---
title: Galar Dataset for VCE Machine Learning
url: https://www.emergentmind.com/topics/galar-dataset
type: topic
---

# Galar Dataset for VCE Machine Learning

Searching arXiv for the original Galar dataset paper and recent papers that use it.
Searching arXiv: `Galar video capsule endoscopy dataset`
Galar is a public video capsule endoscopy (VCE) dataset for machine learning on gastrointestinal imaging. In downstream literature, it is described as a large multi-label VCE resource with **3,513,539 labeled images from 80 patient VCE studies**, containing annotated anatomical and pathological findings, and supporting tasks ranging from binary anomaly detection to joint gastrointestinal localization, temporal multi-label classification, and study-level systems evaluation [2504.06039, 2507.23479, 2604.25464].

## 1. Scope, modality, and dataset role

Galar belongs to the VCE domain, in which a swallowable capsule camera acquires long image sequences through the gastrointestinal tract. Later task papers treat it not as a small curated image collection but as a dataset of **whole studies**, which makes it suitable for both frame-level classification and temporally structured inference. One study describes it as “the only publicly available VCE dataset” with labels for both **different GI organs** and **anomalies**, while another describes it as the **currently largest available VCE dataset** and emphasizes that it contains **80 complete studies** [2507.23479, 2604.25464].

The dataset is used across several distinct problem formulations. In anomaly-detection work, Galar is treated as a source of **small-intestine capsule frames** with pathology annotations. In multi-task work, it becomes a joint benchmark for **anatomical localization** and **binary anomaly detection**. In competition-oriented temporal classification, it is the basis for **17-label multi-label temporal prediction** with event-level evaluation. This breadth of usage indicates that Galar is not merely an image archive; it functions as a general-purpose supervised benchmark for VCE learning pipelines [2504.06039, 2603.17879, 2605.22209].

The source images are also reported under multiple operational resolutions. One anomaly-detection study states that Galar videos were originally recorded with varying resolutions from **\(336 \times 336\)** to **\(576 \times 576\)** pixels, with training images resized to **\(224 \times 224\)** and test-time evaluation performed on original image sizes [2504.06039].

## 2. Annotation structure and task-specific label projections

Published uses of Galar make clear that the dataset is fundamentally **multi-label**, but that downstream works frequently project it into task-specific label spaces. In the competition-oriented setting, the frame-level label space comprises **17 classes**: **8 anatomical regions** and **9 pathological findings**. The anatomy classes are **mouth, esophagus, z-line, stomach, pylorus, small intestine, ileocecal valve, colon**; the pathology classes are **active bleeding, angiectasia, blood, erosion, erythema, hematin, lymphangioectasis, polyp, ulcer** [2603.17879, 2605.22209].

Other works collapse this richer structure. For pooled anomaly detection in the small intestine, one paper relabels Galar into a binary problem with **Normal Clean Mucosa** as the negative class and **Polyp, Blood, Active Bleeding, Angiectasia, Erosion, Erythema, Ulcer** merged into the positive class [2504.06039]. A multi-task study uses a different projection: **five sequential GI organ classes**—**Mouth, Esophagus, Stomach, Small Intestine, Colon**—plus a binary anomaly label formed by combining all pathologies into a single positive class [2507.23479].

A separate systems paper identifies an additional annotation layer: a **technical label group** for **six studies**, centered on image quality. In that subset, selected frames are labeled as **good view**, **reduced view**, or **no view**, with visibility reduction attributed to **bubbles** or **dirt**. The definitions are explicit: **good view** means visibility reduction of **less than 50%**; **reduced view** means **between 50% and 95%**; **no view** means **over 95%** [2604.25464].

| Task projection | Labels used | Notes |
|---|---|---|
| Multi-label temporal classification | 17 classes: 8 anatomy + 9 pathology | Frame-level prediction with temporal event generation |
| Binary anomaly detection | Normal Clean Mucosa vs pooled pathology class | Small intestine only |
| Multi-task localization + anomaly | 5 organ classes + binary anomaly | All pathologies collapsed into one anomaly class |
| Technical quality analysis | good view / reduced view / no view; bubbles or dirt | Available for 6 studies |

This multiplicity of label projections is a defining property of Galar’s published use. It suggests that the underlying annotations are rich enough to support distinct supervision regimes, but also that results from different papers are not directly comparable unless the relabeling protocol is specified.

