Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/marcionicolau/awesome-neurosymbolic-cv

Awesome Neurosymbolic Computer Vision
https://github.com/marcionicolau/awesome-neurosymbolic-cv
List: awesome-neurosymbolic-cv
Last synced: about 1 month ago
JSON representation
Awesome Neurosymbolic Computer Vision
Host: GitHub
URL: https://github.com/marcionicolau/awesome-neurosymbolic-cv
Owner: marcionicolau
License: mit
Created: 2024-01-09T14:23:38.000Z (12 months ago)
Default Branch: main
Last Pushed: 2024-01-10T12:48:02.000Z (12 months ago)
Last Synced: 2024-10-29T11:34:10.068Z (about 2 months ago)
Size: 38.1 KB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project

ultimate-awesome - awesome-neurosymbolic-cv - Awesome Neurosymbolic Computer Vision. (Other Lists / PowerShell Lists)
README

        # Awesome Neurosymbolic Computer Vision

This repository is built for paper: Neurosymbolic Computer Vision: A Survey

## Citation

- Neurosymbolic Computer Vision Publications

  -  [Learning and Reasoning from symbolic rules](#learning-and-reasoning-from-symbolic-rules)

  -  [Learning from symbolic rules](#learning-from-symbolic-rules)

  -  [Reasoning from symbolic rules](#reasoning-from-symbolic-rules)

  -  [Learning and Reasoning from approximated rules](#learning-and-reasoning-from-approximated-rules)

  -  [Frameworks](#frameworks)

  -  [Datasets](#datasets)

## Learning and Reasoning from symbolic rules

- *ABL*: Bridging Machine Learning and Logical Reasoning by Abductive Learning. 2019. [📑](https://proceedings.neurips.cc/paper_files/paper/2019/file/9c19a2aa1d84e04b0bd4bc888792bd1e-Paper.pdf).

- *LB-VQA*: Visual Question Answering based on Formal Logic. 2021. [📑](https://doi.org/10.1109/icmla52953.2021.00157).

- *DeepProbLog*: Neural probabilistic logic programming in DeepProbLog. 2021. [📑](https://doi.org/10.1016/j.artint.2021.103504). [💻](https://github.com/ML-KULeuven/deepproblog).

- *DFLO*: Analyzing Differentiable Fuzzy Logic Operators. 2022. [📑](https://doi.org/10.1016/j.artint.2021.103602).

- *VDP*: Composing Neural Learning and Symbolic Reasoning with an Application to Visual Discrimination. 2022. [📑](https://doi.org/10.24963/ijcai.2022/466). [💻](https://github.com/muraliadithya/vdp).

- *NLRL*: Neural logic rule layers. 2022. [📑](https://doi.org/10.1016/j.ins.2022.03.021).

- *Rapid*: Rapid Image Labeling via Neuro-Symbolic Learning. 2023. [📑](https://doi.org/10.1145/3580305.3599485). [💻](https://github.com/Neural-Symbolic-Image-Labeling/Rapid/).

- *RelaTe*: Sample-Efficient Learning of Novel Visual Concepts. 2023. [📑](https://doi.org/10.48550/arxiv.2306.09482).

- *SMTLayer*: Learning Modulo Theories. 2023. [📑](https://doi.org/10.48550/arxiv.2301.11435).

- αILP: thinking visual scenes as differentiable logic programs. 2023. [📑](https://doi.org/10.1007/s10994-023-06320-1).

## Learning from symbolic rules

- *SBR*: Integrating Prior Knowledge into Deep Learning. 2017. [📑](https://doi.org/10.1109/icmla.2017.00-37).

- *Semantic Loss*: A Semantic Loss Function for Deep Learning with Symbolic Knowledge. 2017. [📑](https://proceedings.mlr.press/v80/xu18h.html). [💻](https://github.com/UCLA-StarAI/Semantic-Loss).

- *RwPK*: Regularizing deep networks with prior knowledge: A constraint-based approach. 2021. [📑](https://doi.org/10.1016/j.knosys.2021.106989). [💻](https://sites.google.com/view/regularizingdeepnetworks/home).

- *logLTN*: Differentiable Fuzzy Logic in the Logarithm Space. 2023. [📑](https://doi.org/10.48550/arxiv.2306.14546). [💻](https://github.com/sbadredd/logltn-experiments).

