Methods › Natural Language Processing › Language Models › CAM

Class-activation map

CAM

267 papers tagged archive 2025-07-28

Introduced by Maxime Oquab et al. in Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural Networks

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN).

Image source: Learning Deep Features for Discriminative Localization

PaperSource

Papers archive 2025-07-28

30 shown of 267, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 211 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Semantic Segmentation73
Weakly supervised Semantic Segmentation60
Weakly-Supervised Semantic Segmentation60
Segmentation36
Object Localization28
Object27
Image Classification21
Weakly-Supervised Object Localization21
image-classification20
Classification15
General Classification11
Contrastive Learning10
Decision Making9
Weakly supervised segmentation9
Image Segmentation8
Pseudo Label8
Few-Shot Learning7
Object Detection7
Data Augmentation6
Decoder6

Usage over time archive 2025-07-28

Papers per year tagged with CAM: 2015 to 2025, peak 59 59 0 2015: 2 papers 2015 2016: 2 papers 2016 2017: 2 papers 2017 2018: 5 papers 2018 2019: 15 papers 2019 2020: 27 papers 2020 2021: 27 papers 2021 2022: 46 papers 2022 2023: 59 papers 2023 2024: 58 papers 2024 2025: 24 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (267 dated). Bars are counts, not a trend claim.

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

Language ModelsInterpretability

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