SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection

TL;DR

SimLTD introduces a simple, scalable method for long-tailed object detection that leverages unlabeled images to improve performance without relying on extensive labeled datasets, achieving state-of-the-art results.

Contribution

The paper presents a straightforward framework for long-tailed detection that uses unlabeled images, avoiding complex meta-learning or distillation techniques.

Findings

Achieves new record results on LVIS v1 benchmark

Effective in both supervised and semi-supervised settings

Utilizes unlabeled images without additional annotations

Abstract

While modern visual recognition systems have made significant advancements, many continue to struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object classes follow a natural long-tailed distribution. Existing methods for long-tailed detection resort to external ImageNet labels to augment the low-shot training instances. However, such dependency on a large labeled database has limited utility in practical scenarios. We propose a versatile and scalable approach to leverage optional unlabeled images, which are easy to collect without the burden of human annotations. Our SimLTD framework is straightforward and intuitive, and consists of three simple steps: (1) pre-training on abundant head classes; (2) transfer learning on scarce tail classes; and (3) fine-tuning on a sampled set of both head and tail classes. Our approach can be viewed as an improved head-to-tail model transfer paradigm without the added complexities of meta-learning or knowledge distillation, as was required in past research. By harnessing supplementary unlabeled images, without extra image labels, SimLTD establishes new record results on the challenging LVIS v1 benchmark across both supervised and semi-supervised settings.