Alert button
Picture for Filipe Condessa

Filipe Condessa

Alert button

Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning

Nov 14, 2023
Xidong Wu, Wan-Yi Lin, Devin Willmott, Filipe Condessa, Yufei Huang, Zhenzhen Li, Madan Ravi Ganesh

Viaarxiv icon

Defending Multimodal Fusion Models against Single-Source Adversaries

Jun 25, 2022
Karren Yang, Wan-Yi Lin, Manash Barman, Filipe Condessa, Zico Kolter

Figure 1 for Defending Multimodal Fusion Models against Single-Source Adversaries
Figure 2 for Defending Multimodal Fusion Models against Single-Source Adversaries
Figure 3 for Defending Multimodal Fusion Models against Single-Source Adversaries
Figure 4 for Defending Multimodal Fusion Models against Single-Source Adversaries
Viaarxiv icon

Smooth-Reduce: Leveraging Patches for Improved Certified Robustness

May 12, 2022
Ameya Joshi, Minh Pham, Minsu Cho, Leonid Boytsov, Filipe Condessa, J. Zico Kolter, Chinmay Hegde

Figure 1 for Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Figure 2 for Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Figure 3 for Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Figure 4 for Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Viaarxiv icon

You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries

Jan 29, 2021
Devin Willmott, Anit Kumar Sahu, Fatemeh Sheikholeslami, Filipe Condessa, Zico Kolter

Figure 1 for You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries
Figure 2 for You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries
Figure 3 for You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries
Figure 4 for You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries
Viaarxiv icon

Provably robust deep generative models

Apr 22, 2020
Filipe Condessa, Zico Kolter

Figure 1 for Provably robust deep generative models
Figure 2 for Provably robust deep generative models
Figure 3 for Provably robust deep generative models
Figure 4 for Provably robust deep generative models
Viaarxiv icon

Performance measures for classification systems with rejection

Jan 27, 2016
Filipe Condessa, Jelena Kovacevic, Jose Bioucas-Dias

Figure 1 for Performance measures for classification systems with rejection
Figure 2 for Performance measures for classification systems with rejection
Figure 3 for Performance measures for classification systems with rejection
Figure 4 for Performance measures for classification systems with rejection
Viaarxiv icon

Image Classification with Rejection using Contextual Information

Sep 03, 2015
Filipe Condessa, José Bioucas-Dias, Carlos Castro, John Ozolek, Jelena Kovačević

Figure 1 for Image Classification with Rejection using Contextual Information
Figure 2 for Image Classification with Rejection using Contextual Information
Figure 3 for Image Classification with Rejection using Contextual Information
Figure 4 for Image Classification with Rejection using Contextual Information
Viaarxiv icon

Robust hyperspectral image classification with rejection fields

Apr 29, 2015
Filipe Condessa, Jose Bioucas-Dias, Jelena Kovacevic

Figure 1 for Robust hyperspectral image classification with rejection fields
Figure 2 for Robust hyperspectral image classification with rejection fields
Figure 3 for Robust hyperspectral image classification with rejection fields
Viaarxiv icon

SegSALSA-STR: A convex formulation to supervised hyperspectral image segmentation using hidden fields and structure tensor regularization

Apr 27, 2015
Filipe Condessa, Jose Bioucas-Dias, Jelena Kovacevic

Figure 1 for SegSALSA-STR: A convex formulation to supervised hyperspectral image segmentation using hidden fields and structure tensor regularization
Viaarxiv icon