Cluster Centers Provide Good First Labels for Object Detection

• Published in: Image Analysis and Processing – ICIAP 2022 pp. 404 - 413
• Main Authors: Burghouts, Gertjan J., Kruithof, Maarten, Huizinga, Wyke, Schutte, Klamer
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Clustering; Few labels; Label selection; Object detection
• ISBN: 3031064267; 9783031064265
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-031-06427-2_34

Learning object detection models with a few labels, is possible due to ingenious few-shot techniques, and due to clever selection of images to be labeled. Few-shot techniques work with as few as 1 to 10 randomized labels per object class. We are curious if performance of randomized label selection can be improved by selecting 1 to 10 labels per object class in a non-random manner. Several active learning techniques have been proposed to select object labels, but all started with a minimum of several tens of labels. We explore an effective and simple label selection strategy, for the case of 1 to 10 labels per object class. First, the full unlabeled dataset is clustered into N clusters, where N is the desired number of labels. Clustering is based on k-means on embedding vectors from a state-of-the-art pretrained image classification model (SimCLR v2). The image closest to the center is selected to be labeled. It is effective: on Pascal VOC we validate that it improves over randomized selection over 25%, with large improvements especially when having 1 label per object class. We have several benefits to report on this simple strategy: it is easy to implement, it is effective, and it is relevant in practice where one often starts with a dataset without any labels.