paper-with-me

홈 › Papers

A Neural-Symbolic Architecture for Inverse Graphics Improved by Lifelong Meta-Learning

2019-05-22 · Michael Kissner, Helmut Mayer

We follow the idea of formulating vision as inverse graphics and propose a new type of element for this task, a neural-symbolic capsule. It is capable of de-rendering a scene into semantic information feed-forward, as well as rendering it feed-backward. An initial set of capsules for graphical primitives is obtained from a generative grammar and connected into a full capsule network. Lifelong meta-learning continuously improves this network's detection capabilities by adding capsules for new and more complex objects it detects in a scene using few-shot learning. Preliminary results demonstrate the potential of our novel approach.

📄 PDF Abstract BibTeX arXiv:1905.08910

Code (1)

Kayzaks/VividNet 공식 구현

Tasks

Few-Shot LearningMeta-Learning

Similar Papers 제목 키워드 기반

A Neural-Symbolic Framework for Mental Simulation

2020-08-05 · Michael Kissner

We present a neural-symbolic framework for observing the environment and continuously learning visual semantics and intuitive physics to reproduce them in an interactive simulation. The framework consists of five parts, …

Meta-Learning

Neuro-Logic Lifelong Learning

2025-11-16 · Bowen He, Xiaoan Xu, Alper Kamil Bozkurt, Vahid Tarokh 외 arxiv

Solving Inductive Logic Programming (ILP) problems with neural networks is a key challenge in Neural-Symbolic Ar- tificial Intelligence (AI). While most research has focused on designing novel network architectures for i…

Inductive logic programming

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning

2026-01-16 · Shaofeng Yin, Jiaxin Ge, Zora Zhiruo Wang, Chenyang Wang 외 arxiv

Vision-as-inverse-graphics, the concept of reconstructing images into editable programs, remains challenging for Vision-Language Models (VLMs), which inherently lack fine-grained spatial grounding in one-shot settings. T…

Multimodal Reasoning3D Reconstruction

Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder

2024-10-30 · Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi, Laurent Caraffa 외

While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides reducing the training and rendering complex…

3D geometryNeRF

HOUDINI: Lifelong Learning as Program Synthesis

2018-03-31 · NeurIPS 2018 12 · Lazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles Sutton 외

We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing high-level concepts across domains and learning complex procedures are key challen…

Lifelong learningProgram SynthesisTransfer Learning