Methods › General › Prioritized Sampling › PISA
PrIme Sample Attention
PISA
Introduced by Yuhang Cao et al. in Prime Sample Attention in Object Detection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
In Syntology no code under this exact name (no_code; paper_only). The archive credits no paper with an arXiv id for this method, so whether this answer (about the paper Syntology's graph keys as openreview_DG7S1hhwUL) is about this method is not checked; it does not say whether this method has code.
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: 17 · with a code link: 8 · where Syntology ran a sample: 1 (1 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 (1 of 17 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 17 of 17, 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.
-
Large Language Models Don't Make Sense of Word Problems. A Scoping Review from a Mathematics Education Perspective 30 Jun 2025 · 0 repositories · arXiv:2506.24006
-
Preconditioned Inexact Stochastic ADMM for Deep Model 15 Feb 2025 · 0 repositories · arXiv:2502.10784
-
Transformers Meet ACT-R: Repeat-Aware and Sequential Listening Session Recommendation 29 Aug 2024 · 1 repository · arXiv:2408.16578
-
Path-Specific Causal Reasoning for Fairness-aware Cognitive Diagnosis 5 Jun 2024 · 1 repository · arXiv:2406.03064
-
Proving Theorems Recursively 23 May 2024 · 1 repository · arXiv:2405.14414
-
Scalable Learning of Item Response Theory Models 1 Mar 2024 · 1 repository · arXiv:2403.00680Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
csranks: An R Package for Estimation and Inference Involving Ranks 26 Jan 2024 · 0 repositories · arXiv:2401.15205
-
Correcting Selection Bias in Standardized Test Comparisons 19 Sep 2023 · 0 repositories · arXiv:2309.10642
-
A systematic study of the foreground-background imbalance problem in deep learning for object detection 28 Jun 2023 · 0 repositories · arXiv:2306.16539
-
Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity 9 Jun 2023 · 0 repositories · arXiv:2306.06291
-
Magnushammer: A Transformer-Based Approach to Premise Selection 8 Mar 2023 · 0 repositories · arXiv:2303.04488
-
Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning 24 Feb 2023 · 2 repositories · arXiv:2302.12826
-
PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting 20 Sep 2022 · 2 repositories · arXiv:2210.08964
-
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers 22 May 2022 · 0 repositories · arXiv:2205.10893
-
Supporting Interoperability Between Open-Source Search Engines with the Common Index File Format 18 Mar 2020 · 2 repositories · arXiv:2003.08276
-
New Item Consumption Prediction Using Deep Learning 5 May 2019 · 0 repositories · arXiv:1905.01686
-
Prime Sample Attention in Object Detection 9 Apr 2019 · 1 repository · arXiv:1904.04821
Tasks archive 2025-07-28
20 shown of 29 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