OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World

TL;DR

OpenMix is a novel method that enhances open world visual category discovery by mixing labeled and unlabeled data to improve pseudo-label credibility and exploit object relations, outperforming existing methods.

Contribution

The paper introduces OpenMix, a dynamic data mixing technique that leverages labeled and unlabeled data to improve novel class discovery in open world settings.

Findings

OpenMix outperforms state-of-the-art methods on three classification datasets.

It effectively prevents overfitting on incorrect pseudo-labels.

The method enhances the exploitation of object relations among new classes.

Abstract

In this paper, we tackle the problem of discovering new classes in unlabeled visual data given labeled data from disjoint classes. Existing methods typically first pre-train a model with labeled data, and then identify new classes in unlabeled data via unsupervised clustering. However, the labeled data that provide essential knowledge are often underexplored in the second step. The challenge is that the labeled and unlabeled examples are from non-overlapping classes, which makes it difficult to build the learning relationship between them. In this work, we introduce OpenMix to mix the unlabeled examples from an open set and the labeled examples from known classes, where their non-overlapping labels and pseudo-labels are simultaneously mixed into a joint label distribution. OpenMix dynamically compounds examples in two ways. First, we produce mixed training images by incorporating labeled examples with unlabeled examples. With the benefits of unique prior knowledge in novel class discovery, the generated pseudo-labels will be more credible than the original unlabeled predictions. As a result, OpenMix helps to prevent the model from overfitting on unlabeled samples that may be assigned with wrong pseudo-labels. Second, the first way encourages the unlabeled examples with high class-probabilities to have considerable accuracy. We introduce these examples as reliable anchors and further integrate them with unlabeled samples. This enables us to generate more combinations in unlabeled examples and exploit finer object relations among the new classes. Experiments on three classification datasets demonstrate the effectiveness of the proposed OpenMix, which is superior to state-of-the-art methods in novel class discovery.