4 papers
T2T-VICL: Cross-Task Visual In-Context Learning via Implicit Text-Driven VLMs
Shao-Jun Xia, Huixin Zhang, Zhengzhong Tu
Visual in-context learning (VICL) solves visual tasks by conditioning on a few input-output demonstrations without any model training. Recent advances in large vision-language mode…
PestVL-Net: Enabling Multimodal Pest Learning via Fine-grained Vision-Language Interaction
Xueheng Li, Tao Hu, Ke Cao +5
Effective pest recognition and management are crucial for sustainable agricultural development. However, collecting pest data in real scenarios is often challenging. Compared to ot…
Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
Jianhua Han, Meng Tian, Jiangtong Zhu +16
Autonomous driving heavily relies on accurate and robust spatial perception. Many failures arise from inaccuracies and instability, especially in long-tail scenarios and complex in…
Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning
Tian Liu, Huixin Zhang, Shubham Parashar +1
Few-shot recognition (FSR) aims to train a classification model with only a few labeled examples of each concept concerned by a downstream task, where data annotation cost can be p…