- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2(+1)
- Presentation
- 2
- Soundness
- 3(+1)
Read review
Paper summary
This paper investigates the problem of multi-label image hashing retrieval under instance-dependent label noise. The authors categorize the impact of label noise on pairwise supervision into two types: false attraction caused by erroneously added labels, and false repulsion caused by missing ground-truth labels, and propose the IDNRH framework.
The method consists of two main modules: Sample-to-Label Truncation (SLT) partitions samples via a GMM based on classification losses, reconstructs label confidence by incorporating dual-view neighbor information, and truncates low-confidence positive labels in suspicious samples; Repulsion-Filtered Soft Contrastive Learning (RFSCL) leverages the Jaccard similarity of the truncated labels to modulate the attraction strength, and exploits shared neighbor relationships to mitigate potential false repulsion. The model employs a frozen CLIP ViT-B/32 backbone and jointly optimizes a classification loss, a pairwise loss, and a quantization loss to train the hash head. Experiments are conducted on three synthetic noisy datasets and one real-world Web noisy label dataset.
Critical strengths
-
The paper addresses a practically relevant problem with a clear design rationale: label additions and omissions cause false attraction and repulsion, motivating label truncation and repulsion filtering.
-
IDNRH reports competitive results across datasets, noise settings, and code lengths, including a backbone-controlled CLIP comparison and evaluation on real Web-label noise. These results suggest practical value, subject to the evaluation concerns below.
Critical weaknesses
-
Novelty relative to closely related work is unclear. Robust Contrastive Cross-modal Hashing with Noisy Labels (ACM MM 2024) already uses a loss-based two-component GMM for noisy-label hashing; Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval (AAAI 2026) has already constructed soft contrastive learning based on label overlap, performing repulsion and attraction. This paper likewise uses a GMM to distinguish noisy samples and constructs soft contrastive learning based on label overlap, with and , but neither cites nor compares against these works, leaving its incremental contribution unclear.
-
Table 3 lacks a clear comparison protocol and contains an apparent metric inconsistency. It is unclear whether NACR and SLT share the same training samples, noisy labels, and mixed IDN setting, or how the single-modality adaptation was performed. Under matched data and aggregate-count metrics, Appendix B.3 implies Yet the inferred ratios differ: 2.365 versus 1.078 on NUS-WIDE, and 1.586 versus 3.110 on MS COCO. These discrepancies require clarification before Table 3 can reliably support SLT’s advantage.
-
The evaluation provides limited support for fine-grained ranking and noise robustness. The relevance definition and mAP cutoff are unspecified. If relevance means sharing at least one clean label, binary metrics cannot distinguish degrees of semantic overlap. Moreover, actual addition/deletion rates and proportions of corrupted samples are unreported. Algorithm 2’s nominal noise parameter controls CLIP-score percentiles rather than actual corruption rates, which are further affected by label restoration. These omissions obscure both ranking quality and corruption severity.
Questions for authors
-
What are the specific contributions beyond NRCH and SCBCH? Can adapted baseline or component-replacement comparisons be provided under matched backbone and supervision settings?
-
Do NACR and SLT use identical data and noise settings in Table 3? Please clarify the protocol and provide raw counts such as , , , and to resolve the metric discrepancy. For each synthetic setting, report the proportions of clean, addition-only, deletion-only, and mixed-error samples, plus post-restoration addition/deletion rates. Can separate-noise experiments and a clean-label reference also be provided?
-
Can nDCG@K be reported over all queries using clean-label-based graded relevance and an explicit gain function?
-
How much does training improve over pretrained CLIP? Please include frozen CLIP continuous-feature retrieval and a same-length hashing baseline using a fixed projection without labels or task-specific training, to separate the benefits of pretraining, hash learning, and noise handling.
9 comments
Response to Reviewer XpTN (Q1/W1 2/2)
3. Backbone-controlled comparison with adapted NRCH and SCBCH.
To further validate the methodological advantages under matched backbone and supervision settings, we extend the backbone-controlled comparison by including NRCH and SCBCH.
Since both are originally cross-modal hashing methods, we adapt them to image-only retrieval while preserving their respective training mechanisms:
- We use a frozen CLIP ViT-B/32 to replace the original fixed image features and set the input dimension to 512.
- We retain the two independent hash branches, but feed the same image's CLIP feature to the branch originally used for text. We preserve the original losses, NRCH's DNS, SCBCH's reliability weighting, and their respective optimizers.
- During retrieval, both queries and gallery images are encoded using the main image branch.
We follow the same backbone-controlled experimental protocol, using matched training settings in terms of data splits, noisy-label annotations, backbone, 128-bit hash codes, noise levels (20%, 40%, and 60%), and evaluation protocol, while retaining each method's native training strategy.
As shown in Table 1, IDNRH achieves the best mAP across all nine dataset-noise settings. These results demonstrate that the advantage of IDNRH is not merely attributable to the backbone or supervision setting, but also comes from its specifically designed noise-robust learning mechanisms.
Table 1. Backbone-controlled comparison with adapted NRCH and SCBCH (mAP, %).
| Method | Reference | Dataset | 20% | 40% | 60% |
|---|---|---|---|---|---|
| Bi-half | AAAI'21 | NUS-WIDE | 66.6 | 66.6 | 66.6 |
| MS COCO | 54.5 | 54.5 | 54.5 | ||
| MIRFLICKR-25K | 74.1 | 74.1 | |||
| SDC | BMVC'23 | NUS-WIDE | 62.7 | 62.7 | 62.7 |
| MS COCO | 58.1 | 58.1 | 58.1 | ||
| MIRFLICKR-25K | 72.3 | 72.3 | 72.3 | ||
| HHCH | TIP'24 | NUS-WIDE | 62.2 | 62.2 | 62.2 |
| MS COCO | 59.0 | 59.0 | 59.0 | ||
| MIRFLICKR-25K | 73.9 | 73.9 | 73.9 | ||
| DIOR | TKDE'24 | NUS-WIDE | 73.5 | 71.2 | 65.8 |
| MS COCO | 68.9 | 63.9 | 51.7 | ||
| MIRFLICKR-25K | 75.8 | 72.4 | 71.4 | ||
| SEGA | NeurIPS'25 | NUS-WIDE | 76.2 | 72.3 | 65.7 |
| MS COCO | 64.8 | ||||
| MIRFLICKR-25K | 83.8 | 80.0 | 73.0 | ||
| NDBE | TMM'26 | NUS-WIDE | 69.5 | 65.6 | 56.9 |
| MS COCO | 62.4 | 56.2 | 52.3 | ||
| MIRFLICKR-25K | 77.5 | 73.4 | 67.6 | ||
| NRCH | ACM MM'24 | NUS-WIDE | 75.7 | 73.5 | |
| MS COCO | 65.2 | 59.5 | |||
| MIRFLICKR-25K | 85.2 | 80.0 | 72.5 | ||
| SCBCH | AAAI'26 | NUS-WIDE | 65.3 | ||
| MS COCO | 71.3 | 55.9 | |||
| MIRFLICKR-25K | 71.6 | ||||
| IDNRH | Ours | NUS-WIDE | 77.9 | 75.4 | 69.8 |
| MS COCO | 71.3 | 67.8 | 62.8 | ||
| MIRFLICKR-25K | 87.1 | 82.6 | 75.1 |
Thank you for the response. Your answers effectively addressed my key concerns regarding the paper's core arguments and novelty, and the additional comparison results with closely related methods are highly convincing. Based on this, I am inclined to give a positive score. However, I still have a few remaining concerns: providing more diverse evaluation metrics for comparison in the multi-label setting would significantly strengthen my confidence in the conclusions. Additionally, access to detailed training logs would further solidify my final rating.
Response to Reviewer XpTN (Q1/W1 1/2)
We thank the reviewer for the constructive comments and positive assessment. We respond to each concern point by point below.
Q1/W1: What are the specific contributions beyond NRCH and SCBCH? Can adapted baseline or component-replacement comparisons be provided under matched backbone and supervision settings?
