A Simple Parametric Classification Baseline for Generalized Category Discovery

  title={A Simple Parametric Classification Baseline for Generalized Category Discovery},
  author={Xin Wen and Bingchen Zhao and Xiaojuan Qi},
Generalized category discovery (GCD) is a problem setting where the goal is to discover novel categories within an unlabelled dataset using the knowledge learned from a set of labelled samples. Recent works in GCD argue that a non-parametric classifier formed using semi-supervised k means can outperform strong baselines which use parametric classifiers as it can alleviate the over-fitting to seen categories in the labelled set. In this paper, we revisit the reason that makes previous parametric… 



Generalized Category Discovery

This paper establishes strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task, and introduces a simple yet effective semi-supervised k-means method to cluster the unlabelled data into seen and unseen classes automatically, substantially outperforming the baselines.

XCon: Learning with Experts for Fine-grained Category Discovery

A novel method called Expert-Contrastive Learning (XCon) is presented to help the model to mine useful information from the images by partitioning the dataset into sub-datasets using k -means clustering and then performing contrastive learning on each of the sub- datasets to learn fine-grained discriminative features.

A Unified Objective for Novel Class Discovery

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.

Learning to Discover Novel Visual Categories via Deep Transfer Clustering

The problem of discovering novel object categories in an image collection is considered, and Deep Embedded Clustering is extended to a transfer learning setting, and the algorithm is improved by introducing a representation bottleneck, temporal ensembling, and consistency.

Neighborhood Contrastive Learning for Novel Class Discovery

This paper addresses Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes, and builds a new framework, named Neighborhood Contrastive Learning (NCL), to learn discriminative representations that are important to clustering performance.

Semi-Supervised Learning with Scarce Annotations

This work considers the problem of SSL multi-class classification with very few labelled instances, and introduces a new algorithm for SSL that can exploit well a pre-trained representation of the data without making use of any label.

AutoNovel: Automatically Discovering and Learning Novel Visual Categories

This work suggests that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data.

Open-World Semi-Supervised Learning

Despite solving the harder task ORCA outperforms semisupervised methods on seen classes, as well as novel class discovery methods on novel classes, achieving 7% and 151% improvements on seen and novel classes in the ImageNet dataset.

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

Despite the simplicity of the approach, PAWS outperforms other semi-supervised methods across architectures, setting a new state-of-the-art for a ResNet-50 on ImageNet trained with either 10% or 1% of the labels, reaching 75% and 66.5% top-1 respectively.

Self-labelling via simultaneous clustering and representation learning

The proposed novel and principled learning formulation is able to self-label visual data so as to train highly competitive image representations without manual labels and yields the first self-supervised AlexNet that outperforms the supervised Pascal VOC detection baseline.