In AI-TOD-v2, the missing annotation and location error problems are considerably alleviated, facilitating more reliable training and validation processes. Embedding NWD-RKA into DetectoRS, the detection performance achieves 4.3 AP points …

[Paper] AI-TOD is a dataset for tiny object detection in aerial images. [Dataset] Please download the xView trainig set and AI-TOD_wo_xview to construct the complete AI-TOD dataset! AI-TOD comes with 700,621 object instances for eight categories across 28,036 aerial images.

AI-TOD comes with 700,621 object instances for eight categories across 28,036 aerial images. Compared to existing object detection datasets in aerial images, the mean size of objects in AI-TOD is about 12.8 pixels, which is much smaller than others.

The current state-of-the-art on AI-TOD is DNTR. See a full comparison of 7 papers with code.

The Normalized Wasserstein Distance and the RanKing-based Assigning strategy (NWD-RKA) for tiny object detection. A comparison between AI-TOD and AI-TOD-v2.

Jan 16, 2024 · To mitigate these challenges, we propose a DeNoising Tiny Object Detector (DN-TOD), which incorporates a Class-aware Label Correction (CLC) scheme to address class shifts and a Trend-guided Learning Strategy (TLS) to handle bounding box noise.

Tod AI helps you discover clarity and insight through AI-enhanced conversation pathways. Available 24/7 on your schedule to simply think out loud, reflect, and gain clarity.

Offical dataset, code and visualization of detecting tiny objects in aerial images. - Chasel-Tsui/AI-TOD-v2

2999 open source 1-2-3-4 images plus a pre-trained AI-TOD model and API. Created by VOC.

Oct 15, 2023 · The AI-TOD (Aerial Images Tiny Object Detection) dataset is a treasure trove of aerial images specifically designed for detecting tiny objects. With 700,621 object instances across 28,036 images, this dataset provides unique challenges and opportunities for machine learning enthusiasts and researchers.