We appreciate the reviewer for highlighting these closely related works. We will cite NRCH and SCBCH in the revision.While GMM-based sample partitioning and soft contrastive learning are established techniques, the novelty of IDNRH lies in its targeted treatment of two distinct pairwise supervision errors induced by multi-label IDN, rather than the individual use of these techniques.
1. Differences from NRCH (ACM MM 2024).
NRCH employs GMM-based dynamic noise separation to select reliable training samples. However, its sample-level partitioning does not explicitly distinguish clean and corrupted labels within a partially corrupted instance.
In contrast, IDNRH introduces a finer-grained sample-to-label strategy. Specifically, we apply exponential moving average (EMA) smoothing to per-sample BCE losses before GMM estimation, and use the clean-component posterior probability to guide multi-view neighbor-based label confidence reconstruction. Subsequently, class-specific adaptive thresholds selectively remove unreliable positive labels from potentially noisy samples while preserving their remaining useful supervision.
Thus, unlike sample-level selection in NRCH, IDNRH transforms coarse sample reliability into fine-grained label-level correction, which is particularly important when correct and incorrect labels coexist within the same multi-label instance.
2. Differences from SCBCH (AAAI 2026).
Although SCBCH also employs bidirectional soft contrastive learning, its attraction and repulsion terms differ from those of our RFSCL. We clarify this distinction by comparing their respective formulations.
Its attraction term (Eq. 5) is formulated as:
\frac{1}{n^2} \sum_{i=1}^{n}\sum_{j\ne i} \exp(\xi-S_{ij})M_{ij} -\frac{1}{n}\sum_{i=1}^{n}S_{ii}.$$ where $M_{ij}=\mathbb I(R_{ij}>0)$ is a binary positive-pair mask. Therefore, although SCBCH includes partially overlapping samples as soft pairs, its label-based attraction weighting is binary rather than determined by the degree of label overlap. Its repulsion term (Eq. 7), on the other hand, employs continuous label similarity: $$\mathcal L_{\mathrm{rep}}^{\mathrm{SCBCH}} = \frac{1}{2n^2} \sum_{i=1}^{n}\sum_{j\ne i} \sum_{d=1}^{2} \exp\left( N_{ij}^{d}(1-R_{ij}) \right).$$ where $N_{ij}^{d}$ denotes the margin-adjusted feature similarity in each retrieval direction. Our RFSCL employs continuous label similarity in **both attraction and repulsion**: $$\mathcal L_{\mathrm{att}}^{\mathrm{IDNRH}} = \frac{1}{n^2} \sum_{i=1}^{n}\sum_{j=1}^{n} R_{ij}\exp(\xi-S_{ij}^{w}).$$ $$\mathcal L_{\mathrm{rep}}^{\mathrm{IDNRH}} = \frac{1}{n^2} \sum_{i=1}^{n}\sum_{j=1}^{n} (1-R_{ij})(1-\bar C_{ij}) \exp(S_{ij}^{w}).$$ Here, $S_{ij}^{w}$ denotes the feature similarity between two samples in the weak view, and $\bar C_{ij}$ denotes the normalized shared-neighbor similarity. This formulation introduces two important differences from SCBCH. **First, unlike the binary positive-pair mask in SCBCH, our attraction term directly uses continuous label similarity ($R_{ij}$) to determine attraction strength.** Consequently, samples with stronger semantic overlap receive stronger attraction, while those with weaker overlap receive correspondingly weaker attraction. This preserves fine-grained semantic relationships and helps mitigate false attraction caused by additive IDN. **Second, beyond using label similarity to regulate repulsion, we introduce shared-neighbor similarity ($\bar C_{ij}$) as complementary structural evidence**. Under subtractive IDN, genuine positive labels may be missing, resulting in underestimated label overlap and potentially incorrect repulsion between semantically related samples. High shared-neighbor similarity indicates potential semantic relevance even when observed label overlap is low. The factor $(1-\bar C_{ij})$ therefore selectively suppresses such potentially unreliable repulsion while retaining repulsion between samples with little neighborhood overlap.