Copertina

Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Chenyang, Wang, Kun, Hsiao, Janet H., Chan, Antoni B.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation
di: Cui, Yongjin, et al.
Pubblicazione: (2026)

Density-based Object Detection in Crowded Scenes
di: Zhao, Chenyang, et al.
Pubblicazione: (2025)

Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting
di: Lin, Wei, et al.
Pubblicazione: (2025)

Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics
di: Wang, Hai, et al.
Pubblicazione: (2026)

FG-CLIP: Fine-Grained Visual and Textual Alignment
di: Xie, Chunyu, et al.
Pubblicazione: (2025)

CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP
di: Yang, Tianyu, et al.
Pubblicazione: (2024)

MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection
di: Park, Jun Yeong, et al.
Pubblicazione: (2026)

Guided AbsoluteGrad: Magnitude of Gradients Matters to Explanation's Localization and Saliency
di: Huang, Jun, et al.
Pubblicazione: (2024)

MLLM-based Textual Explanations for Face Comparison
di: Sony, Redwan, et al.
Pubblicazione: (2026)

CLIP-DR: Textual Knowledge-Guided Diabetic Retinopathy Grading with Ranking-aware Prompting
di: Yu, Qinkai, et al.
Pubblicazione: (2024)

Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning
di: He, Lingfeng, et al.
Pubblicazione: (2025)

un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
di: Li, Yinqi, et al.
Pubblicazione: (2025)

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

3D Crowd Counting via Geometric Attention-guided Multi-View Fusion
di: Zhang, Qi, et al.
Pubblicazione: (2020)

Learning Tracking Representations from Single Point Annotations
di: Wu, Qiangqiang, et al.
Pubblicazione: (2024)

A Fixed-Point Approach to Unified Prompt-Based Counting
di: Lin, Wei, et al.
Pubblicazione: (2024)

WP-CLIP: Leveraging CLIP to Predict Wölfflin's Principles in Visual Art
di: Ghildyal, Abhijay, et al.
Pubblicazione: (2025)

Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment
di: Thakur, Rini Smita, et al.
Pubblicazione: (2025)

Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
di: Lu, Haodong, et al.
Pubblicazione: (2025)

Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention
di: Wang, Jiuniu, et al.
Pubblicazione: (2025)

CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
di: Xiao, Linhui, et al.
Pubblicazione: (2023)

Zero-Shot Textual Explanations via Translating Decision-Critical Features
di: Yamauchi, Toshinori, et al.
Pubblicazione: (2025)

Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization
di: Zhang, Qi, et al.
Pubblicazione: (2024)

SuperCLIP: CLIP with Simple Classification Supervision
di: Zhao, Weiheng, et al.
Pubblicazione: (2025)

Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family
di: Chew, Oscar, et al.
Pubblicazione: (2026)

Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
di: Yamauchi, Toshinori, et al.
Pubblicazione: (2026)

CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation
di: Rusanovsky, Matan, et al.
Pubblicazione: (2024)

SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs
di: Yin, Yuanyang, et al.
Pubblicazione: (2024)

Autonomous Imagination: Closed-Loop Decomposition of Visual-to-Textual Conversion in Visual Reasoning for Multimodal Large Language Models
di: Liu, Jingming, et al.
Pubblicazione: (2024)

VisText-Mosquito: A Unified Multimodal Dataset for Visual Detection, Segmentation, and Textual Explanation on Mosquito Breeding Sites
di: Islam, Md. Adnanul, et al.
Pubblicazione: (2025)

Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations
di: Dekdegue, Hajar, et al.
Pubblicazione: (2026)

CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering
di: Vardi, Ben, et al.
Pubblicazione: (2025)

AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection
di: Gao, Bin-Bin, et al.
Pubblicazione: (2025)

Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation
di: Lu, Jinda, et al.
Pubblicazione: (2024)

Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition
di: Wang, Zhifeng, et al.
Pubblicazione: (2025)

TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model
di: Yao, Hantao, et al.
Pubblicazione: (2023)

GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers
di: Zablocki, Éloi, et al.
Pubblicazione: (2024)

CLIP Model for Images to Textual Prompts Based on Top-k Neighbors
di: Zhang, Xin, et al.
Pubblicazione: (2024)

MIP: CLIP-based Image Reconstruction from PEFT Gradients
di: Zhou, Peiheng, et al.
Pubblicazione: (2024)

CLIP-IT: CLIP-based Pairing for Histology Images Classification
di: Karimian, Banafsheh, et al.
Pubblicazione: (2025)