Related papers: Prototype Perturbation for Relaxing Alignment Cons…
In object re-identification (ReID), the development of deep learning techniques often involves model updates and deployment. It is unbearable to re-embedding and re-index with the system suspended when deploying new models. Therefore,…
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…
Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argue that the imbalance between old task and new task data…
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…
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…
Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…
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…
Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backward compatibility is also an important aspect for industrial…
Continual Learning (CL) aims to enable models to continuously acquire new knowledge from a sequence of tasks with avoiding the forgetting of learned information. However, existing CL methods only rely on the parameters of the most recent…
Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential drift in the feature…
Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…
Recently, prototype learning has emerged in semi-supervised medical image segmentation and achieved remarkable performance. However, the scarcity of labeled data limits the expressiveness of prototypes in previous methods, potentially…
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…
Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle this challenge, methods based on knowledge…
Despite considerable advances in deep reinforcement learning, it has been shown to be highly vulnerable to adversarial perturbations to state observations. Recent efforts that have attempted to improve adversarial robustness of…
Continual Learning (CL) seeks to enable neural networks to incrementally acquire new knowledge (plasticity) while retaining existing knowledge (stability). Although pre-trained models (PTMs) have provided a strong foundation for CL,…
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…
In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…
Local class imbalance and data heterogeneity across clients often trap prototype-based federated contrastive learning in a prototype bias loop: biased local prototypes induced by imbalanced data are aggregated into biased global prototypes,…
This paper proposes a novel Deep Positive-Negative Prototype (DPNP) model that combines prototype-based learning (PbL) with discriminative methods to improve class compactness and separability in deep neural networks. While PbL…