Related papers: Spacing Loss for Discovering Novel Categories

This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures…

Generalized Category Discovery (GCD) utilizes labeled samples of known classes to discover novel classes in unlabeled samples. Existing methods show effective performance on artificial datasets with balanced distributions. However,…

We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a challenging category incremental learning setting where the goal is to develop models that can correctly categorize images from previously seen…

We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online point-wise clustering method with a simplified equal class-size…

Multi-label classification is a type of supervised learning where an instance may belong to multiple labels simultaneously. Predicting each label independently has been criticized for not exploiting any correlation between labels. In this…

A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised deep learning,…

On-the-Fly Category Discovery (OCD) aims to recognize known classes while simultaneously discovering emerging novel categories during inference, using supervision only from known classes during offline training. Existing approaches rely…

In this paper, we carry out null space analysis for Class-Specific Discriminant Analysis (CSDA) and formulate a number of solutions based on the analysis. We analyze both theoretically and experimentally the significance of each algorithmic…

In recent years, automated, supervised classification techniques have been fruitfully applied to labeling and organizing large astronomical databases. These methods require off-line classifier training, based on labeled examples from each…

This paper addresses the problem of Rehearsal-Free Continual Category Discovery (RF-CCD), which focuses on continuously identifying novel class by leveraging knowledge from labeled data. Existing methods typically train from scratch,…

Deep-embedding methods aim to discover representations of a domain that make explicit the domain's class structure and thereby support few-shot learning. Disentangling methods aim to make explicit compositional or factorial structure. We…

While neural networks trained for semantic segmentation are essential for perception in autonomous driving, most current algorithms assume a fixed number of classes, presenting a major limitation when developing new autonomous driving…

In Generalized Category Discovery (GCD), we cluster unlabeled samples of known and novel classes, leveraging a training dataset of known classes. A salient challenge arises due to domain shifts between these datasets. To address this, we…

This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign…

Although existing semi-supervised learning models achieve remarkable success in learning with unannotated in-distribution data, they mostly fail to learn on unlabeled data sampled from novel semantic classes due to their closed-set…

Generalized Category Discovery (GCD) aims to recognize both known and novel categories from a set of unlabeled data, based on another dataset labeled with only known categories. Without considering differences between known and novel…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

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…

Continuous Generalized Category Discovery (C-GCD) aims to continually discover novel classes from unlabelled image sets while maintaining performance on old classes. In this paper, we propose a novel learning framework, dubbed Neighborhood…

This paper introduces a novel approach to Generalized Category Discovery (GCD) by leveraging the concept of contextuality to enhance the identification and classification of categories in unlabeled datasets. Drawing inspiration from human…