 

## Reasoning from symbolic rules

- *SSR*: A Scalable Reasoning and Learning Approach for Neural-Symbolic Stream Fusion. 2021. [📑](https://doi.org/10.1609/aaai.v35i6.16633).

- *NSL*: Unifying neural learning and symbolic reasoning for spinal medical report generation. 2021. [📑](https://doi.org/10.1016/j.media.2020.101872).

- *NS-VQA*:  A Neuro-Symbolic ASP Pipeline for Visual Question Answering. 2022. [📑](https://doi.org/10.1017/s1471068422000229). [💻](https://github.com/macehil/nesy-asp-vqa-pipeline).

- *DUA*: Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework. 2022. [📑](https://doi.org/10.1007/s10994-022-06142-7).

- *FO-SL*: Composing Neural Learning and Symbolic Reasoning with an Application to Visual Discrimination. 2022. [📑](https://doi.org/10.24963/ijcai.2022/466). [💻](https://github.com/muraliadithya/vdp).

 

## Learning and Reasoning from approximated rules

- *SII*: Logic Tensor Networks for Semantic Image Interpretation. 2017. [📑](). [💻](https://gitlab.fbk.eu/donadello/LTN_IJCAI17).

- *▽-FOL*: Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning". 2020. [📑](https://proceedings.mlr.press/v119/amizadeh20a.html). [💻](https://github.com/microsoft/DFOL-VQA).

- *PrediNet*: An Explicitly Relational Neural Network Architecture. 2020. [📑](https://dl.acm.org/doi/abs/10.5555/3524938.3525735). 

- *DLM*: Integrating Learning and Reasoning with Deep Logic Models. 2020. [📑](https://doi.org/10.1007/978-3-030-46147-8_31). 

- *PrAE*: Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution. 2021. [📑](https://doi.org/10.1109/cvpr46437.2021.00961).

- *Faster-LTN*: A Neuro-Symbolic, End-to-End Object Detection Architecture. 2021. [📑](https://doi.org/10.1007/978-3-030-86340-1_4). [💻](https://gitlab.com/grains2/Faster-LTN).

- *TCAV-LTN*: Neural-Symbolic Integration for Interactive Learning and Conceptual Grounding. 2021. [📑](http://arxiv.org/abs/2112.11805v2). 

- *pix2rule*: End-to-end Neuro-symbolic Rule Learning. 2021. [📑](https://ceur-ws.org/Vol-2986/paper3.pdf). [💻](https://github.com/nuric/pix2rule).

- *NeSy XIL*: **Right for the Right Concept**: Revising Neuro-Symbolic Concepts by Interacting with their Explanations. 2021. [📑](https://doi.org/10.1109/cvpr46437.2021.00362). [💻](https://github.com/ml-research/NeSyXIL).

- *Scallop*: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning. 2021. [📑](https://openreview.net/forum?id=ngdcA1tlDvj). [💻](https://github.com/scallop-lang/scallop-old).

- *Apperception Engine*: Making sense of raw input. 2021. [📑](https://doi.org/10.1016/j.artint.2021.103521). [💻](https://github.com/RichardEvans/apperception).

- *PALO*: A probabilistic approximate logic for neuro-symbolic learning and reasoning. 2022. [📑](https://doi.org/10.1016/j.jlamp.2021.100719).

- _BPGR_: A Probabilistic Graphical Model Based on Neural-symbolic Reasoning for Visual Relationship Detection. 2022. [📑](https://doi.org/10.1109/cvpr52688.2022.01035).

- *A-NeSI*: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference. 2022. [📑](https://doi.org/10.48550/arxiv.2212.12393). [💻](https://github.com/HEmile/a-nesi).

- *e-LENs*: Entropy-Based Logic Explanations of Neural Networks. 2022. [📑](https://doi.org/10.1609/aaai.v36i6.20551). [💻](https://github.com/pietrobarbiero/entropy-lens).

- *Graybox XAI*: A Neural-Symbolic learning framework to produce interpretable predictions for image classification. 2022. [📑](https://doi.org/10.1016/j.knosys.2022.109947). [💻](https://github.com/AdriBento/Greybox-).

- *PROTO-LTN*: PROTOtypical Logic Tensor Networks (PROTO-LTN) for Zero Shot Learning. 2022. [📑](https://doi.org/10.1109/icpr56361.2022.9956239). [💻](https://github.com/FrancescoManigrass/PROTO-LTN).

