• Corpus ID: 227254688

Multi-Label Contrastive Learning for Abstract Visual Reasoning

@article{Malkinski2020MultiLabelCL,
  title={Multi-Label Contrastive Learning for Abstract Visual Reasoning},
  author={Mikolaj Malki'nski and Jacek Ma'ndziuk},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.01944}
}
For a long time the ability to solve abstract reasoning tasks was considered one of the hallmarks of human intelligence. Recent advances in application of deep learning (DL) methods led, as in many other domains, to surpassing human abstract reasoning performance, specifically in the most popular type of such problems - the Raven's Progressive Matrices (RPMs). While the efficacy of DL systems is indeed impressive, the way they approach the RPMs is very different from that of humans. State-of… 

Figures and Tables from this paper

Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
TLDR
This paper focuses on the most common type of AVR tasks—the Raven's Progressive Matrices (RPMs)—and provides a comprehensive review of the learning methods and deep neural models applied to solve RPMs, as well as, the RPM benchmark sets.
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
TLDR
A novel contrastive learning boosted multi-label prediction model based on a Gaussian mixture variational autoencoder (C-GMVAE), which learns a multimodal prior space and employs a contrastive loss.
A Review of Emerging Research Directions in Abstract Visual Reasoning
TLDR
This work proposes a taxonomy to categorise the AVR tasks along 5 dimensions: input shapes, hidden rules, target task, cognitive function, and specific challenge, and provides a unified view on the existing approaches to solving A VR tasks.
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework
TLDR
A hierarchical multi-label representation learning framework that can leverage all available labels and preserve the hierarchical relationship between classes is presented and a novel hierarchy preserving losses are introduced.

References

SHOWING 1-10 OF 40 REFERENCES
Hierarchical Rule Induction Network for Abstract Visual Reasoning
TLDR
A Hierarchical Rule Induction Network (HriNet) is proposed, by intimating human induction strategies and introducing a rule similarity metric based on the embeddings, so that HriNet can not only be trained using a tuplet loss but also infer the best answer according to the similarity score.
RAVEN: A Dataset for Relational and Analogical Visual REasoNing
TLDR
This work proposes a new dataset, built in the context of Raven's Progressive Matrices (RPM) and aimed at lifting machine intelligence by associating vision with structural, relational, and analogical reasoning in a hierarchical representation and establishes a semantic link between vision and reasoning by providing structure representation.
Abstract Reasoning with Distracting Features
TLDR
This paper proposes feature robust abstract reasoning (FRAR) model, which consists of a reinforcement learning based teacher network to determine the sequence of training and a student network for predictions that is able to beat the state-of-the-art models.
Learning Perceptual Inference by Contrasting
TLDR
It is demonstrated that CoPINet sets the new state-of-the-art for permutation-invariant models on two major datasets and concludes that spatial-temporal reasoning depends on envisaging the possibilities consistent with the relations between objects and can be solved from pixel-level inputs.
A simple neural network module for relational reasoning
TLDR
This work shows how a deep learning architecture equipped with an RN module can implicitly discover and learn to reason about entities and their relations.
Yin and Yang: Balancing and Answering Binary Visual Questions
TLDR
This paper addresses binary Visual Question Answering on abstract scenes as visual verification of concepts inquired in the questions by converting the question to a tuple that concisely summarizes the visual concept to be detected in the image.
DeepIQ: A Human-Inspired AI System for Solving IQ Test Problems
TLDR
The proposed DeepIQ system is composed of a deep autoencoder which is trained to learn a feature-based representation of various figure images used in IQ tests, an ensemble of shallow multilayer perceptrons applied to detection of feature differences, and a scoring module use for assessment of candidate answers.
Contrastive Learning of Structured World Models
TLDR
These experiments demonstrate that C-SWMs can overcome limitations of models based on pixel reconstruction and outperform typical representatives of this model class in highly structured environments, while learning interpretable object-based representations.
Measuring abstract reasoning in neural networks
TLDR
A dataset and challenge designed to probe abstract reasoning, inspired by a well-known human IQ test, is proposed and ways to both measure and induce stronger abstract reasoning in neural networks are introduced.
Abstract Diagrammatic Reasoning with Multiplex Graph Networks
TLDR
This work proposes MXGNet, a multilayer graph neural network for multi-panel diagrammatic reasoning tasks that combines three powerful concepts, namely, object-level representation, graph neural networks and multiplex graphs, for solving visual reasoning tasks.
...
1
2
3
4
...