A Unified Objective for Novel Class Discovery

By Enrico Fini, Enver Sangineto, Stéphane Lathuilière, Zhun Zhong, Moin Nabi, Elisa Ricci. 2021

266 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Novel Class Discovery without Forgetting (2022, methodology): “– When compared with prominent class-discovery methods [16,19,60] adapted to our proposed setting, our methodology achieves improved class-discovery performance with significantly less forgetting.”
Class-incremental Novel Class Discovery (2022, methodology): “The task of automatically discovering novel (or new ) classes in an unsupervised fashion while leveraging some previously learned knowledge is referred to as novel class discovery (NCD) [15,16,36,37,11] (see Fig.”
Novel Class Discovery in Semantic Segmentation (2021, background): “In view of the practicability of NCD, previous works [8, 10] explore NCD in the image classification task.”
Generalized Category Discovery (2022, methodology): “RankStats [18] is widely used as a competitive baseline for novel category discovery, while UNO [13] is to the best of our knowledge the state-of-the-art method for NCD. Baseline: RankStats+ RankStats trains two classiﬁers on top of a shared feature representation: the ﬁrst head is fed instances…”
Residual Tuning: Toward Novel Category Discovery Without Labels (2022, unknown): “In contrast, the methods in the second group rely on “Joint Training,” through mixing both labeled and unlabeled images to accomplish the objective [16]–[19], [21].”
Spacing Loss for Discovering Novel Categories (2022, methodology): “A common theme in most NCD methodologies is to learn a feature extractor using the labeled data and use clustering [13, 15, 16], psuedo-labelling based learning [10, 11] or contrastive learning [17, 45] to identify classes in the unlabeled pool.”
Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data (2021, background): “performance by augmenting the training samples by mixing the labelled and unlabelled data [52], aggregating pseudopositive pairs with contrastive learning [51], designing a unified objective [12], and leveraging local part information [50].”
Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation (2021, unknown): “Concurrent to our work, several methods [28, 58, 57, 14] are proposed to improve the performance of novel category discovery from different perspectives, showing promising results.”