5 papers
Explicit Uncertainty Modeling for Active CLIP Adaptation with Dual Prompt Tuning
Qian-Wei Wang, Yaguang Song, Shu-Tao Xia
Pre-trained vision-language models such as CLIP exhibit strong transferability, yet adapting them to downstream image classification tasks under limited annotation budgets remains…
Fine-tuning Pre-trained Vision-Language Models in a Human-Annotation-Free Manner
Qian-Wei Wang, Guanghao Meng, Ren Cai +2
Large-scale vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization, but adapting them to downstream tasks typically requires costly labeled data. Existi…
Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation
Qian-Wei Wang, Yaguang Song, Shu-Tao Xia
In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators. With the emergence…
Enhancing Retrieval Augmentation via Adversarial Collaboration
Letian Zhang, Guanghao Meng, Xudong Ren +2
Retrieval-augmented Generation (RAG) is a prevalent approach for domain-specific LLMs, yet it is often plagued by "Retrieval Hallucinations"--a phenomenon where fine-tuned models f…
Is Self-Supervised Pre-training on Satellite Imagery Better than ImageNet? A Systematic Study with Sentinel-2
Saad Lahrichi, Zion Sheng, Shufan Xia +2
Self-supervised learning (SSL) has demonstrated significant potential in pre-training robust models with limited labeled data, making it particularly valuable for remote sensing (R…