Few-shot Visual Reasoning with Meta-analogical Contrastive Learning
- URL: http://arxiv.org/abs/2007.12020v1
- Date: Thu, 23 Jul 2020 14:00:34 GMT
- Title: Few-shot Visual Reasoning with Meta-analogical Contrastive Learning
- Authors: Youngsung Kim, Jinwoo Shin, Eunho Yang, Sung Ju Hwang
- Abstract summary: We propose to solve a few-shot (or low-shot) visual reasoning problem, by resorting to analogical reasoning.
We extract structural relationships between elements in both domains, and enforce them to be as similar as possible with analogical learning.
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.
- Score: 141.2562447971
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective [48.99488315273868]
We present a contrastive knowledge distillation approach, which can be formulated as a sample-wise alignment problem with intra- and inter-sample constraints.
Our method minimizes logit differences within the same sample by considering their numerical values.
We conduct comprehensive experiments on three datasets including CIFAR-100, ImageNet-1K, and MS COCO.
arXiv Detail & Related papers (2024-04-22T11:52:40Z) - Pooling Image Datasets With Multiple Covariate Shift and Imbalance [22.53402104452306]
We show how viewing this problem from the perspective of Category theory provides a simple and effective solution.
We show the effectiveness of this approach via extensive experiments on real datasets.
arXiv Detail & Related papers (2024-03-05T02:20:33Z) - Investigate the Essence of Long-Tailed Recognition from a Unified
Perspective [11.080317683184363]
deep recognition models often suffer from long-tailed data distributions due to heavy imbalanced sample number across categories.
In this work, we demonstrate that long-tailed recognition suffers from both sample number and category similarity.
arXiv Detail & Related papers (2021-07-08T11:08:40Z) - Visual analogy: Deep learning versus compositional models [3.2435333321661983]
We compare human performance on visual analogies with the performance of alternative computational models.
Human reasoners achieved above-chance accuracy for all problem types, but made more errors in several conditions.
The compositional model based on part representations, but not the deep learning models, generated qualitative performance similar to that of human reasoners.
arXiv Detail & Related papers (2021-05-14T20:56:02Z) - An Empirical Comparison of Instance Attribution Methods for NLP [62.63504976810927]
We evaluate the degree to which different potential instance attribution agree with respect to the importance of training samples.
We find that simple retrieval methods yield training instances that differ from those identified via gradient-based methods.
arXiv Detail & Related papers (2021-04-09T01:03:17Z) - An Empirical Study on Measuring the Similarity of Sentential Arguments
with Language Model Domain Adaptation [0.0]
A dataset must be annotated using expertise in a variety of topics, making supervised learning with labeled data expensive.
We first adapted a pretrained language model to a domain of interest using self-supervised learning.
We fine-tuned the model to a task of measuring the similarity between sentences taken from different domains.
arXiv Detail & Related papers (2021-02-19T08:05:46Z) - Towards Visually Explaining Similarity Models [29.704524987493766]
We present a method to generate gradient-based visual attention for image similarity predictors.
By relying solely on the learned feature embedding, we show that our approach can be applied to any kind of CNN-based similarity architecture.
We show that our resulting attention maps serve more than just interpretability; they can be infused into the model learning process itself with new trainable constraints.
arXiv Detail & Related papers (2020-08-13T17:47:41Z) - Pairwise Supervision Can Provably Elicit a Decision Boundary [84.58020117487898]
Similarity learning is a problem to elicit useful representations by predicting the relationship between a pair of patterns.
We show that similarity learning is capable of solving binary classification by directly eliciting a decision boundary.
arXiv Detail & Related papers (2020-06-11T05:35:16Z) - Memory-Augmented Relation Network for Few-Shot Learning [114.47866281436829]
In this work, we investigate a new metric-learning method, Memory-Augmented Relation Network (MRN)
In MRN, we choose the samples that are visually similar from the working context, and perform weighted information propagation to attentively aggregate helpful information from chosen ones to enhance its representation.
We empirically demonstrate that MRN yields significant improvement over its ancestor and achieves competitive or even better performance when compared with other few-shot learning approaches.
arXiv Detail & Related papers (2020-05-09T10:09:13Z) - Learning What Makes a Difference from Counterfactual Examples and
Gradient Supervision [57.14468881854616]
We propose an auxiliary training objective that improves the generalization capabilities of neural networks.
We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task.
Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
arXiv Detail & Related papers (2020-04-20T02:47:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.