Language-Aware Information Maximization for Transductive Few-Shot CLIP
cs.CV
Submitted: 2025-08-30
Updated: 2026-11-06
Code: https://github.com/ghassenbaklouti/LIMO
Terminology
Sources
- One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning
- A Closer Look at Few-shot Classification
- A Baseline for Few-Shot Image Classification
- CLIP's Visual Embedding Projector is a Few-shot Cornucopia
- Learning deep representations by mutual information estimation and maximization
- LoRA: Low-Rank Adaptation of Large Language Models
- Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
- Fine-Grained Visual Classification of Aircraft
- QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- On Mutual Information Maximization for Representation Learning
- DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation
- BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
- AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs