Cover Image

Logits DeConfusion with CLIP for Few-Shot Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Shuo, Liu, Fang, Hao, Zehua, Wang, Xinyi, Li, Lingling, Liu, Xu, Chen, Puhua, Ma, Wenping
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reliable Multimodal Learning Via Multi-Level Adaptive DeConfusion
by: Zhang, Tong, et al.
Published: (2025)

Multiplane Prior Guided Few-Shot Aerial Scene Rendering
by: Gao, Zihan, et al.
Published: (2024)

ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025
by: He, Jing, et al.
Published: (2025)

Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds
by: Ma, Yanbiao, et al.
Published: (2024)

Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
by: Ma, Yanbiao, et al.
Published: (2023)

Res$^2$CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment
by: Liu, Xinyue, et al.
Published: (2026)

Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners
by: Liu, Mushui, et al.
Published: (2024)

Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification
by: Ma, Yanbiao, et al.
Published: (2024)

Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation
by: Wang, Jin, et al.
Published: (2024)

CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning
by: Liu, Chengyan, et al.
Published: (2024)

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

MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition
by: Xing, Jiazheng, et al.
Published: (2023)

Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation
by: Chi, Zhixiang, et al.
Published: (2025)

MASSeg : 2nd Technical Report for 4th PVUW MOSE Track
by: Cao, Xuqiang, et al.
Published: (2025)

Boosting Few-Shot Learning via Attentive Feature Regularization
by: Zhu, Xingyu, et al.
Published: (2024)

Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification
by: Ma, Yanbiao, et al.
Published: (2024)

Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds
by: He, Pei, et al.
Published: (2025)

Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning
by: Zhou, Haichen, et al.
Published: (2024)

Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editing
by: Zuo, Yi, et al.
Published: (2024)

Learning to Adapt Category Consistent Meta-Feature of CLIP for Few-Shot Classification
by: Shi, Jiaying, et al.
Published: (2024)

AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning
by: Tang, Yuwei, et al.
Published: (2024)

Topology-Aware CLIP Few-Shot Learning
by: Huang, Dazhi
Published: (2025)

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

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

Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning
by: Zhang, Zhenyu, et al.
Published: (2025)

Mining Open Semantics from CLIP: A Relation Transition Perspective for Few-Shot Learning
by: Yan, Cilin, et al.
Published: (2024)

CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP
by: Zuo, Zuo, et al.
Published: (2024)

Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP
by: Li, Yayuan, et al.
Published: (2024)

CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion
by: Meng, Boyuan, et al.
Published: (2025)

Fast and Efficient: Mask Neural Fields for 3D Scene Segmentation
by: Gao, Zihan, et al.
Published: (2024)

Selective Vision-Language Subspace Projection for Few-shot CLIP
by: Zhu, Xingyu, et al.
Published: (2024)

MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning
by: Wang, Yue, et al.
Published: (2025)

The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning
by: Li, Yaohui, et al.
Published: (2024)

Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
by: P, Jishnu Jaykumar, et al.
Published: (2023)

Backdooring CLIP through Concept Confusion
by: Hu, Lijie, et al.
Published: (2025)

CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels
by: Deng, Shizhuo, et al.
Published: (2024)

EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logits
by: Ochal, Mateusz, et al.
Published: (2024)

Multimodal CLIP Inference for Meta-Few-Shot Image Classification
by: Ferragu, Constance, et al.
Published: (2024)

Language-Aware Information Maximization for Transductive Few-Shot CLIP
by: Baklouti, Ghassen, et al.
Published: (2025)

Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting
by: Kravets, Alexey, et al.
Published: (2025)