{"url":"/method/paa","slug":"paa","name":"PAA","full_name":"Patch AutoAugment","full_name_withheld":false,"description_markdown":"**Patch AutoAugment** is a patch-level automatic data augmentation algorithm that automatically searches for the optimal augmentation policies for the patches of an image. Specifically, PAA allows each patch DA operation to be controlled by an agent and models it as a Multi-Agent Reinforcement Learning (MARL) problem. At each step, PAA samples the most effective operation for each patch based on its content and the semantics of the whole image. The agents cooperate as a team and share a unified team reward for achieving the joint optimal DA policy of the whole image. PAA is co-trained with a target network through adversarial training. At each step, the policy network samples the most effective operation for each patch based on its content and the semantics of the image.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Local Patch AutoAugment with Multi-Agent Collaboration","paper":"/paper/patch-autoaugment","first_author":"Shiqi Lin","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/patch-autoaugment"},"source":{"url":"https://arxiv.org/abs/2103.11099v2","title":"Local Patch AutoAugment with Multi-Agent Collaboration","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Data Augmentation","url":"/methods/category/image-data-augmentation","pwc_aliases":[]}],"n_papers_tagged":10,"archive_num_papers":10,"papers_newest_first":[{"paper":null,"title":"Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/political-actor-agent-simulating-legislative","title":"Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models","date":"2024-12-10","arxiv_id":"2412.07144","n_code_links":1,"syntology":null},{"paper":null,"title":"Efficient Algorithms for Recognizing Weighted Tree-Adjoining Languages","date":"2023-10-23","arxiv_id":"2310.15276","n_code_links":0,"syntology":null},{"paper":null,"title":"Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Models","date":"2023-08-10","arxiv_id":"2308.05881","n_code_links":0,"syntology":null},{"paper":null,"title":"Impact of Sensing Range on Real-Time Adaptive Control of Signalized Intersections Using Vehicle Trajectory Information","date":"2023-08-03","arxiv_id":"2308.01646","n_code_links":0,"syntology":null},{"paper":"/paper/self-similarity-based-super-resolution-of","title":"Self-similarity-based super-resolution of photoacoustic angiography from hand-drawn doodles","date":"2023-05-02","arxiv_id":"2305.01165","n_code_links":1,"syntology":null},{"paper":"/paper/personalized-dialogue-generation-with-persona","title":"Personalized Dialogue Generation with Persona-Adaptive Attention","date":"2022-10-27","arxiv_id":"2210.15088","n_code_links":1,"syntology":null},{"paper":null,"title":"Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models","date":"2021-11-14","arxiv_id":"2111.07355","n_code_links":0,"syntology":null},{"paper":"/paper/tood-task-aligned-one-stage-object-detection","title":"TOOD: Task-aligned One-stage Object Detection","date":"2021-08-17","arxiv_id":"2108.07755","n_code_links":6,"syntology":{"ran":2,"of":4,"unverified":2,"pointer_only":2}},{"paper":"/paper/patch-autoaugment","title":"Local Patch AutoAugment with Multi-Agent Collaboration","date":"2021-03-20","arxiv_id":"2103.11099","n_code_links":2,"syntology":null}],"papers_shown":10,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/2d-object-detection","name":"2D Object Detection","papers":1},{"task":"/task/continual-learning","name":"Continual Learning","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/dialogue-generation","name":"Dialogue Generation","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/ensemble-learning","name":"Ensemble Learning","papers":1},{"task":"/task/fine-grained-image-recognition","name":"Fine-Grained Image Recognition","papers":1},{"task":"/task/fracture-detection","name":"Fracture detection","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/medical-object-detection","name":"Medical Object Detection","papers":1},{"task":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/super-resolution","name":"Super-Resolution","papers":1},{"task":"/task/tag","name":"TAG","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":1}],"tasks_shown":20,"n_tasks":21,"usage_by_year":[{"year":"2021","papers":3},{"year":"2022","papers":1},{"year":"2023","papers":4},{"year":"2024","papers":1},{"year":"2025","papers":1}],"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/paa"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}