Copertina

MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Yue, Xu, Shuai, Zhu, Xuelin, Li, Yicong
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

Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
di: Zhao, Shuai, et al.
Pubblicazione: (2023)

StackCLIP: Clustering-Driven Stacked Prompt in Zero-Shot Industrial Anomaly Detection
di: Hou, Yanning, et al.
Pubblicazione: (2025)

Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts
di: Hou, Yanning, et al.
Pubblicazione: (2025)

Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
di: Zhang, Zhaoxiang, et al.
Pubblicazione: (2024)

Transductive Zero-Shot and Few-Shot CLIP
di: Martin, Ségolène, et al.
Pubblicazione: (2024)

Logits DeConfusion with CLIP for Few-Shot Learning
di: Li, Shuo, et al.
Pubblicazione: (2025)

Zero-Shot Class Unlearning in CLIP with Synthetic Samples
di: Kravets, A., et al.
Pubblicazione: (2024)

PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness
di: Pan, Yurui, et al.
Pubblicazione: (2025)

Learning Visual Proxy for Compositional Zero-Shot Learning
di: Zhang, Shiyu, et al.
Pubblicazione: (2025)

GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
di: Xu, Rui, et al.
Pubblicazione: (2022)

AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation
di: Fang, Qingqing, et al.
Pubblicazione: (2025)

CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation
di: Ali, Muhammad, et al.
Pubblicazione: (2024)

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
di: Cao, Yunkang, et al.
Pubblicazione: (2024)

C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
di: Li, Rongchang, et al.
Pubblicazione: (2024)

Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
di: Yi, Shuai, et al.
Pubblicazione: (2026)

Online Zero-Shot Classification with CLIP
di: Qian, Qi, et al.
Pubblicazione: (2024)

Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
di: Yi, Shuai, et al.
Pubblicazione: (2026)

MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning
di: Xu, Shuo, et al.
Pubblicazione: (2024)

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
di: Dehdashtian, Sepehr, et al.
Pubblicazione: (2024)

Compositional Zero-Shot Learning: A Survey
di: Munir, Ans, et al.
Pubblicazione: (2025)

FlowComposer: Composable Flows for Compositional Zero-Shot Learning
di: He, Zhenqi, et al.
Pubblicazione: (2026)

Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning
di: Rao, Zhijie, et al.
Pubblicazione: (2025)

Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Models
di: Mishra, Ashish, et al.
Pubblicazione: (2025)

Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning
di: Zhang, Haozhe, et al.
Pubblicazione: (2025)

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
di: Li, Yunheng, et al.
Pubblicazione: (2024)

Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning
di: Peng, Zhong, et al.
Pubblicazione: (2025)

TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification
di: Munir, Ans, et al.
Pubblicazione: (2025)

HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA
di: Dibitonto, Francesco, et al.
Pubblicazione: (2026)

Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training
di: Li, Yun, et al.
Pubblicazione: (2024)

LineCounter: Learning Handwritten Text Line Segmentation by Counting
di: Li, Deng, et al.
Pubblicazione: (2021)

TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
di: Li, Miaoge, et al.
Pubblicazione: (2024)

Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning
di: Li, Yun, et al.
Pubblicazione: (2024)

Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation
di: Stangl, Kevin, et al.
Pubblicazione: (2024)

ViP$^2$-CLIP: Visual-Perception Prompting with Unified Alignment for Zero-Shot Anomaly Detection
di: Yang, Ziteng, et al.
Pubblicazione: (2025)

Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
di: Dai, Fengyuan, et al.
Pubblicazione: (2024)

AttriPrompt: Dynamic Prompt Composition Learning for CLIP
di: Zhan, Qiqi, et al.
Pubblicazione: (2025)

CLIP Architecture for Abdominal CT Image-Text Alignment and Zero-Shot Learning: Investigating Batch Composition and Data Scaling
di: Shivika, et al.
Pubblicazione: (2026)

FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance
di: Zhuang, Jiedong, et al.
Pubblicazione: (2024)

Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
di: Sammani, Fawaz, et al.
Pubblicazione: (2024)

WMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detection
di: Chen, Peng, et al.
Pubblicazione: (2026)