Few-shot Visual Reasoning with Meta-analogical Contrastive Learning

While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same task. In this work, we propose to solve such a few-shot (or low-shot) visual reasoning problem, by resorting to analogical reasoning, which is a unique human ability to identify structural or relational similarity between two sets. Specifically, given training and test sets that contain the same type of visual reasoning problems, we extract the structural relationships between elements in both domains, and enforce them to be as similar as possible with analogical learning. We repeatedly apply this process with slightly modified queries of the same problem under the assumption that it does not affect the relationship between a training and a test sample. This allows to learn the relational similarity between the two samples in an effective manner even with a single pair of samples. We validate our method on RAVEN dataset, on which it outperforms state-of-the-art method, with larger gains when the training data is scarce. We further meta-learn our analogical contrastive learning model over the same tasks with diverse attributes, and show that it generalizes to the same visual reasoning problem with unseen attributes.

[1]  J. Raven,et al.  A NEW SERIES OF PERCEPTUAL TESTS: PRELIMINARY COMMUNICATION , 1936 .

[2]  M A Just,et al.  From the SelectedWorks of Marcel Adam Just 1990 What one intelligence test measures : A theoretical account of the processing in the Raven Progressive Matrices Test , 2016 .

[3]  Melanie Mitchell,et al.  Analogy-making as perception - a computer model , 1993, Neural network modeling and connectionism.

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  John E. Hummel,et al.  Distributed representations of structure: A theory of analogical access and mapping. , 1997 .

[6]  J. Raven,et al.  Raven Progressive Matrices , 2003 .

[7]  Aapo Hyvärinen,et al.  Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics , 2012, J. Mach. Learn. Res..

[8]  Yee Whye Teh,et al.  A fast and simple algorithm for training neural probabilistic language models , 2012, ICML.

[9]  K. Holyoak Analogy and Relational Reasoning , 2012 .

[10]  Koray Kavukcuoglu,et al.  Learning word embeddings efficiently with noise-contrastive estimation , 2013, NIPS.

[11]  Kristen Grauman,et al.  Analogy-preserving Semantic Embedding for Visual Object Categorization , 2013, ICML.

[12]  Yuting Zhang,et al.  Deep Visual Analogy-Making , 2015, NIPS.

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Razvan Pascanu,et al.  A simple neural network module for relational reasoning , 2017, NIPS.

[15]  Bo Dai,et al.  Contrastive Learning for Image Captioning , 2017, NIPS.

[16]  Michael Werman,et al.  IQ of Neural Networks , 2017, ArXiv.

[17]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[18]  Ron Sun,et al.  Similarity-Based Reasoning, Raven's Matrices, and General Intelligence , 2018, IJCAI.

[19]  Felix Hill,et al.  Measuring abstract reasoning in neural networks , 2018, ICML.

[20]  Yixin Zhu,et al.  Learning Perceptual Inference by Contrasting , 2019, NeurIPS.

[21]  Felix Hill,et al.  Learning to Make Analogies by Contrasting Abstract Relational Structure , 2019, ICLR.

[22]  Mikhail Khodak,et al.  A Theoretical Analysis of Contrastive Unsupervised Representation Learning , 2019, ICML.

[23]  Sjoerd van Steenkiste,et al.  Are Disentangled Representations Helpful for Abstract Visual Reasoning? , 2019, NeurIPS.

[24]  Feng Gao,et al.  RAVEN: A Dataset for Relational and Analogical Visual REasoNing , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Kecheng Zheng,et al.  Abstract Reasoning with Distracting Features , 2019, NeurIPS.