{"url":"/method/pisa","slug":"pisa","name":"PISA","full_name":"PrIme Sample Attention","full_name_withheld":false,"description_markdown":"**PrIme Sample Attention (PISA)** directs the training of object detection frameworks towards prime samples. These are samples that play a key role in driving the detection performance. The authors define Hierarchical Local Rank (HLR) as a metric of importance. Specifically, they use IoU-HLR to rank positive samples and ScoreHLR to rank negative samples in each mini-batch. This ranking strategy places the positive samples with highest IoUs around each object and the negative samples with highest scores in each cluster to the top of the ranked list and directs the focus of the training process to them via a simple re-weighting scheme. The authors also devise a classification-aware regression loss to jointly optimize the classification and regression branches. Particularly, this loss would suppress those samples with large regression loss, thus reinforcing the attention to prime samples.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Prime Sample Attention in Object Detection","paper":"/paper/prime-sample-attention-in-object-detection","first_author":"Yuhang Cao","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/prime-sample-attention-in-object-detection"},"source":{"url":"https://arxiv.org/abs/1904.04821v2","title":"Prime Sample Attention in Object Detection","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":"Prioritized Sampling","url":"/methods/category/prioritized-sampling","pwc_aliases":[]}],"n_papers_tagged":17,"archive_num_papers":17,"papers_newest_first":[{"paper":null,"title":"Large Language Models Don't Make Sense of Word Problems. A Scoping Review from a Mathematics Education Perspective","date":"2025-06-30","arxiv_id":"2506.24006","n_code_links":0,"syntology":null},{"paper":null,"title":"Preconditioned Inexact Stochastic ADMM for Deep Model","date":"2025-02-15","arxiv_id":"2502.10784","n_code_links":0,"syntology":null},{"paper":"/paper/transformers-meet-act-r-repeat-aware-and","title":"Transformers Meet ACT-R: Repeat-Aware and Sequential Listening Session Recommendation","date":"2024-08-29","arxiv_id":"2408.16578","n_code_links":1,"syntology":null},{"paper":"/paper/path-specific-causal-reasoning-for-fairness","title":"Path-Specific Causal Reasoning for Fairness-aware Cognitive Diagnosis","date":"2024-06-05","arxiv_id":"2406.03064","n_code_links":1,"syntology":null},{"paper":"/paper/proving-theorems-recursively","title":"Proving Theorems Recursively","date":"2024-05-23","arxiv_id":"2405.14414","n_code_links":1,"syntology":null},{"paper":"/paper/scalable-learning-of-item-response-theory","title":"Scalable Learning of Item Response Theory Models","date":"2024-03-01","arxiv_id":"2403.00680","n_code_links":1,"syntology":{"ran":13,"of":13,"unverified":0,"pointer_only":13}},{"paper":null,"title":"csranks: An R Package for Estimation and Inference Involving Ranks","date":"2024-01-26","arxiv_id":"2401.15205","n_code_links":0,"syntology":null},{"paper":null,"title":"Correcting Selection Bias in Standardized Test Comparisons","date":"2023-09-19","arxiv_id":"2309.10642","n_code_links":0,"syntology":null},{"paper":null,"title":"A systematic study of the foreground-background imbalance problem in deep learning for object detection","date":"2023-06-28","arxiv_id":"2306.16539","n_code_links":0,"syntology":null},{"paper":null,"title":"Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity","date":"2023-06-09","arxiv_id":"2306.06291","n_code_links":0,"syntology":null},{"paper":null,"title":"Magnushammer: A Transformer-Based Approach to Premise Selection","date":"2023-03-08","arxiv_id":"2303.04488","n_code_links":0,"syntology":null},{"paper":"/paper/permutation-invariant-set-autoencoders-with","title":"Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning","date":"2023-02-24","arxiv_id":"2302.12826","n_code_links":2,"syntology":null},{"paper":"/paper/prompt-based-time-series-forecasting-a-new","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","date":"2022-09-20","arxiv_id":"2210.08964","n_code_links":2,"syntology":null},{"paper":"/paper/thor-wielding-hammers-to-integrate-language","title":"Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers","date":"2022-05-22","arxiv_id":"2205.10893","n_code_links":0,"syntology":null},{"paper":"/paper/supporting-interoperability-between-open","title":"Supporting Interoperability Between Open-Source Search Engines with the Common Index File Format","date":"2020-03-18","arxiv_id":"2003.08276","n_code_links":2,"syntology":null},{"paper":null,"title":"New Item Consumption Prediction Using Deep Learning","date":"2019-05-05","arxiv_id":"1905.01686","n_code_links":0,"syntology":null},{"paper":"/paper/prime-sample-attention-in-object-detection","title":"Prime Sample Attention in Object Detection","date":"2019-04-09","arxiv_id":"1904.04821","n_code_links":1,"syntology":null}],"papers_shown":17,"tasks":[{"task":"/task/automated-theorem-proving","name":"Automated Theorem Proving","papers":3},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/mathematical-reasoning","name":"Mathematical Reasoning","papers":1},{"task":"/task/multi-armed-bandits","name":"Multi-Armed Bandits","papers":1},{"task":"/task/music-recommendation","name":"Music Recommendation","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/selection-bias","name":"Selection bias","papers":1},{"task":"/task/sentence","name":"Sentence","papers":1},{"task":"/task/sequential-recommendation","name":"Sequential Recommendation","papers":1},{"task":"/task/text-generation","name":"Text Generation","papers":1}],"tasks_shown":20,"n_tasks":29,"usage_by_year":[{"year":"2019","papers":2},{"year":"2020","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":5},{"year":"2024","papers":5},{"year":"2025","papers":2}],"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/pisa"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}