统一无监督与半监督图像分类，用邻近信息提升聚类和类别发现性能
Utilization of Neighbor Information for Image Classification with Different Levels of Supervision
- 利用邻近样本的正负反馈优化聚类与分类
- 在ImageNet-100等数据集上聚类准确率提升3%，类别发现提升5%
- 适合需要跨监督层级泛化能力的研究者
我们提出一种灵活方法，弥合半监督与无监督图像识别之间的差距，在广义类别发现（GCD）和图像聚类任务中均表现优异。现有方法通常仅针对单一任务：GCD依赖标签数据，而深度聚类方法无法有效利用标签。为此，我们设计了基于邻近信息的统一分类框架（UNIC），在无监督和半监督场景下均适用。通过引入精准的正负邻域采样与清洗策略，并结合双类型邻域计算的聚类损失对主干网络进行微调，显著提升聚类性能。进一步将该流程拓展至GCD任务，以标注图像作为真实邻域参考。实验表明，本方法在聚类任务上于ImageNet-100、ImageNet200上分别取得+3%准确率提升；在GCD任务中，于CUB、SCars、Aircraft上分别达到+5%、+2%、+4%的提升，整体达当前最优水平。
原文摘要 · Abstract (English)
We propose to bridge the gap between semi-supervised and unsupervised image recognition with a flexible method that performs well for both generalized category discovery (GCD) and image clustering. Despite the overlap in motivation between these tasks, the methods themselves are restricted to a single task -- GCD methods are reliant on the labeled portion of the data, and deep image clustering methods have no built-in way to leverage the labels efficiently. We connect the two regimes with an innovative approach that Utilizes Neighbor Information for Classification (UNIC) both in the unsupervised (clustering) and semisupervised (GCD) setting. State-of-the-art clustering methods already rely heavily on nearest neighbors. We improve on their results substantially in two parts, first with a sampling and cleaning strategy where we identify accurate positive and negative neighbors, and secondly by finetuning the backbone with clustering losses computed by sampling both types of neighbors. We then adapt this pipeline to GCD by utilizing the labelled images as ground truth neighbors. Our method yields state-of-the-art results for both clustering (+3% ImageNet-100, Imagenet200) and GCD (+0.8% ImageNet-100, +5% CUB, +2% SCars, +4% Aircraft).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。