PulseAugur
EN
LIVE 08:44:40
ENTITY OfficeHome

OfficeHome

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

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

2 day(s) with sentiment data

RECENT · PAGE 1/1 · 9 TOTAL
  1. TOOL · CL_366419 ·

    New Lamarck Method Enhances Domain-Incremental Learning Accuracy

    Researchers have developed a new method for domain-incremental learning called Lamarck, which improves model accuracy without requiring replay of previous domain data. Lamarck utilizes inherited adapter experts, with ad…

  2. TOOL · CL_317578 ·

    New framework simplifies federated domain adaptation with knowledge distillation

    Researchers have introduced SKD-ETR, a novel framework for one-shot federated unsupervised domain adaptation. This method addresses challenges in existing federated learning approaches by reducing communication rounds a…

  3. TOOL · CL_275148 ·

    New framework SaCRL learns causal structure without prior knowledge

    Researchers have developed SaCRL, a novel framework for causal representation learning that can identify the underlying causal structure of data without prior knowledge. This approach formulates structure selection as a…

  4. TOOL · CL_273573 ·

    New method improves AI model reliability in domain generalization

    Researchers have developed a new method called Accuracy-Constrained (AC) selection for domain generalization in computer vision. This technique aims to improve the reliability of predictive probabilities from selected m…

  5. TOOL · CL_268984 ·

    New OVDU protocol rigorously removes unwanted domains from vision-language models

    Researchers have introduced Open-Vocabulary Domain Unlearning (OVDU), a new protocol designed to rigorously remove specific stylistic domains from vision-language models (VLMs). Unlike previous methods that only overfit…

  6. TOOL · CL_129518 ·

    New CoDoL method enhances vision-language model generalization

    Researchers have developed CoDoL, a novel method for improving out-of-distribution (OOD) generalization in vision-language models (VLMs). CoDoL addresses limitations in existing prompt-based CLIP methods by utilizing do…

  7. RESEARCH · CL_128839 ·

    New AI methods boost model robustness in shifting environments

    Researchers have developed new methods for unsupervised domain adaptation (UDA) to improve the robustness of AI models in dynamic environments. One approach, SFT+RL, uses supervised fine-tuning and reinforcement learnin…

  8. RESEARCH · CL_104715 ·

    New methods enhance AI model adaptation robustness against adversarial attacks and data shifts · 6 sources tracked

    Researchers have developed new methods to improve the robustness of test-time adaptation (TTA) for machine learning models, particularly in scenarios with adversarial attacks and evolving data distributions. One approac…

  9. TOOL · CL_93856 ·

    New AI method uses language to improve visual domain generalization

    Researchers have developed a new framework for domain generalization in computer vision that leverages language guidance from pre-trained Visual Foundation Models (VFMs). The method first disentangles text prompts using…