- *RILL*: Reduced Implication-bias Logic Loss for Neuro-Symbolic Learning. 2023. [📑](https://doi.org/10.48550/arxiv.2208.06838). [💻](https://git.nju.edu.cn/Alkane/clion).

- *GBPGR*: A Novel Neural-symbolic System under Statistical Relational Learning. 2023. [📑](https://doi.org/10.48550/arxiv.2309.08931). 

- *CL-STE*: Injecting Logical Constraints into Neural Networks via Straight-Through Estimators. 2023. [📑](https://proceedings.mlr.press/v162/yang22h/yang22h.pdf). 

- *DCR*: Interpretable Neural-Symbolic Concept Reasoning. 2023. [📑](https://proceedings.mlr.press/v202/barbiero23a.html). [💻](https://github.com/pietrobarbiero/pytorch_explain).

- *NEUMANN*: Learning Differentiable Logic Programs for Abstract Visual Reasoning. 2023. [📑](https://doi.org/10.48550/arxiv.2307.00928). [💻](https://github.com/ml-research/neumann/).

- *LEN*: Logic Explained Networks. 2023. [📑](https://doi.org/10.1016/j.artint.2022.103822). [💻](https://github.com/pietrobarbiero/pytorch_explain).

- *LogicSeg*: Parsing Visual Semantics with Neural Logic Learning and Reasoning. 2023. [📑](http://arxiv.org/abs/2309.13556). 

- *NeSyFOLD*: Neurosymbolic Framework for Interpretable Image Classification. 2023. [📑](https://doi.org/10.48550/arxiv.2301.12667). 

- *NeuPSL*: Neural Probabilistic Soft Logic. 2023. [📑](https://doi.org/10.24963/ijcai.2023/461). [💻](https://github.com/linqs/neupsl-ijcai23).

- *ILR*: Refining neural network predictions using background knowledge. 2023. [📑](https://doi.org/10.1007/s10994-023-06310-3). [💻](https://github.com/DanieleAlessandro/IterativeLocalRefinement).

- *Semantic Strengthening*: Semantic Strengthening of Neuro-Symbolic Learning. 2023. [📑](https://doi.org/10.48550/arxiv.2302.14207). [💻](https://github.com/UCLAStarAI/Semantic-Strengthening).

  

## Frameworks

- *LTN*: Logic Tensor Networks. 2017. [📑](https://doi.org/10.1016/j.artint.2021.103649). [💻](https://github.com/logictensornetworks/logictensornetworks).

- *Scallop*: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning. 2021. [📑](https://openreview.net/forum?id=ngdcA1tlDvj). [💻](https://www.scallop-lang.org/).

- *PyTorch Explain*: Interpretable Neural-Symbolic Concept Reasoning. 2022. [📑](https://proceedings.mlr.press/v202/barbiero23a.html). [💻](https://pypi.org/project/torch-explain/).

 

## Datasets

- MNIST. [📑](https://doi.org/10.1109/5.726791). [💾](http://yann.lecun.com/exdb/mnist/).

- PASCAL-PART. [📑](https://dl.acm.org/doi/10.1109/CVPR.2014.254). [💾](https://roozbehm.info/pascal-parts/pascal-parts.html).

- CLEVR. [📑](https://doi.org/10.1109/CVPR.2017.215). [💾](https://cs.stanford.edu/people/jcjohns/clevr/).

- GQA. [📑](https://arxiv.org/abs/1902.09506). [💾](https://cs.stanford.edu/people/dorarad/gqa/index.html).

- CIFAR-10. [📑](https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf). [💾](https://www.cs.toronto.edu/~kriz/cifar.html).

- Visual Sudoku. [📑](https://ceur-ws.org/Vol-3212/paper2.pdf). [💾](https://github.com/linqs/visual-sudoku-puzzle-classification).

- CLEVR-Hans. [📑](https://doi.org/10.1109/cvpr46437.2021.00362). [💾](https://github.com/ml-research/CLEVR-Hans).

- ImageNet. [📑](https://doi.org/10.1007/s11263-015-0816-y). [💾](https://www.image-net.org/challenges/LSVRC/2010/index).

- CUB. [📑](https://doi.org/10.1109/ICCV.2011.6126539). [💾](https://www.vision.caltech.edu/datasets/cub_200_2011/).