AIConfPaper
← Search

Agata Lapedriza

5 accepted papers

2025

Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent

Christy Li, Josep Lopez Camuñas, Jake Thomas Touchet, Jacob Andreas, Agata Lapedriza, Antonio Torralba +1
NeurIPS 2025poster

When a vision model performs image recognition, which visual attributes drive its predictions? Detecting unintended reliance on specific visual features is critical for ensuring model robustness, preventing overfitting, and avoiding spurious correlations. We introduce an automated framework for dete…

Cited by 0Source ↗Scholar ↗
2020

Detecting Natural Disasters, Damage, and Incidents in the Wild

Ethan Weber, Nuria Marzo, Dim P. Papadopoulos, Aritro Biswas, Agata Lapedriza, Ferda Ofli +2
ECCV 2020poster

damage, and incidents in the wild","Responding to natural disasters, such as earthquakes, floods, and wildfires, is a laborious task performed by on-the-ground emergency responders and analysts. Social media has emerged as a low-latency data source to quickly understand disaster situations. While mo…

Cited by 77Source ↗PDF ↗Scholar ↗
2019

Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems

Asma Ghandeharioun, Judy Hanwen Shen, Natasha Jaques, Craig Ferguson, Noah Jones, Agata Lapedriza +1
NeurIPS 2019poster

Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we investigate interactive human evaluation and provide evidence…

Cited by 120Source ↗PDF ↗code ↗Scholar ↗
2016

Learning Deep Features for Discriminative Localization

Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba
CVPR 2016poster

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on image-level labels. While this technique was previously proposed as a means…

Cited by 13283PDF ↗code ↗Scholar ↗