SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
Prompt learning with optimal transport for vision-language models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
FMA introduces flow matching for multi-step cross-modal feature alignment in few-shot learning, using fixed coupling, noise augmentation, and early-stopping to outperform one-step PEFT methods.
TAME uses a Mixture-of-Experts prompt bank with input-dependent routing and three unsupervised objectives to adaptively defend CLIP against adversarial attacks at inference time, achieving at least 49.1% robustness gain on 11 datasets.
CAKI generates class-specific prompts from few-shot samples of the same class, stores them in a knowledge bank, and uses query-key matching to inject relevant class knowledge into test instance predictions for improved VLM performance.
MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter and memory usage.
citing papers explorer
-
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
-
Exploring Cross-Modal Flows for Few-Shot Learning
FMA introduces flow matching for multi-step cross-modal feature alignment in few-shot learning, using fixed coupling, noise augmentation, and early-stopping to outperform one-step PEFT methods.
-
TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
TAME uses a Mixture-of-Experts prompt bank with input-dependent routing and three unsupervised objectives to adaptively defend CLIP against adversarial attacks at inference time, achieving at least 49.1% robustness gain on 11 datasets.
-
Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model
CAKI generates class-specific prompts from few-shot samples of the same class, stores them in a knowledge bank, and uses query-key matching to inject relevant class knowledge into test instance predictions for improved VLM performance.
-
MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter and memory usage.
- Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP