Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP
cs.CV, cs.LG
Submitted: 2026-01-14
Updated: 2026-11-02
Terminology
Sources
- Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation
- Don't Stop Learning: Towards Continual Learning for the CLIP Model
- CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Data Filtering Networks
- Adam: A Method for Stochastic Optimization
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
- Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
- Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization
- To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO
- How Much Can CLIP Benefit Vision-and-Language Tasks?
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications
- VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions
- FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources
- ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms
- CoCa: Contrastive Captioners are Image-Text Foundation Models
- CLIP in Medical Imaging: A Survey
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