- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
GRef combines a regional graph encoder with relevance–diversity reranking to select query-specific normal references for generalizable anomaly detection. However, I think the biggest problem with this paper is the setting and motivation: setting the budget based on the number of images makes no sense, and the observation in Fig. 1 does not justify the use of a graph. The experimental gains are very small, and there is no variance, so this method is not well supported.
Critical strengths
The comparisons across four fixed detectors provide useful controlled evidence that GRef improves reference selection under the prescribed reference budget.
Critical weaknesses
- Insufficient justification of the setting. Why must exactly K reference images be selected from a pool of normal samples? Limited compute does not by itself imply that the budget should be a fixed number of images, so this setting seems to have been invented to accommodate the authors’ own retrieval pipeline.
- Gap between the observation and the proposed solution. Fig. 1 only shows that the quality of the selected reference images affects the results, but it does not prove that the bottleneck is redundancy or spatial structure. Existing methods already perform feature matching against the query, yet the authors do not clearly state what problem remains or why a graph can solve it.
- Insufficient validation. The encoder learns dropout consistency and similarity preservation, while MMR penalizes embedding similarity. Neither has been shown to measure how useful a reference image is for detection or whether it can provide complementary evidence.
- The gains are very small. With UniVAD, the strongest detector tested, GRef is only 0.09 points higher than CPR. After training, ResAD++ improves by only 0.17 points, while RegAD drops by 0.34 points. No variance across multiple runs is reported, so it is unclear whether these differences are reliable.
Questions for authors
See weaknesses.
5 comments
Response to Reviewer Lqe3 (Part II)
Response to Weakness 3 (reference utility and redundancy proxies)
Appendix E.1 reports the comparison of Top-K and MMR in Table 4 and the ablations of the two training losses in Table 5.
A reference can match the query well and still repeat a normal pattern covered by a selected reference. With the graph encoder fixed and eight references per query, penalizing similarity to already selected references improved all three detection and localization metrics.
Q1: How do the two training objectives support reference selection?
GRef encodes regional appearance, spatial adjacency and containment across scales. The similarity-preservation loss encourages the embeddings to retain similarities in the original regional features. Dropout consistency encourages the same image to have similar embeddings under different feature masks. We removed each loss in turn and retrained the encoder with the reference pool, budget, MMR rule and ResAD++ weights fixed.
| Training objective | Image-level AUROC (%) | Pixel-level AUROC (%) | AUPRO (%) |
|---|---|---|---|
| Without dropout consistency | 87.55 ± 0.05 | 92.95 ± 0.01 | 84.90 ± 0.05 |
| Without similarity preservation | 87.40 ± 0.05 | 92.90 ± 0.02 | 84.75 ± 0.07 |
| Both loss terms | 87.94 ± 0.00 | 93.08 ± 0.01 | 85.34 ± 0.03 |
We averaged the six datasets equally within each seed and report the mean ± sample standard deviation over three seeds. Values shown as ±0.00 are rounded.
Removing dropout consistency or similarity preservation lowered mean image-level AUROC by 0.39 and 0.54 percentage points, respectively. References selected with both losses gave the highest scores on all three metrics.
Q2: Why use embedding similarity as a proxy for reference redundancy?
A close match to even one selected reference suggests that the candidate may repeat a regional pattern already covered. We kept the encoder, candidates, detector weights and reference count fixed. Top-K (λ = 1) ranks candidates by query relevance. MMR (λ = 0.7) also penalizes each candidate’s highest embedding similarity to a selected reference.
| Metric (%) | Relevance-only Top-K (λ = 1) | MMR (λ = 0.7) | Mean paired gain (percentage points) |
|---|---|---|---|
| Image-level AUROC | 87.52 ± 0.04 | 87.94 ± 0.00 | +0.420 |
| Pixel-level AUROC | 92.91 ± 0.02 | 93.08 ± 0.01 | +0.173 |
| AUPRO | 85.00 ± 0.05 | 85.34 ± 0.03 | +0.338 |
Averaged over three paired seeds, MMR gained 0.420, 0.173 and 0.338 percentage points over Top-K in image-level AUROC, pixel-level AUROC and AUPRO, respectively. At the same eight-reference budget, similarity to the selected set added useful information beyond query relevance and led to better detection and localization.
Response to Reviewer Lqe3 (Part III)
Additional results on graph encoding and reference selection
Table 4 compares full GRef with raw regional features plus MMR, a graph-free MLP plus MMR, and the graph encoder with Top-K.
