Image de couverture de livre

Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jung, Yoojin, Song, Byung Cheol
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Two Heads are Better than One: Robust Learning Meets Multi-branch Models
par: Zhang, Zongyuan, et autres
Publié: (2022)

Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution
par: Yuan, Hsuan, et autres
Publié: (2025)

Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency
par: Ingwersen, Christian Keilstrup, et autres
Publié: (2023)

Defense That Attacks: How Robust Models Become Better Attackers
par: Awad, Mohamed, et autres
Publié: (2025)

Semantic Layering in Room Segmentation via LLMs
par: Kim, Taehyeon, et autres
Publié: (2024)

Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation
par: Cuevas-Velasquez, Hanz, et autres
Publié: (2021)

2Xplat: Two Experts Are Better Than One Generalist
par: Jeong, Hwasik, et autres
Publié: (2026)

ZeroSCD: Zero-Shot Street Scene Change Detection
par: Kannan, Shyam Sundar, et autres
Publié: (2024)

PlaceFormer: Transformer-based Visual Place Recognition using Multi-Scale Patch Selection and Fusion
par: Kannan, Shyam Sundar, et autres
Publié: (2024)

Meta Co-Training: Two Views are Better than One
par: Rothenberger, Jay C., et autres
Publié: (2023)

Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking
par: Xu, Long, et autres
Publié: (2025)

Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles
par: Xie, Jun, et autres
Publié: (2025)

Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
par: Qiao, Bingtian, et autres
Publié: (2026)

SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation
par: Yu, Jihyun, et autres
Publié: (2025)

Two Hands Are Better Than One: Resolving Hand to Hand Intersections via Occupancy Networks
par: Ivashechkin, Maksym, et autres
Publié: (2024)

Robust and Efficient Adversarial Defense in SNNs via Image Purification and Joint Detection
par: Chen, Weiran, et autres
Publié: (2024)

EasyTrack: Efficient and Compact One-stream 3D Point Clouds Tracker
par: Fan, Baojie, et autres
Publié: (2024)

From Tokens to Photons: Test-Time Physical Prompting for Vision-Language Models
par: Im, Boyeong, et autres
Publié: (2025)

Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
par: Oh, Yoojin, et autres
Publié: (2025)

This Looks Better than That: Better Interpretable Models with ProtoPNeXt
par: Willard, Frank, et autres
Publié: (2024)

Efficient and Robust Video Defense Framework against 3D-field Personalized Talking Face
par: Sun, Rui-qing, et autres
Publié: (2025)

LPOI: Listwise Preference Optimization for Vision Language Models
par: Zadeh, Fatemeh Pesaran, et autres
Publié: (2025)

EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering
par: Cheng, Kai, et autres
Publié: (2024)

Decoupling Defense Strategies for Robust Image Watermarking
par: Chen, Jiahui, et autres
Publié: (2026)

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
par: Kim, Pum Jun, et autres
Publié: (2023)

APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
par: Jung, Geunyoung, et autres
Publié: (2026)

Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks
par: Wu, Zhewei, et autres
Publié: (2024)

Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching
par: Lee, Junho, et autres
Publié: (2025)

MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis
par: Zhu, Yitao, et autres
Publié: (2023)

Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake
par: Zheng, Hongrui, et autres
Publié: (2025)

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
par: Kim, Dongwon, et autres
Publié: (2025)

Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability
par: Zeng, Hui, et autres
Publié: (2024)

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
par: Kumar, Vishesh, et autres
Publié: (2026)

When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models
par: Razafindralambo, Raphaël, et autres
Publié: (2026)

Efficient Adaptive Ensembling for Image Classification
par: Bruno, Antonio, et autres
Publié: (2022)

Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking
par: Zhu, Jiawen, et autres
Publié: (2025)

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
par: Park, Junsung, et autres
Publié: (2025)

MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation
par: Hao, Xiaoshuai, et autres
Publié: (2024)

Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration
par: Zhang, Xu, et autres
Publié: (2024)

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
par: Wang, Zeyu, et autres
Publié: (2025)