Related papers: Proxy-Anchor and EVT-Driven Continual Learning Met…

In this paper we offer a method and algorithm, which make possible fully autonomous (unsupervised) detection of new classes, and learning following a very parsimonious training priming (few labeled data samples only). Moreover, new unknown…

A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to…

The labor-intensive labeling for semantic segmentation has spurred the emergence of Unsupervised Semantic Segmentation. Recent studies utilize patch-wise contrastive learning based on features from image-level self-supervised pretrained…

Continual learning (CL) enables deep networks to acquire new knowledge while avoiding catastrophic forgetting. The powerful generalization ability of pre-trained models (PTMs), such as the Contrastive Language-Image Pre-training (CLIP)…

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in…

The natural world often follows a long-tailed data distribution where only a few classes account for most of the examples. This long-tail causes classifiers to overfit to the majority class. To mitigate this, prior solutions commonly adopt…

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies…

In this paper, we explore various statistical techniques for anomaly detection in conjunction with the popular Long Short-Term Memory (LSTM) deep learning model for transportation networks. We obtain the prediction errors from an LSTM…

We introduce the first work to tackle the image retrieval problem as a continuous operation. While the proposed approaches in the literature can be roughly categorized into two main groups: category- and instance-based retrieval, in this…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten…

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…

Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolating knowledge across tasks and resulting in suboptimal…

Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a…

Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In particular, updating an intelligent diagnosis system with…

In incremental classification tasks for hyperspectral images, catastrophic forgetting is an unavoidable challenge. While memory recall methods can mitigate this issue, they heavily rely on samples from old categories. This paper proposes a…

Set-valued classification, a new classification paradigm that aims to identify all the plausible classes that an observation belongs to, can be obtained by learning the acceptance regions for all classes. Many existing set-valued…

The ability to learn and retain a wide variety of tasks is a hallmark of human intelligence that has inspired research in artificial general intelligence. Continual learning approaches provide a significant step towards achieving this goal.…