Siamese Neural Networks for One-Shot Image Recognition

By Gregory R. Koch. 2015

4,748 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (2017, methodology): “6 % – – Siamese nets (Koch, 2015) 97 .”
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning (2016, background): “In the broader context of machine learning, there has been a lot of interest in one-shot learning for object classiﬁcation (Vilalta & Drissi, 2002; Fei-Fei et al., 2006; Larochelle et al., 2008; Lake et al., 2011; Koch, 2015).”
Matching Networks for One Shot Learning (2016, methodology): “Like the authors in [11], we also test our method trained on Omniglot on a completely disjoint task – one-shot, 10 way MNIST classification.”
Growing a Brain: Fine-Tuning by Increasing Model Capacity (2017, background): “Transfer learning is related to both multi-task learning [32, 4, 28, 10, 11, 45, 24, 2] and learning novel categories from few examples [49, 19, 21, 35, 51, 22, 5, 13, 50, 47, 31].”
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? (2020, methodology): “rs and use them to design proper kernel functions. The predicted label of a query is the weighted sum of labels over support samples. Metric-based meta-learning aims to learn a task-dependent metric. [22] used Siamese network to encode image pairs and predict conﬁdence scores for each pair. Matching”
Exploring Simple Siamese Representation Learning (2020, background): “Their applications include signature [4] and face [34] veriﬁcation, tracking [3], one-shot learning [23], and others.”
One-Shot Imitation Learning (2017, background): “One-shot and few-shot learning has been studied for image recognition (Vinyals et al., 2016; Koch, 2015; Santoro et al., 2016; Ravi & Larochelle, 2017), generative modeling (Edwards & Storkey, 2017; Rezende et al., 2016), learning “fast” reinforcement learning agents with recurrent policies (Duan…”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “Matching-based methods [28, 75, 78, 89] instead learn representations for similarity functions [11, 16, 17, 44, 82], in the hope that the similarities will generalize to new data.”
Meta-Learning Probabilistic Inference for Prediction (2018, neutral): “Omniglot miniImageNet 5-way accuracy (%) 20-way accuracy (%) 5-way accuracy (%) Method 1-shot 5-shot 1-shot 5-shot 1-shot 5-shot Siamese Nets (Koch et al., 2015) 97.”
Meta-learning with differentiable closed-form solvers (2018, methodology): “On one side of the spectrum, methods related to nearest-neighbours, such as learning similarity functions (Koch et al., 2015; Vinyals et al., 2016; Snell et al., 2017), are fast but rely solely on the quality of the similarity metric, with no additional data-dependent adaptation at test-time.”
Prototypical Networks for Few-shot Learning (2017, background): “Few-shot classification [22, 18, 15] is a task in which a classifier must be adapted to accommodate new classes not seen in training, given only a few examples of each of these classes.”
Learning feed-forward one-shot learners (2016, methodology): “[10] using much deeper networks applied to images of size 105 × 105.”
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data (2016, background): “Siamese networks: Our ﬁrst attempt was to train a pair of siamese networks, introduced by Brom-ley et al. (1993) in the context of one-shot learning and later improved by Koch (2015).”
A Closer Look at Few-shot Classification (2019, background): “The intuition is that if a model can determine the similarity of two images, it can classify an unseen input image with the labeled instances Koch et al. (2015).”
Meta-Learning with Latent Embedding Optimization (2018, background): “The latter can be classified as metric-based [18, 40, 37], memory-based [35, 32], model-based [27, 26, 8, 9], and optimization-based [6, 7, 29].”
Meta-Learning for Semi-Supervised Few-Shot Classification (2018, background): “Previous work in metric-learning for few-shot-classiﬁcation includes Deep Siamese Networks (Koch et al., 2015), Matching Networks (Vinyals et al., 2016), and Prototypical Networks (Snell et al., 2017), which is the model we extend to the semi-supervised setting in our work.”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Plenty of advanced techniques, such as metric learning [84] and meta learning [85], [86], have been introduced for one-shot object recognition and image classiﬁcation [87], [88], [89].”
Data Augmentation Generative Adversarial Networks (2017, background): “One early but effective approach to one-shot learning involved the use of Siamese networks (Koch, 2015).”