"Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervision","date":"2024-07-01","arxiv_id":"2407.01518","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":2}},{"paper":"/paper/decoupling-general-and-personalized-knowledge","title":"Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition","date":"2024-06-28","arxiv_id":"2406.19931","n_code_links":1,"syntology":{"ran":6,"of":7,"unverified":1,"pointer_only":7}},{"paper":null,"title":"Enhancing Precision in Tactile Internet-Enabled Remote Robotic Surgery: Kalman Filter Approach","date":"2024-06-06","arxiv_id":"2406.04503","n_code_links":0,"syntology":null},{"paper":null,"title":"Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence","date":"2024-06-05","arxiv_id":"2406.10242","n_code_links":0,"syntology":null},{"paper":"/paper/solving-masked-jigsaw-puzzles-with-diffusion","title":"Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers","date":"2024-04-10","arxiv_id":"2404.07292","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":2}},{"paper":null,"title":"Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation","date":"2024-04-08","arxiv_id":"2404.05143","n_code_links":0,"syntology":null},{"paper":null,"title":"Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","date":"2024-03-18","arxiv_id":"2403.12172","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervision-in-time-for-satellite-images","title":"Self-Supervision in Time for Satellite Images(S3-TSS): A novel method of SSL technique in Satellite images","date":"2024-03-07","arxiv_id":"2403.04859","n_code_links":1,"syntology":null},{"paper":null,"title":"Collaborative Learning with Artificial Intelligence Speakers (CLAIS): Pre-Service Elementary Science Teachers' Responses to the Prototype","date":"2023-12-20","arxiv_id":"2401.05400","n_code_links":0,"syntology":null},{"paper":null,"title":"Rethinking Model Inversion Attacks With Patch-Wise Reconstruction","date":"2023-12-12","arxiv_id":"2312.07040","n_code_links":0,"syntology":null},{"paper":"/paper/characterizing-large-language-model-geometry","title":"Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation","date":"2023-12-04","arxiv_id":"2312.01648","n_code_links":1,"syntology":{"ran":7,"of":13,"unverified":6,"pointer_only":13}},{"paper":null,"title":"Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models","date":"2023-11-29","arxiv_id":"2311.17919","n_code_links":0,"syntology":null},{"paper":"/paper/unmasking-and-improving-data-credibility-a","title":"Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models","date":"2023-11-19","arxiv_id":"2311.11202","n_code_links":1,"syntology":{"ran":13,"of":17,"unverified":4,"pointer_only":17}},{"paper":null,"title":"The possibility of making \\$138,000 from shredded banknote pieces using computer vision","date":"2023-11-17","arxiv_id":"2401.06133","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-context-learning-for-visual","title":"SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects","date":"2023-11-11","arxiv_id":"2311.06504","n_code_links":1,"syntology":null},{"paper":null,"title":"Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering","date":"2023-10-27","arxiv_id":"2310.17869","n_code_links":0,"syntology":null},{"paper":null,"title":"Jigsaw: Supporting Designers to Prototype Multimodal Applications by Chaining AI Foundation Models","date":"2023-10-12","arxiv_id":"2310.08574","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":30},{"task":"/task/representation-learning","name":"Representation Learning","papers":16},{"task":"/task/classification-1","name":"Classification","papers":11},{"task":"/task/image-classification","name":"Image Classification","papers":11},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":9},{"task":"/task/image-classification","name":"image-classification","papers":9},{"task":"/task/classification","name":"General Classification","papers":8},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":7},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":7},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":6},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":6},{"task":"/task/domain-generalization","name":"Domain Generalization","papers":6},{"task":"/task/object-detection","name":"Object Detection","papers":6},{"task":"/task/segmentation","name":"Segmentation","papers":6},{"task":"/task/object-detection-1","name":"object-detection","papers":6},{"task":"/task/language-modelling","name":"Language Modelling","papers":4},{"task":"/task/object-recognition","name":"Object Recognition","papers":4},{"task":null,"name":"Position","papers":4},{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":3},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":3}],"tasks_shown":20,"n_tasks":160,"usage_by_year":[{"year":"2016","papers":2},{"year":"2017","papers":7},{"year":"2018","papers":7},{"year":"2019","papers":8},{"year":"2020","papers":21},{"year":"2021","papers":26},{"year":"2022","papers":22},{"year":"2023","papers":26},{"year":"2024","papers":14},{"year":"2025","papers":7}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/jigsaw"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}