# Interactive Multi-Class Tiny-Object Detection Source: [Interactive Multi-Class Tiny-Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:03:49.010Z Authors: Chunggi Lee, Seonwook Park, Heon Song, Jeongun Ryu, Sanghoon Kim, Haejoon Kim, S\\'ergio Pereira, Donggeun Yoo Published: 2022-03-29T06:27:29.000Z ## Abstract Annotating tens or hundreds of tiny objects in a given image is laborious yet crucial for a multitude of Computer Vision tasks. Such imagery typically contains objects from various categories, yet the multi-class interactive annotation setting for the detection task has thus far been unexplored. To address these needs, we propose a novel interactive annotation method for multiple instances of tiny objects from multiple classes, based on a few point-based user inputs. Our approach, C3Det, relates the full image context with annotator inputs in a local and global manner via late-fusion and feature-correlation, respectively. We perform experiments on the Tiny-DOTA and LCell datasets using both two-stage and one-stage object detection architectures to verify the efficacy of our approach. Our approach outperforms existing approaches in interactive annotation, achieving higher mAP with fewer clicks. Furthermore, we validate the annotation efficiency of our approach in a user study where it is shown to be 2.85x faster and yield only 0.36x task load (NASA-TLX, lower is better) compared to manual annotation. The code is available at https://github.com/ChungYi347/Interactive-Multi-Class-Tiny-Object-Detection. ## 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. - [Power Battery Detection on PBD5K Regular 1.0](): Power Battery Detection; PBD5K Regular 1.0; AN-MAE: 1.9377. - [Plate Counting and Localization on X-ray PBD (Tough)](): Plate Counting and Localization; X-ray PBD (Tough); AN-MAE: 3.7356. - [Power Battery Detection on PBD5K 1.0 (Tough)](): Power Battery Detection; PBD5K 1.0 (Tough); AN MAE: 7.4658. - [Power Battery Detection on PBD5K Average 1.0](): Power Battery Detection; PBD5K Average 1.0; AN MAE: 4.1834. - [Plate Counting and Localization on X-ray PBD (Difficult)](): Plate Counting and Localization; X-ray PBD (Difficult); AN-MAE: 2.265. - [Plate Counting and Localization on X-ray PBD (Regular)](): Plate Counting and Localization; X-ray PBD (Regular); AN-MAE: 3.1835. - [Power Battery Detection on PBD5K Difficult 1.0](): Power Battery Detection; PBD5K Difficult 1.0; AN-MAE: 2.8645. ## Original sources and implementation [Original paper]() [PDF]()