8 papers
iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models
Xuezhi Cui, Dongbo Zhou, Wang Guo +8
Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastrophic forgetting, assigning iso…
The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?
Zhaoyang Zhang, Run Shao, Dongyue Wu +4
Understanding why independently trained neural networks from different modalities converge toward shared representations, and where this convergence leads, remains an open question…
Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts
Mingning Guo, Mengwei Wu, Shaoxian Li +2
Existing image perception methods based on VLMs generally follow a paradigm wherein models extract and analyze image content based on user-provided textual task prompts. However, s…
BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVs
Mingning Guo, Mengwei Wu, Jiarun He +3
With the rapid advancement of low-altitude remote sensing and Vision-Language Models (VLMs), Embodied Agents based on Unmanned Aerial Vehicles (UAVs) have shown significant potenti…
IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Models
Mingning Guo, Mengwei Wu, Yuxiang Shen +2
End-to-end interpretation currently dominates the remote sensing fine-grained ship classification (RS-FGSC) task. However, the inference process remains uninterpretable, leading to…
Enhancing Scene Classification in Cloudy Image Scenarios: A Collaborative Transfer Method with Information Regulation Mechanism using Optical Cloud-Covered and SAR Remote Sensing Images
Yuze Wang, Rong Xiao, Haifeng Li +2
In remote sensing scene classification, leveraging the transfer methods with well-trained optical models is an efficient way to overcome label scarcity. However, cloud contaminatio…