Full GRef reached 87.94% mean image-level AUROC across six datasets. It gained 1.74, 1.67 and 0.42 percentage points over raw regional features with MMR, a graph-free MLP with MMR, and the graph encoder with Top-K, respectively. Keeping both graph message passing and MMR gave better detection than each of the three alternatives we tested. Within each seed, all configurations shared the same ResAD++ weights, normal pool and test set, and selected 8 references from 32 candidates.
| Selection rule | Representation | Image-level AUROC (%) | Pixel-level AUROC (%) | AUPRO (%) |
|---|---|---|---|---|
| Top-K | Global pooling | 85.55 ± 0.05 | 91.80 ± 0.02 | 83.82 ± 0.06 |
| Raw regional features | 85.95 ± 0.05 | 91.90 ± 0.02 | 84.03 ± 0.06 | |
| Graph-free MLP | 86.02 ± 0.05 | 91.99 ± 0.02 | 84.17 ± 0.05 | |
| Graph encoder | 87.52 ± 0.04 | 92.91 ± 0.02 | 85.00 ± 0.05 | |
| MMR | Global pooling | 85.80 ± 0.03 | 91.84 ± 0.02 | 83.88 ± 0.05 |
| Raw regional features | 86.20 ± 0.03 | 91.96 ± 0.02 | 84.14 ± 0.04 | |
| Graph-free MLP | 86.27 ± 0.03 | 92.09 ± 0.02 | 84.38 ± 0.04 | |
| Graph encoder (full GRef) | 87.94 ± 0.00 | 93.08 ± 0.01 | 85.34 ± 0.03 |
For each seed, we averaged the six datasets with equal weight. The table reports the mean ± sample standard deviation across three seeds. Values shown as ±0.00 are due to rounding.
Q1: How does GRef compare with raw regional features and MMR?
With the same regional inputs and MMR rule, mean image-level AUROC was 86.20% for raw features, 86.27% for the graph-free MLP and 87.94% for the graph encoder. Learning regional features alone added 0.07 points, while the graph encoder gained 1.74 points over raw features. The graph encoder was the strongest of these three regional representations under the same MMR rule.
Q2: What does graph encoding add over a graph-free MLP with MMR fixed?
The MLP and graph encoder used the same regional inputs, pretraining objectives and training budget. Modeling spatial adjacency and hierarchical containment gained 1.67 percentage points in mean image-level AUROC with MMR and 1.50 points with Top-K. The graph encoder outperformed the MLP under both selection rules.
Q3: What does MMR add over Top-K with the graph encoder fixed?
With the same graph encoder, MMR (λ = 0.7) gained 0.42 percentage points in image-level AUROC over relevance-only Top-K (λ = 1). Pixel-level AUROC and AUPRO also rose by about 0.17 and 0.34 points, respectively. Across all eight configurations in the table, full GRef, combining the graph encoder and MMR, ranked first in image-level AUROC, pixel-level AUROC and AUPRO.
Response to Reviewer Lqe3 (Part I)
Dear Reviewer Lqe3,
Thank you for your feedback on the four fixed detectors and for your patience with our delayed reply. We took the extra time to test a simpler selector with more references and to benchmark GRef against the full feature bank and its coreset.
Response to Weakness 1 (reference budget in deployment)
Section 1 gives the example of a ceramic bottle line changing designs. As production ramps up, the line can quickly accumulate many images of normal bottles. A reference-based detector can use these images to inspect the new design without retraining at each changeover.
Even with cached features, matching each bottle against regional features from the entire pool requires more computation and data access as the pool grows. Many normal images also show similar patterns on the bottle or similar viewing angles. For each query, GRef selects a few references that are relevant in appearance and have little redundancy, then passes them to the detector for fine-grained matching.
K is the number of references passed to the detector for each query. It can vary with the product and the latency budget. We study the regime where K is much smaller than the normal pool. Fixing K in the experiments controls the detector’s per-query reference workload and gives all selectors the same budget. Prior few-shot evaluations of RegAD, ResAD++, InCTRL, SPADE, PaDiM, PatchCore, and D²4FAD have reused a randomly sampled set of K normal references across queries, which motivates us to ask whether choosing the K references for each query can improve detection.
Response to Weakness 2 (motivation for graph encoding and MMR)
In Figure 1, the same detector uses four references from a pool of eight normal images. Changing only the selection strategy changes image-level AUROC on the test set. Existing query-adaptive matching methods can find features in the supplied references that correspond to regions in the query. When the normal pool is much larger than the reference budget, the selection of images determines which normal patterns are available for this matching step.
Graph encoding estimates the relevance of each reference to the query. Product appearance and texture can change from one product to the next, while spatial adjacency and cross-scale containment have the same definition across products. GRef encodes regional appearance together with these relationships, allowing retrieval to distinguish candidates with similar local textures but different spatial arrangements. Related approaches to learning transferable representations include the multiscale relational modeling in UniOD [1] and the encoding of structure and context in REFI-GAD [2].
MMR reduces redundancy in the selected set. Several nearly identical images can rank highly by relevance. MMR penalizes candidates that resemble an already selected reference, leaving room for other normal patterns. With the graph encoder fixed, MMR raised mean image-level AUROC from 87.52% to 87.94%, a gain of 0.42 percentage points over relevance-only Top-K. With the same eight reference slots, accounting for overlap among references gave the detector a better set than ranking by relevance alone.
[1] Dazhi Fu and Jicong Fan. UniOD: A Universal Model for Outlier Detection across Diverse Domains. ICLR 2026.
[2] Yujing Liu et al. Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach. ICML 2026.