## 3. Splits, partitions, and evaluation protocols

Galar’s published train/validation/test usage is notably protocol-dependent. For pooled anomaly detection, the **test set** preserves **patient IDs \(61\)–\(80\)** from the original publication, while **patient IDs \(1\)–\(60\)** are split **80:20 (train:val)** on a **patient-wise** basis [2504.06039]. This protocol is intended to avoid leakage across adjacent frames from the same study.

A multi-task study retains the same high-level structure—**IDs \(61\)–\(80\)** as untouched test studies and **IDs \(1\)–\(60\)** as a development pool—but after preprocessing and downsampling it performs a **70:30** training/validation split on the development data. That paper states that the data were “randomly shuffled and split,” but does not specify whether train/validation separation was again patient-wise at that stage [2507.23479].

Competition-oriented temporal classification papers describe a different partitioning vocabulary. One reports a **training partition of 60 videos** with approximately **494,696 sampled frames**, a **validation partition of 10 videos** with approximately **80,399 frames**, and a held-out **RARE-VISION test set** comprising **3 NaviCam examinations** with **161,025 frames** in total [2603.17879]. Another temporal paper reports results on the same three videos—`ukdd_navi_00051`, `ukdd_navi_00068`, and `ukdd_navi_00076`—but does not provide a full dataset inventory beyond that benchmark framing [2605.22209].

These published protocols indicate that Galar benchmarking is not organized around a single universally adopted split. A plausible implication is that methodological comparisons require careful attention to the exact task projection, patient partitioning rule, and evaluation backend.

## 4. Benchmark tasks and reported results

Reported Galar benchmarks span binary classification, multi-task frame classification, and temporal event detection. Because the label spaces and metrics differ, these results describe different operating regimes rather than a single leaderboard.

| Task/setup | Reported best result | Source |
|---|---|---|
| Binary anomaly detection over pooled small-intestine classes | **AUC 76.98%** with SVM-based ensemble | [2504.06039] |
| Joint 5-organ localization + binary anomaly detection | **93.63%** localization accuracy and **87.48%** anomaly-detection accuracy, using **1M parameters** | [2507.23479] |
| Multi-label temporal classification on held-out RARE-VISION test set | **temporal mAP@0.5 = 0.2456**, **mAP@0.95 = 0.2353** | [2603.17879] |
| Post-competition temporal model (“GALAR-TemporalNet v2”) | **mAP@0.5 = 0.3409**, **mAP@0.95 = 0.3333** | [2605.22209] |

In the pooled anomaly-detection formulation, the strongest ranking metric comes from an **SVM ensemble** combining at least classifier and autoencoder signals, with **AUC 76.98**, **recall 80.58**, **accuracy 73.83**, **F1 27.44**, **MCC 28.29**, and **precision 16.53**. The plain image classifier is stronger on **accuracy, F1, MCC, and precision**, with **accuracy 87.28**, **F1 37.01**, **MCC 34.45**, and **precision 26.59**, while the standalone autoencoder performs poorly on Galar with **AUC 45.83** and **MCC -4.15** [2504.06039].

In the multi-task formulation, the shared MobileNetV3-Small model produces large gains for localization when coupled with sequence constraints. The best reported configuration, **MT DWA Focal + HMM**, reaches **93.63** accuracy, **92.41** F1, **90.40** precision, and **94.94** recall on localization. For anomaly detection, the best reported F1 is **54.38** under **MT DWA**, while the headline abstract value for anomaly-detection accuracy is **87.48%** [2507.23479].

Competition papers emphasize that rare pathological classes remain difficult even with strong backbones and temporal post-processing. One validation table reports high AP for common anatomical classes such as **stomach (0.849)**, **small intestine (0.969)**, and **colon (0.996)**, but near-zero AP for ultra-rare findings such as **active bleeding (0.002)**, **erythema (0.001)**, **hematin (0.001)**, and **ulcer (0.012)** [2603.17879]. Another anomaly-detection study similarly notes that **blood**, **active bleeding**, and **angiectasias** are detected relatively well, whereas **polyps** and **erosions** are mostly not correctly classified [2504.06039].

