# Effective Abstract Reasoning with Dual-Contrast Network

arXiv: https://arxiv.org/abs/2205.13720 · HTML: https://mlsanity.com/paper/2205.13720/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 27 May 2022.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [Learning to Transfer Examples for Partial Domain Adaptation](https://mlsanity.com/paper/1903.12230/) (2019)
- [Learning Perceptual Inference by Contrasting](https://mlsanity.com/paper/1912.00086/) (2019)
- [Abstract Diagrammatic Reasoning with Multiplex Graph Networks](https://mlsanity.com/paper/2006.11197/) (2020)
- [Explainable Video Action Reasoning via Prior Knowledge and State Transitions](https://mlsanity.com/paper/1908.10700/) (2019)
- [Abstract Reasoning with Distracting Features](https://mlsanity.com/paper/1912.00569/) (2019)
- [Few-shot Visual Reasoning with Meta-analogical Contrastive Learning](https://mlsanity.com/paper/2007.12020/) (2020)
- [IQ of Neural Networks](https://mlsanity.com/paper/1710.01692/) (2017)
- [Solving Raven's Progressive Matrices with Multi-Layer Relation Networks](https://mlsanity.com/paper/2003.11608/) (2020)
- [Solving Raven's Progressive Matrices with Neural Networks](https://mlsanity.com/paper/2002.01646/) (2020)

## Built on by (most cited first, 23 of 23)

- [Learning to reason over visual objects](https://mlsanity.com/paper/2303.02260/) (2023)
- [Slot Abstractors: Toward Scalable Abstract Visual Reasoning](https://mlsanity.com/paper/2403.03458/) (2024)
- [SAViR-T: Spatially Attentive Visual Reasoning with Transformers](https://mlsanity.com/paper/2206.09265/) (2022)
- [Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2303.11730/) (2023)
- [Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability](https://mlsanity.com/paper/2210.14914/) (2022)
- [Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems](https://mlsanity.com/paper/2307.07734/) (2023)
- [One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems](https://mlsanity.com/paper/2312.09997/) (2023)
- [Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces](https://mlsanity.com/paper/2209.08750/) (2022)
- [A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processing](https://mlsanity.com/paper/2309.10532/) (2023)
- [Sandra -- A Neuro-Symbolic Reasoner Based On Descriptions And Situations](https://mlsanity.com/paper/2402.00591/) (2024)
- [A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning](https://mlsanity.com/paper/2406.11061/) (2024)
- [Learning Visual Abstract Reasoning through Dual-Stream Networks](https://mlsanity.com/paper/2411.19451/) (2024)
- [Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introduction](https://mlsanity.com/paper/2302.04238/) (2023)
- [Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection](https://mlsanity.com/paper/2401.09966/) (2024)
- [Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Ability](https://mlsanity.com/paper/2403.03190/) (2024)
- [Learning Abstract Visual Reasoning via Task Decomposition: A Case Study in Raven Progressive Matrices](https://mlsanity.com/paper/2308.06528/) (2023)
- [Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability](https://mlsanity.com/paper/2407.02688/) (2024)
- [Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture](https://mlsanity.com/paper/2501.11896/) (2025)
- [D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability](https://mlsanity.com/paper/2403.03452/) (2024)
- [DIO: Refining Mutual Information and Causal Chain to Enhance Machine Abstract Reasoning Ability](https://mlsanity.com/paper/2508.15387/) (2025)
- [A Study of Rule Omission in Raven's Progressive Matrices](https://mlsanity.com/paper/2510.03127/) (2025)
- [Supporting Calibrated Reliance in Human-AI Collaboration: Different Strategies for Different Tasks](https://mlsanity.com/paper/2604.03237/) (2026)
- [DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENs](https://mlsanity.com/paper/2604.17584/) (2026)

## Abstract (arXiv)

As a step towards improving the abstract reasoning capability of machines, we aim to solve Raven's Progressive Matrices (RPM) with neural networks, since solving RPM puzzles is highly correlated with human intelligence. Unlike previous methods that use auxiliary annotations or assume hidden rules to produce appropriate feature representation, we only use the ground truth answer of each question for model learning, aiming for an intelligent agent to have a strong learning capability with a small amount of supervision. Based on the RPM problem formulation, the correct answer filled into the missing entry of the third row/column has to best satisfy the same rules shared between the first two rows/columns. Thus we design a simple yet effective Dual-Contrast Network (DCNet) to exploit the inherent structure of RPM puzzles. Specifically, a rule contrast module is designed to compare the latent rules between the filled row/column and the first two rows/columns; a choice contrast module is designed to increase the relative differences between candidate choices. Experimental results on the RAVEN and PGM datasets show that DCNet outperforms the state-of-the-art methods by a large margin of 5.77%. Further experiments on few training samples and model generalization also show the effectiveness of DCNet. Code is available at https://github.com/visiontao/dcnet.