Cover Image

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Srinivas, Suraj, Bordt, Sebastian, Lakkaraju, Hima
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Manifold Hypothesis for Gradient-Based Explanations
by: Bordt, Sebastian, et al.
Published: (2022)

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
by: Bhalla, Usha, et al.
Published: (2023)

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
by: Bhalla, Usha, et al.
Published: (2024)

Counterfactual Explanations on Robust Perceptual Geodesics
by: Zaher, Eslam, et al.
Published: (2026)

Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics
by: Croce, Francesco, et al.
Published: (2025)

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
by: Kim, Beomsu, et al.
Published: (2025)

Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models
by: Hoang, Dung Anh, et al.
Published: (2026)

LipSim: A Provably Robust Perceptual Similarity Metric
by: Ghazanfari, Sara, et al.
Published: (2023)

Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI
by: Kim, Won Jun, et al.
Published: (2024)

Speech-Synchronized Whiteboard Generation via VLM-Driven Structured Drawing Representations
by: Prasad, Suraj, et al.
Published: (2026)

Robustness of Visual Explanations to Common Data Augmentation
by: Tětková, Lenka, et al.
Published: (2023)

Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning
by: Ballas, Aristotelis, et al.
Published: (2026)

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization
by: Xing, Shuo, et al.
Published: (2025)

Detection and Classification of Diseases in Multi-Crop Leaves using LSTM and CNN Models
by: Kanakala, Srinivas, et al.
Published: (2025)

Which Model to Transfer? A Survey on Transferability Estimation
by: Ding, Yuhe, et al.
Published: (2024)

Towards Unified Benchmark and Models for Multi-Modal Perceptual Metrics
by: Ghazanfari, Sara, et al.
Published: (2024)

Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations
by: Yang, Ziyan, et al.
Published: (2022)

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations
by: Babadi, Narges, et al.
Published: (2026)

Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape
by: Chen, Tiejin, et al.
Published: (2024)

Towards Gradient-based Time-Series Explanations through a SpatioTemporal Attention Network
by: Lee, Min Hun
Published: (2024)

Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Off
by: Halmosi, Levente, et al.
Published: (2024)

On Spectral Properties of Gradient-based Explanation Methods
by: Mehrpanah, Amir, et al.
Published: (2025)

MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
by: Ren, Dayong
Published: (2026)

Diffusion Model with Perceptual Loss
by: Lin, Shanchuan, et al.
Published: (2023)

Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
by: Chen, Jian, et al.
Published: (2024)

SynthPID: P&ID digitization from Topology-Preserving Synthetic Data
by: Prasad, Suraj, et al.
Published: (2026)

Advancing Melanoma Diagnosis with Self-Supervised Neural Networks: Evaluating the Effectiveness of Different Techniques
by: Vusirikala, Srivishnu, et al.
Published: (2024)

On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
by: Mehrpanah, Amir, et al.
Published: (2025)

Predicting Lung Disease Severity via Image-Based AQI Analysis using Deep Learning Techniques
by: Mahajan, Anvita, et al.
Published: (2024)

Characterizing Model Robustness via Natural Input Gradients
by: Rodríguez-Muñoz, Adrián, et al.
Published: (2024)

Histopathology Image Normalization via Latent Manifold Compaction
by: Zhang, Xiaolong, et al.
Published: (2026)

Beyond Perceptual Distances: Rethinking Disparity Assessment for Out-of-Distribution Detection with Diffusion Models
by: Fang, Kun, et al.
Published: (2024)

Interpretability Needs a New Paradigm
by: Madsen, Andreas, et al.
Published: (2024)

How to Squeeze An Explanation Out of Your Model
by: Roxo, Tiago, et al.
Published: (2024)

When Does Perceptual Alignment Benefit Vision Representations?
by: Sundaram, Shobhita, et al.
Published: (2024)

MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering
by: He, Lixuan, et al.
Published: (2025)

ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model
by: Han, Kunyang, et al.
Published: (2024)

Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations
by: Adachi, Kazuki, et al.
Published: (2022)

Data-centric Prediction Explanation via Kernelized Stein Discrepancy
by: Sarvmaili, Mahtab, et al.
Published: (2024)

Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks
by: Madden, Jordan, et al.
Published: (2024)