Papers › Two-stage coarse-to-fine image anomaly segmentation and detection model
Two-stage coarse-to-fine image anomaly segmentation and detection model
Rizwan Ali Shah, Odilbek Urmonov, HyungWon Kim
Existing Convolutional Neural Network (CNN) based anomaly detection and segmentation approaches are overly sensitive or not sensitive enough to noise, resulting in anomaly patterns, partially detected in the testing stage. The previous methods may also differentiate normal and abnormal images, but they cannot identify the location of anomaly presented in test images with high accuracy. To address this issue, we propose a two-stage CNN model for coarse-to-fine anomaly segmentation and detection called (TASAD). In both stages of TASAD, we train our model on a mixture of normal and abnormal training samples. The abnormal images are obtained by insert- ing pseudo-anomaly patterns that are automatically generated from anomaly source images. We use a novel and sophisticated anomaly insertion technique to generate various anomalous samples. In the first stage, we design a coarse anomaly segmentation (CAS) model that takes a whole image as an input, while in the second stage, we train a fine anomaly segmentation (FAS) model on image patches. FAS model improves detection and segmenta- tion performance by refining anomaly patterns partially detected by CAS model. We train our framework on MVTec dataset and compare it with state-of-the-art (SOTA) methods. The proposed architecture leads to a com- pact model size – four times smaller than the SOTA method, while exhibiting better pixel-level accuracy. TASAD can also be applied to SOTAs to further improve their anomaly detection performance. Our experiments demon- strate that when applied to the latest SOTAs, TASAD improves the average precision (AP) performance of previ- ous methods by 6.2%. For reproducibility of the results, code is provided at https://github.com/RizwanAliQau/ tasad.git.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Anomaly Detection | MVTec AD | TASAD | Detection AUROC | 98.0 | #67 of 148 | Archive leaderboard | report |
| Anomaly Detection | MVTec AD | TASAD | FPS | 142 | #67 of 148 | Archive leaderboard | report |
| Anomaly Detection | MVTec AD | TASAD | Segmentation AP | 74.6 | #67 of 148 | Archive leaderboard | report |
| Anomaly Detection | MVTec AD | TASAD | Segmentation AUROC | 98.2 | #67 of 148 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections