Cover Image

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Magistri, Simone, Goswami, Dipam, Mistretta, Marco, Twardowski, Bartłomiej, van de Weijer, Joost, Bagdanov, Andrew D.
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
by: Goswami, Dipam, et al.
Published: (2024)

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification
by: Goswami, Dipam, et al.
Published: (2026)

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers
by: Goswami, Dipam, et al.
Published: (2024)

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
by: Mistretta, Marco, et al.
Published: (2025)

Exemplar-free Continual Representation Learning via Learnable Drift Compensation
by: Gomez-Villa, Alex, et al.
Published: (2024)

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
by: Goswami, Dipam, et al.
Published: (2023)

SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
by: Caselli, Lorenzo, et al.
Published: (2026)

Accurate and Efficient Low-Rank Model Merging in Core Space
by: Panariello, Aniello, et al.
Published: (2025)

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
by: Goswami, Dipam, et al.
Published: (2024)

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
by: Magistri, Simone, et al.
Published: (2025)

Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning
by: Magistri, Simone, et al.
Published: (2024)

Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning
by: Yu, Lu, et al.
Published: (2024)

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
by: Goswami, Dipam, et al.
Published: (2025)

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
by: Marczak, Daniel, et al.
Published: (2025)

On the importance of cross-task features for class-incremental learning
by: Soutif--Cormerais, Albin, et al.
Published: (2021)

CLIP Adaptation by Intra-modal Overlap Reduction
by: Kravets, Alexey, et al.
Published: (2024)

DeCLIP: Decoupled Prompting for CLIP-based Multi-Label Class-Incremental Learning
by: Du, Kaile, et al.
Published: (2025)

Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation
by: Mistretta, Marco, et al.
Published: (2024)

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR
by: Cignoni, Giacomo, et al.
Published: (2026)

ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
by: Lan, Mengcheng, et al.
Published: (2024)

CLIP's Visual Embedding Projector is a Few-shot Cornucopia
by: Fahes, Mohammad, et al.
Published: (2024)

Augmentation-aware Self-supervised Learning with Conditioned Projector
by: Przewięźlikowski, Marcin, et al.
Published: (2023)

Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP
by: Herzog, Jonas, et al.
Published: (2026)

An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates
by: Soutif--Cormerais, Albin, et al.
Published: (2024)

The Art of Deception: Color Visual Illusions and Diffusion Models
by: Gomez-Villa, Alex, et al.
Published: (2024)

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
by: Liu, Yuyang, et al.
Published: (2025)

CLIP Multi-modal Hashing for Multimedia Retrieval
by: Zhu, Jian, et al.
Published: (2024)

MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP
by: Truong, Chau, et al.
Published: (2025)

Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
by: Rota, Claudio, et al.
Published: (2023)

CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
by: Chung, Jeannie, et al.
Published: (2026)

PERL: Parameter Efficient Reasoning in CLIP Latent Space
by: Carnemolla, Simone, et al.
Published: (2026)

CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression
by: Zhang, Kangjie, et al.
Published: (2026)

CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination
by: Yang, Kaicheng, et al.
Published: (2024)

AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model Alignment
by: Nawaz, Umair, et al.
Published: (2024)

MoCLIP-Lite: Efficient Video Recognition by Fusing CLIP with Motion Vectors
by: Huang, Binhua, et al.
Published: (2025)

CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition
by: Alyami, Sarah, et al.
Published: (2025)

RE-tune: Incremental Fine Tuning of Biomedical Vision-Language Models for Multi-label Chest X-ray Classification
by: Mistretta, Marco, et al.
Published: (2024)

FLEX-CLIP: Feature-Level GEneration Network Enhanced CLIP for X-shot Cross-modal Retrieval
by: Xie, Jingyou, et al.
Published: (2024)

SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation
by: Cho, Taewan, et al.
Published: (2026)

SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels
by: Singh, Darshan, et al.
Published: (2024)