PulseAugur
EN
LIVE 08:25:49
ENTITY Class activation mapping

Class activation mapping

PulseAugur coverage of Class activation mapping — every cluster mentioning Class activation mapping across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
2
5 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
5 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

2 day(s) with sentiment data

RECENT · PAGE 1/1 · 5 TOTAL
  1. TOOL · CL_315160 ·

    New SRCD framework combats AI shortcut learning in long-tailed recognition

    Researchers have introduced Shortcut-Resistant CAM Distillation (SRCD), a new framework designed to improve the generalization of AI models to tail classes in long-tailed recognition tasks. This method addresses the iss…

  2. TOOL · CL_323116 ·

    New SRCD Framework Combats AI Shortcut Learning in Long-Tailed Datasets

    Researchers have developed Shortcut-Resistant CAM Distillation (SRCD), a new framework designed to improve AI model generalization on long-tailed datasets. This method addresses shortcut learning, where models rely on n…

  3. TOOL · CL_198114 ·

    Review paper tracks evolution of visual explanation methods in AI

    A new review paper published on arXiv details the evolution of Class Activation Mapping (CAM) techniques in explainable computer vision. The paper categorizes 57 method-centered studies from 2016 onwards, highlighting a…

  4. RESEARCH · CL_109658 ·

    New C2RM-Seg Framework Enhances Histopathological Tissue Segmentation

    Researchers have introduced C$^2$RM-Seg, a novel two-stage framework designed to improve histopathological tissue segmentation. This method addresses limitations in existing weakly supervised techniques, which often pro…

  5. TOOL · CL_29285 ·

    New FAME method enhances AI model explainability in image tasks

    Researchers have introduced FAME, a new method for explaining deep learning models in image processing tasks. FAME combines gradient-based techniques with input manipulation to generate attribution maps, aiming to impro…