Category: 10. Image similarity search

Introduction Self-supervised learning Self-supervised representation learning aims to obtain robust representations of samples from raw data without expensive labels or annotations. Early methods in this field focused on defining pretraining tasks which involved a surrogate task on a domain with ample weak supervision labels. Encoders trained to solve such tasks are expected to learn general…

Overview This example is based on the “Metric learning for image similarity search” example. We aim to use the same data set but implement the model using TensorFlow Similarity. Metric learning aims to train models that can embed inputs into a high-dimensional space such that “similar” inputs are pulled closer to each other and “dissimilar” inputs are…

Overview Metric learning aims to train models that can embed inputs into a high-dimensional space such that “similar” inputs, as defined by the training scheme, are located close to each other. These models once trained can produce embeddings for downstream systems where such similarity is useful; examples include as a ranking signal for search or…

Introduction A Siamese Network is a type of network architecture that contains two or more identical subnetworks used to generate feature vectors for each input and compare them. Siamese Networks can be applied to different use cases, like detecting duplicates, finding anomalies, and face recognition. This example uses a Siamese Network with three identical subnetworks. We will…

Introduction Siamese Networks are neural networks which share weights between two or more sister networks, each producing embedding vectors of its respective inputs. In supervised similarity learning, the networks are then trained to maximize the contrast (distance) between embeddings of inputs of different classes, while minimizing the distance between embeddings of similar classes, resulting in embedding…

Introduction This example demonstrates how to apply the Semantic Clustering by Adopting Nearest neighbors (SCAN) algorithm (Van Gansbeke et al., 2020) on the CIFAR-10 dataset. The algorithm consists of two phases: Setup Prepare the data Define hyperparameters Implement data preprocessing The data preprocessing step resizes the input images to the desired target_size and applies feature-wise normalization. Note that, when using keras.applications.ResNet50V2 as the…

Introduction Fetching similar images in (near) real time is an important use case of information retrieval systems. Some popular products utilizing it include Pinterest, Google Image Search, etc. In this example, we will build a similar image search utility using Locality Sensitive Hashing (LSH) and random projection on top of the image representations computed by a pretrained image classifier.…