# Semi-Supervised and Long-Tailed Object Detection with CascadeMatch

Source: [Semi-Supervised and Long-Tailed Object Detection with CascadeMatch](<https://www.sota2.com/research/paper/68fa6f6e1e209131cea4582b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:23:26.146Z

Authors: Yuhang Zang, Kaiyang Zhou, Chen Huang, Chen Change Loy

Published: 2023-05-24T07:09:25.000Z

## Abstract

This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detector called CascadeMatch. Our detector features a cascade network architecture, which has multi-stage detection heads with progressive confidence thresholds. To avoid manually tuning the thresholds, we design a new adaptive pseudo-label mining mechanism to automatically identify suitable values from data. To mitigate confirmation bias, where a model is negatively reinforced by incorrect pseudo-labels produced by itself, each detection head is trained by the ensemble pseudo-labels of all detection heads. Experiments on two long-tailed datasets, i.e., LVIS and COCO-LT, demonstrate that CascadeMatch surpasses existing state-of-the-art semi-supervised approaches -- across a wide range of detection architectures -- in handling long-tailed object detection. For instance, CascadeMatch outperforms Unbiased Teacher by 1.9 AP Fix on LVIS when using a ResNet50-based Cascade R-CNN structure, and by 1.7 AP Fix when using Sparse R-CNN with a Transformer encoder. We also show that CascadeMatch can even handle the challenging sparsely annotated object detection problem.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on LVIS v1.0 (val)](<https://www.sota2.com/research/sota/object-detection-on-lvis-v1-0-val.md>): Object Detection; LVIS v1.0 (val); APbbox: 32.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2305.14813>)

[PDF](<https://arxiv.org/pdf/2305.14813.pdf>)