## 5. Temporal structure, visibility labels, and systems-level studies

A distinctive line of work uses Galar not only for recognition but also for **compression**, **visibility estimation**, and **energy-aware control** in capsule systems. In that setting, the dataset’s full-study organization and technical annotations become central.

One systems paper restricts Galar to the **small intestine**, then applies offline post-processing to estimate bubble statistics because the dataset does **not contain labels for the number, positions, or dimensions of bubbles**. On this small-intestine-constrained subset, it reports **1,375,918 frames**, of which **869,147 (63.17%)** contain bubbles, with **15,742,534** detected bubbles in total. The reported mean bubble coverage is **14.86%**, the median is **7.21%**, the mean bubble radius is **24.15 px**, and the median radius is **23 px** [2604.25464].

The same study uses Galar to validate a compression-based proxy for diagnostic visibility. It reports a compression result of **CR = 5.748**—equivalent to **82.6% compression**—at **PSNR = 40.30 dB**, and argues that compression ratio is inversely related to bubble coverage. In its operational interpretation, frames with **CR < 4** are predominantly obscured by bubbles and medically irrelevant [2604.25464].

Because Galar contains **80 complete studies**, it also supports study-level simulation. Using the **small intestine section of all 80 studies** and assuming a constant baseline of **2 fps**, the same paper reports a mean whole-system energy reduction of **20.58%** from compression alone, and an average reduction of **23.12%** when compression is combined with bubble-aware frame-rate adaptation. The greatest observed reduction is **40%**, reported for **study 59** at **CR Threshold = 3.6** and **reduced fps = 0.67**. The conclusion restates this as an **additional reduction of 10.99%**, without missing any pathologies [2604.25464].

These results show that Galar’s value extends beyond recognition benchmarks. Its longitudinal structure and technical labels permit system-level studies in which temporal continuity, visibility degradation, and resource constraints are evaluated jointly.

## 6. Class imbalance, reproducibility issues, and interpretive caveats

A recurring feature across all published uses is **extreme class imbalance**. One competition paper states that pathological findings constitute **less than 0.1% of all annotated frames**, and reports rare-class supports in the training partition as low as **3** positive frames for **z-line**, **73** for **mouth**, and **150** for **active bleeding**, with positive-to-negative ratios exceeding **1:3,000** for some labels [2603.17879]. A later temporal paper likewise emphasizes extreme imbalance, long-range temporal dependencies, and pathology–anatomy entanglement as the three core challenges of the benchmark [2605.22209].

Several methodological caveats also recur. The anomaly-detection paper notes that Galar “only comprises labeled frames,” so unlabeled-data advantages available in other VCE datasets cannot be exploited; this is used to explain why the autoencoder branch contributes less on Galar than on Kvasir-Capsule [2504.06039]. The compression study points out that Galar provides only **post-processed, demosaicked RGB images**, not native **RAW Bayer** sensor data, so Bayer inputs must be reconstructed by **RGGB** subsampling before compression experiments [2604.25464].

Dataset characterization is also fragmented across the literature. Some papers emphasize the **80 patient studies** and the **3,513,539 labeled images** [2504.06039], others foreground **challenge partitions** such as **60 training videos**, **10 validation videos**, and a **3-exam held-out test set** [2603.17879], and method-centric temporal papers do not supply a full standalone dataset card [2605.22209]. This suggests that reproducing published Galar results generally requires reading task-specific benchmark papers rather than relying on a single harmonized specification.

Taken together, these caveats position Galar as a powerful but nontrivial benchmark. It is unusually rich in supervision for VCE, especially when anatomy, pathology, temporal continuity, and image quality are considered together, but its effective use depends on explicit relabeling choices, careful split management, and methods that can tolerate severe long-tail imbalance and strong temporal correlation.

Source: https://www.emergentmind.com/topics/galar-dataset