【DL輪読会】Efficiently Modeling Long Sequences with Structured State SpacesDeep Learning JP
This document summarizes a research paper on modeling long-range dependencies in sequence data using structured state space models and deep learning. The proposed S4 model (1) derives recurrent and convolutional representations of state space models, (2) improves long-term memory using HiPPO matrices, and (3) efficiently computes state space model convolution kernels. Experiments show S4 outperforms existing methods on various long-range dependency tasks, achieves fast and memory-efficient computation comparable to efficient Transformers, and performs competitively as a general sequence model.
SAM is a new segmentation model that can segment objects in images using natural language prompts. It was trained on over 1,100 datasets totaling over 10,000 images using a model-in-the-loop approach. SAM uses a transformer-based architecture with encoders for images, text, bounding boxes and masks. It achieves state-of-the-art zero-shot segmentation performance without any fine-tuning on target datasets.
[DL輪読会]Neural Radiance Flow for 4D View Synthesis and Video Processing (NeRF...Deep Learning JP
Neural Radiance Flow (NeRFlow) is a method that extends Neural Radiance Fields (NeRF) to model dynamic scenes from video data. NeRFlow simultaneously learns two fields - a radiance field to reconstruct images like NeRF, and a flow field to model how points in space move over time using optical flow. This allows it to generate novel views from a new time point. The model is trained end-to-end by minimizing losses for color reconstruction from volume rendering and optical flow reconstruction. However, the method requires training separate models for each scene and does not generalize to unknown scenes.
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
[DL輪読会]Neural Radiance Flow for 4D View Synthesis and Video Processing (NeRF...Deep Learning JP
Neural Radiance Flow (NeRFlow) is a method that extends Neural Radiance Fields (NeRF) to model dynamic scenes from video data. NeRFlow simultaneously learns two fields - a radiance field to reconstruct images like NeRF, and a flow field to model how points in space move over time using optical flow. This allows it to generate novel views from a new time point. The model is trained end-to-end by minimizing losses for color reconstruction from volume rendering and optical flow reconstruction. However, the method requires training separate models for each scene and does not generalize to unknown scenes.
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
23. 参考⽂献
• B. Midenhall et al.: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis.
arxiv prepring, 2020.
• J. T. Kajiya et al.: Ray Tracing Volume Densities. Computer Graphics, 1984.
• N. Max: Optical models for direct volume rendering. IEEE Transactions on Visualization and
Computer Graphics 1995.
• M. Levoy: Efficient ray tracing of volume data. ACM Transactions on Graphics 1990.
• N. Rahaman et al.: On the spectral bias of neural networks. in ICML 2018.
• A. Vaswani et al.: Attention is all you need. in NeurIPS 2018.
• S. Lombardi et al.: Neural volumes: Learning dynamic renderable volumes from images.
SIGGRAPH 2019.
• V. Sitzmann et al.: Scene Representation Networks: Continuous 3D-Structure-Aware Neural
Scene Representations. in NurIPS, 2019.
• B. Mildenhall et al.: Local light field fusion: Practical view synthesis with prescriptive sampling
guidelines. SIGGRAPH 2019.