Skip to content
Preprint

AlbumentationsX: One Augmentation Pipeline for Images and Related Annotations

Aug 2026 · 1 citation · 4 references
Computer Science

TL;DR

AlbumentationsX keeps the transform list, probabilities, annotation settings, and random seed in one Compose object, and applies them to every supported part of the training example.

Abstract

Augmentation can corrupt a training example when an image and its annotations receive different random changes. A crop must use the same coordinates for the image, mask, boxes, keypoints, stereo views, video frames, or volume. Code paths that choose these values separately can silently misalign the data. AlbumentationsX keeps the transform list, probabilities, annotation settings, and random seed in one Compose object. Each call chooses random values once and applies them to every supported part of the training example. The library keeps each object's mask, box, and label together and lets projects add their own transforms. It can also save the pipeline definition, show what happened in one call, and run that call again. The examples place Compose after files have been decoded into arrays and before PyTorch groups examples into a batch. AlbumentationsX executes the declared transforms. Practitioners still decide whether a flip, crop, color change, or other operation preserves the correct label for their task.

View source

Similar papers

Book Open access Oct 2026

FollowMe: Automating Precise Image Annotation Across Various Environments

Precise image annotation is essential for training advanced computer vision models. However, making high-accuracy, pixel-level image annotation efficient is never easy: manual labeling is highly accurate but time-consuming, while automatic labeling that using state-of-the-art models is much faster but often yields unsa...

Sheng-Qing Xia, Jia-Xin Du, Chun-Yi Peng · 0 citations
Preprint Aug 2026

AQ3D: Adaptive Query Transformer for 3D Instance Segmentation

This work presents AQ3D, which is designed to handle scenes of various sizes during training and inference and sets a new state-of-the-art on validation and hidden test splits across the datasets ScanNetV2, ScanNet200, and ScanNet++V2 among decoder methods trained without additional data augmentation.

Keno Moenck, T. Schüppstuhl · 0 citations
Preprint Aug 2026

Frozen DINO Localizes Image Edits Without a Localizer

Localized image edits can change a photograph's meaning while leaving most of it authentic, so forensic analysis must identify where an edit occurred. We show that patch-level perturbation responses from frozen DINO encoders are themselves localization maps. Training-free Localization of AI-image Edits from patch-token...

Zane Kumar, Vishal Jain, Bernhard Kainz · 0 citations
Preprint Sep 2026

Data-Efficient Crosswalk Segmentation from Overhead CCTV via Confidence- and Geometry-Guided Pseudo-Labeling

Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoint and appearance shift when applied to elevated CCTV. We investigate a data-efficient target-domain pipeline using 241 manually annotated CCTV images and 5,926 unlabel...

Abdirashid A. Omar, Jonghyuk Park · 0 citations
Conference Aug 2026

MaskFlow: Attention-Guided Localized Editing for Rectified Flow Models

Text-guided image editing using rectified flow models such as Multimodal Diffusion Transformer (DiT) has demonstrated impressive generation quality. However, existing methods apply edits globally, inevitably modifying background regions unrelated to the intended semantic change. Our key observation is that the Text-to-...

Trong-Tai Dam Vu, Vinh-Tiep Nguyen · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.