:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autore principale:	Shu, Kaixiang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	https://arxiv.org/abs/2604.27529
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models
di: Hollard, Lilian, et al.
Pubblicazione: (2025)

Adversarial Attacks Leverage Interference Between Features in Superposition
di: Stevinson, Edward, et al.
Pubblicazione: (2025)

Spatial Information Bottleneck for Interpretable Visual Recognition
di: Shu, Kaixiang, et al.
Pubblicazione: (2025)

Network Inversion for Generating Confidently Classified Counterfeits
di: Suhail, Pirzada, et al.
Pubblicazione: (2025)

Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier
di: Wang, Kai, et al.
Pubblicazione: (2024)

Flying By ML -- CNN Inversion of Affine Transforms
di: Van Warren, L.
Pubblicazione: (2023)

FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
di: Yang, Kaixiang, et al.
Pubblicazione: (2025)

Nighttime Driver Behavior Prediction Using Taillight Signal Recognition via CNN-SVM Classifier
di: Barshooi, Amir Hossein, et al.
Pubblicazione: (2023)

Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion
di: Kim, Minseo, et al.
Pubblicazione: (2025)

Lemon and Orange Disease Classification using CNN-Extracted Features and Machine Learning Classifier
di: Arifin, Khandoker Nosiba, et al.
Pubblicazione: (2024)

MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language Models
di: Chen, Kaixiang, et al.
Pubblicazione: (2026)

DACAT: Dual-stream Adaptive Clip-aware Time Modeling for Robust Online Surgical Phase Recognition
di: Yang, Kaixiang, et al.
Pubblicazione: (2024)

Innovative Methods for Non-Destructive Inspection of Handwritten Documents
di: Breci, Eleonora, et al.
Pubblicazione: (2023)

Superposition through Active Learning lens
di: Devkar, Akanksha
Pubblicazione: (2024)

What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
di: Ren, Zhihan, et al.
Pubblicazione: (2025)

DBINDS -- Can Initial Noise from Diffusion Model Inversion Help Reveal AI-Generated Videos?
di: Wu, Yanlin, et al.
Pubblicazione: (2025)

A Novel Dataset for Non-Destructive Inspection of Handwritten Documents
di: Breci, Eleonora, et al.
Pubblicazione: (2024)

GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples
di: Gao, Tian, et al.
Pubblicazione: (2023)

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
di: Pan, Jiachun, et al.
Pubblicazione: (2023)

Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
di: Wang, Yubo, et al.
Pubblicazione: (2026)

Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
di: Jia, Lixin, et al.
Pubblicazione: (2025)

GAC-KAN: An Ultra-Lightweight GNSS Interference Classifier for GenAI-Powered Consumer Edge Devices
di: Zeng, Zhihan, et al.
Pubblicazione: (2026)

Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
di: Zeng, Weili, et al.
Pubblicazione: (2025)

CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognition
di: Yang, Kaixiang, et al.
Pubblicazione: (2025)

Post-hoc Selective Classification for Reliable Synthetic Image Detection
di: Zheng, Kaixiang, et al.
Pubblicazione: (2026)

Knowledge Distillation Based on Transformed Teacher Matching
di: Zheng, Kaixiang, et al.
Pubblicazione: (2024)

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing
di: Xu, Yiran, et al.
Pubblicazione: (2023)

Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching
di: Shin, Jeongwoo, et al.
Pubblicazione: (2026)

FALCON: Frequency Adjoint Link with CONtinuous Density Mask for Fast Single Image Dehazing
di: Kim, Donghyun, et al.
Pubblicazione: (2024)

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization
di: Fang, Hao, et al.
Pubblicazione: (2026)

A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers
di: Sengupta, Sourya, et al.
Pubblicazione: (2023)

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
di: Fang, Hao, et al.
Pubblicazione: (2024)

A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks
di: Qiu, Yixiang, et al.
Pubblicazione: (2024)

PolyR-CNN: R-CNN for end-to-end polygonal building outline extraction
di: Jiao, Weiqin, et al.
Pubblicazione: (2024)

From CNN to CNN + RNN: Adapting Visualization Techniques for Time-Series Anomaly Detection
di: Poirier, Fabien
Pubblicazione: (2024)

Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing
di: Huang, Jiancheng, et al.
Pubblicazione: (2024)

SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing
di: Qian, Qi, et al.
Pubblicazione: (2024)

Neural Clustering for Prefractured Mesh Generation in Real-time Object Destruction
di: Kim, Seunghwan, et al.
Pubblicazione: (2025)

Patch Progression Masked Autoencoder with Fusion CNN Network for Classifying Evolution Between Two Pairs of 2D OCT Slices
di: Zhang, Philippe, et al.
Pubblicazione: (2025)

The Mechanics of CNN Filtering with Rectification
di: Frija-Altarac, Liam, et al.
Pubblicazione: (2025)