Yaxing Li

Hang Gao, Xinming Wu, Luming Liang et al.

Seismic geobody interpretation is crucial for structural geology studies and various engineering applications. Existing deep learning methods show promise but lack support for multi-modal inputs and struggle to generalize to different geobody types or surveys. We introduce a promptable foundation model for interpreting any geobodies across seismic surveys. This model integrates a pre-trained vision foundation model (VFM) with a sophisticated multi-modal prompt engine. The VFM, pre-trained on massive natural images and fine-tuned on seismic data, provides robust feature extraction for cross-survey generalization. The prompt engine incorporates multi-modal prior information to iteratively refine geobody delineation. Extensive experiments demonstrate the model's superior accuracy, scalability from 2D to 3D, and generalizability to various geobody types, including those unseen during training. To our knowledge, this is the first highly scalable and versatile multi-modal foundation model capable of interpreting any geobodies across surveys while supporting real-time interactions. Our approach establishes a new paradigm for geoscientific data interpretation, with broad potential for transfer to other tasks.

Xiongye Xiao, Gengshuo Liu, Gaurav Gupta et al.

Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world. Drawing inspiration from neuroscience, we develop the Information-Theoretic Hierarchical Perception (ITHP) model, which utilizes the concept of information bottleneck. Distinct from most traditional fusion models that aim to incorporate all modalities as input, our model designates the prime modality as input, while the remaining modalities act as detectors in the information pathway. Our proposed perception model focuses on constructing an effective and compact information flow by achieving a balance between the minimization of mutual information between the latent state and the input modal state, and the maximization of mutual information between the latent states and the remaining modal states. This approach leads to compact latent state representations that retain relevant information while minimizing redundancy, thereby substantially enhancing the performance of downstream tasks. Experimental evaluations on both the MUStARD and CMU-MOSI datasets demonstrate that our model consistently distills crucial information in multimodal learning scenarios, outperforming state-of-the-art benchmarks.