Image de couverture de livre

Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Shu, Kaixiang
Format:	Preprint
Publié:	2026
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

Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models
par: Hollard, Lilian, et autres
Publié: (2025)

Adversarial Attacks Leverage Interference Between Features in Superposition
par: Stevinson, Edward, et autres
Publié: (2025)

Spatial Information Bottleneck for Interpretable Visual Recognition
par: Shu, Kaixiang, et autres
Publié: (2025)

Network Inversion for Generating Confidently Classified Counterfeits
par: Suhail, Pirzada, et autres
Publié: (2025)

Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier
par: Wang, Kai, et autres
Publié: (2024)

Nighttime Driver Behavior Prediction Using Taillight Signal Recognition via CNN-SVM Classifier
par: Barshooi, Amir Hossein, et autres
Publié: (2023)

Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion
par: Kim, Minseo, et autres
Publié: (2025)

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

FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editing
par: Yang, Kaixiang, et autres
Publié: (2025)

Innovative Methods for Non-Destructive Inspection of Handwritten Documents
par: Breci, Eleonora, et autres
Publié: (2023)

Lemon and Orange Disease Classification using CNN-Extracted Features and Machine Learning Classifier
par: Arifin, Khandoker Nosiba, et autres
Publié: (2024)

What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
par: Ren, Zhihan, et autres
Publié: (2025)

DBINDS -- Can Initial Noise from Diffusion Model Inversion Help Reveal AI-Generated Videos?
par: Wu, Yanlin, et autres
Publié: (2025)

GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples
par: Gao, Tian, et autres
Publié: (2023)

MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language Models
par: Chen, Kaixiang, et autres
Publié: (2026)

DACAT: Dual-stream Adaptive Clip-aware Time Modeling for Robust Online Surgical Phase Recognition
par: Yang, Kaixiang, et autres
Publié: (2024)

A Novel Dataset for Non-Destructive Inspection of Handwritten Documents
par: Breci, Eleonora, et autres
Publié: (2024)

Superposition through Active Learning lens
par: Devkar, Akanksha
Publié: (2024)

Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
par: Jia, Lixin, et autres
Publié: (2025)

Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
par: Wang, Yubo, et autres
Publié: (2026)

Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching
par: Shin, Jeongwoo, et autres
Publié: (2026)

FALCON: Frequency Adjoint Link with CONtinuous Density Mask for Fast Single Image Dehazing
par: Kim, Donghyun, et autres
Publié: (2024)

GAC-KAN: An Ultra-Lightweight GNSS Interference Classifier for GenAI-Powered Consumer Edge Devices
par: Zeng, Zhihan, et autres
Publié: (2026)

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing
par: Xu, Yiran, et autres
Publié: (2023)

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization
par: Fang, Hao, et autres
Publié: (2026)

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
par: Pan, Jiachun, et autres
Publié: (2023)

PolyR-CNN: R-CNN for end-to-end polygonal building outline extraction
par: Jiao, Weiqin, et autres
Publié: (2024)

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

Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
par: Zeng, Weili, et autres
Publié: (2025)

CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognition
par: Yang, Kaixiang, et autres
Publié: (2025)

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
par: Fang, Hao, et autres
Publié: (2024)

The Mechanics of CNN Filtering with Rectification
par: Frija-Altarac, Liam, et autres
Publié: (2025)

ISWSST: Index-space-wave State Superposition Transformers for Multispectral Remotely Sensed Imagery Semantic Segmentation
par: Li, Chang, et autres
Publié: (2024)

MO R-CNN: Multispectral Oriented R-CNN for Object Detection in Remote Sensing Image
par: Wang, Leiyu, et autres
Publié: (2025)

A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks
par: Qiu, Yixiang, et autres
Publié: (2024)

Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing
par: Huang, Jiancheng, et autres
Publié: (2024)

SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing
par: Qian, Qi, et autres
Publié: (2024)

Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier
par: Zhou, Yujie, et autres
Publié: (2026)

FryNet: Dual-Stream Adversarial Fusion for Non-Destructive Frying Oil Oxidation Assessment
par: Ahmed, Khaled R, et autres
Publié: (2026)

A Test Statistic Estimation-based Approach for Establishing Self-interpretable CNN-based Binary Classifiers
par: Sengupta, Sourya, et autres
Publié: (2023)