A Unified Objective for Novel Class Discovery
TL
TL;DR
A UNified Objective function (UNO) for discovering novel classes, with the explicit purpose of favoring synergy between supervised and unsupervised learning, and outperforms the state of the art on several benchmarks.
Abstract
In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labeled set containing different, but related classes. Existing approaches tackle this problem by considering multiple objective functions, usually involving specialized loss terms for the labeled and the unlabeled samples respectively, and often requiring auxiliary regularization terms. In this paper we depart from this traditional scheme and introduce a UNified Objective function (UNO) for discovering novel classes, with the explicit purpose of favoring synergy between supervised and unsupervised learning. Using a multi-view self-labeling strategy, we generate pseudo-labels that can be treated homogeneously with ground truth labels. This leads to a single classification objective operating on both known and unknown classes. De-spite its simplicity, UNO outperforms the state of the art by a significant margin on several benchmarks (≈ +10% on CIFAR-100 and +8% on ImageNet). The project page is available at : https://ncd-uno.github.io.
References33 items
1
ScaleNet: An Unsupervised Representation Learning Method for Limited Information
2
Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
3
AutoNovel: Automatically Discovering and Learning Novel Visual Categories
4
Neighborhood Contrastive Learning for Novel Class Discovery
5