• Corpus ID: 13874643

Siamese Neural Networks for One-Shot Image Recognition

  title={Siamese Neural Networks for One-Shot Image Recognition},
  author={Gregory R. Koch},
The process of learning good features for machine learning applications can be very computationally expensive and may prove difficult in cases where little data is available. A prototypical example of this is the one-shot learning setting, in which we must correctly make predictions given only a single example of each new class. In this paper, we explore a method for learning siamese neural networks which employ a unique structure to naturally rank similarity between inputs. Once a network has… 

Figures and Tables from this paper

Multi-Resolution Siamese Networks for One-Shot Learning
This work proposes an improved architecture and a novel training method that increases a 1-shot 5-way classification accuracy on 5 entirely novel classes by around 5%, 19%, 18% and 13% respectively compared to vanilla Siamese networks when tested on Omniglot, Tiny-Imagenet, CIFAR100 as well as a custom dataset recorded with an event-driven camera.
One-Shot Learning in Discriminative Neural Networks
A Bayesian procedure for updating a pretrained convnet to classify a novel image category for which data is limited is explored, which demonstrates competitive performance with state-of-the-art methods whilst also being consistent with 'normal' methods for training deep networks on large data.
Compare Learning: Bi-Attention Network for Few-Shot Learning
  • Li KeMeng PanWeigao WenDong Li
  • Computer Science
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
A novel approach named Bi-attention network to compare the instances is proposed, which can measure the similarity between embeddings of instances precisely, globally and efficiently and is verified on two benchmarks.
One-shot Learning with Siamese Networks for Environmental Audio
The results show that convolutional siamese networks are indeed a valid approach to the difficult one-shot classification task for environmental audio.
One-Shot Learning for Handwritten Character Recognition
Though shadowed by more modern approaches, this project reveals that even relatively simple deep learning models provide compelling results in many domains – including one-shot learning.
One Shot Logo Recognition Based on Siamese Neural Networks
This work presents an approach for one-shot logo recognition that relies on a Siamese neural network (SNN) embedded with a pre-trained model that is fine-tuned on a challenging logo dataset. Although
Subspace Networks for Few-shot Classification
We propose subspace networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each
Comparative study of deep learning methods for one-shot image classification (abstract)
A comparative study of the most used one-shot learning models, on a challenging real-world dataset, i.e Fashion-MNIST, to understand better the behavior of various deep learning models and approaches.
Robust Compare Network for Few-Shot Learning
This work argues that it is desirable to learn a robust encoder that can draw inferences about other cases from one example, and improves the accuracy of few-shot learning by mining the internal mechanism of deep networks, which can leverage label information more effectively.
Face Recognition - A One-Shot Learning Perspective
This research aims to combine the best of deep learned features with a traditional One- shot learning framework achieving over 90% accuracy on 5-way One-Shot tasks, and 84% on 50-way one-Shot problems.


Very Deep Convolutional Networks for Large-Scale Image Recognition
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
One-shot learning by inverting a compositional causal process
A Hierarchical Bayesian model based on com-positionality and causality that can learn a wide range of natural (although simple) visual concepts, generalizing in human-like ways from just one image.
One shot learning of simple visual concepts
A generative model of how characters are composed from strokes is introduced, where knowledge from previous characters helps to infer the latent strokes in novel characters, using a massive new dataset of handwritten characters.
Learning a similarity metric discriminatively, with application to face verification
The idea is to learn a function that maps input patterns into a target space such that the L/sub 1/ norm in the target space approximates the "semantic" distance in the input space.
A Fast Learning Algorithm for Deep Belief Nets
A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Learning Deep Architectures for AI
The motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer modelssuch as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks are discussed.
One-shot learning of object categories
It is found that on a database of more than 100 categories, the Bayesian approach produces informative models when the number of training examples is too small for other methods to operate successfully.
A Bayesian approach to unsupervised one-shot learning of object categories
This work presents a method for learning object categories from just a few images, based on incorporating "generic" knowledge which may be obtained from previously learnt models of unrelated categories, in a variational Bayesian framework.
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.
Sparse Representations for Fast, One-Shot Learning
A novel model of fast learning that exploits the properties of sparse representations and the constraints imposed by a plausible hardware mechanism and encapsulate phonological information as bidirectional boolean constraint relations operating on the classical linguistic representations of speech sounds in term of distinctive features is proposed.