Related papers: Darwinian Model Upgrades: Model Evolving with Sele…
Conventional model upgrades for visual search systems require offline refresh of gallery features by feeding gallery images into new models (dubbed as "backfill"), which is time-consuming and expensive, especially in large-scale…
The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images. A pioneering work introduced backward-compatible training, where the new…
We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if…
Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computational cost and even entails the downtime of the service.…
Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as backfilling and can be especially costly in the real world…
In many retrieval systems the original high dimensional data (e.g., images) is mapped to a lower dimensional feature through a learned embedding model. The task of retrieving the most similar data from a gallery set to a given query data is…
In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the idea of backward compatible training (BCT) was proposed. To…
Deep Generative Models (DGMs) are versatile tools for learning data representations while adequately incorporating domain knowledge such as the specification of conditional probability distributions. Recently proposed DGMs tackle the…
We introduce the first Automatically Differentiable Model Updating (ADiMU) framework that finds any history-dependent material model from full-field displacement and global force data (global, indirect discovery) or from strain-stress data…
Modern retrieval systems often struggle with upgrading to new and more powerful models due to the incompatibility of embeddings between the old and new models. This necessitates a costly process known as backfilling, which involves…
We study the backward compatible problem for person re-identification (Re-ID), which aims to constrain the features of an updated new model to be comparable with the existing features from the old model in galleries. Most of the existing…
Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires…
The traditional paradigm to update retrieval models requires re-computing the embeddings of the gallery data, a time-consuming and computationally intensive process known as backfilling. To circumvent backfilling, Backward-Compatible…
We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…
Kinship verification is a long-standing research challenge in computer vision. The visual differences presented to the face have a significant effect on the recognition capabilities of the kinship systems. We argue that aggregating multiple…
When machine learning systems meet real world applications, accuracy is only one of several requirements. In this paper, we assay a complementary perspective originating from the increasing availability of pre-trained and regularly…
The boosting on the need of security notably increased the amount of possible facial recognition applications, especially due to the success of the Internet of Things (IoT) paradigm. However, although handcrafted and deep learning-inspired…
Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with…
Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…
Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in search and retrieval systems where it is crucial to avoid reprocessing of the gallery…