- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates whether adding small amounts of noise to images can help identify shortcut-related features in a trained vision model. The authors propose Noise-based Class-Conditional Sensitivity Pruning (NCSP), which measures how much each feature in the backbone’s representation changes when noise is added to the input. These sensitivity scores are calculated separately for each class, and the connections corresponding to the most sensitive features are set to zero in each row of the classification head. The backbone remains frozen, while the remaining classification-head weights are retrained using clean labeled data without requiring nuisance or group annotations. However, noise-sensitive features do not necessarily represent shortcuts, and the method is effective only when shortcut-related features are sufficiently distinguishable from stable semantic features. The method is evaluated on BAR, Waterbirds, MetaShift, and FB-CMNIST, showing substantial improvements over the original ERM baseline.
Critical strengths
- NCSP is computationally lightweight. It freezes the backbone and modifies the classification head after identifying the target feature dimensions.
- The paper does not claim that every noise-representative feature explains a shortcut.
- The evaluation includes multiple spurious-correlation benchmarks and reports both mean and worst-group performance. The experimental section also transparently indicates that head refitting and random pruning are competitive with each other. And the paper does not claim universal success.
Critical weaknesses
- NCSP has considerable overlap with EvA, DFR, and AFR.
- I am not sure about the exact definition of a shortcut used here. A shortcut can be a predictive feature based on how the dataset actually is, i.e., how samples of a particular class follow a certain distribution. A spurious feature, on the other hand, is not expected to remain reliable under the distribution shifts of interest. The authors explicitly define these “nuisance” attributes as noncausal to the target label. That gives them a task-dependent definition of what counts as a shortcut. However, NCSP itself does not establish which features are causally related to the label.
- The method measures noise sensitivity, but it remains unclear whether that measurement reliably identifies shortcut-related features rather than simply unstable semantic features.
Questions for authors
- What is the key methodological contribution of NCSP beyond EvA-E’s class-specific feature erasure and constrained head refitting?
- What evidence demonstrates that Gaussian-noise sensitivity is a more effective criterion for identifying shortcut-related features?
- The method assumes that shortcut-related coordinates are more sensitive to Gaussian noise than semantic features. Please clarify.
- How can this assumption be independently verified on a new dataset without prior knowledge of the shortcut or access to shortcut labels?
- How does NCSP distinguish genuinely useful semantic features from harmful shortcuts when both may be sensitive to Gaussian noise?
- Which exact ImageNet-pretrained ResNet-18 checkpoint and training recipe were used? Were the same pretrained weights and initialization protocols used by the competing methods? Were the baseline results in Tables 1 and 2 independently reproduced or taken from their respective publications? In particular, could the authors clarify the apparent discrepancies between the reported EvA-C results and those in the original EvA paper (ICLR 2025)?
- Can the authors provide a controlled comparison of NCSP, EvA-E, and head-only refitting using identical initial ERM checkpoints, data splits, optimization budgets, and validation protocols to isolate the contribution of noise-sensitivity-based pruning?
3 comments
Q4: Verification on a new dataset without shortcut labels
Sensitivity alone cannot independently certify nuisance alignment. Appendix A.7 considers two possible representations with the same observed sensitivity vector but different nuisance coordinates. A sensitivity-only rule cannot recover the nuisance correctly in both cases.
Label-only measurements can check ranking stability, removability, prediction drift, and whether random or bottom-sensitive masks behave similarly. They can identify reasons to reject an intervention. They cannot confirm that the removed coordinates are causal shortcuts, certify unseen-group performance, or validate the gap's semantic interpretation. We do not present the recommended abstention extension as an already validated screening rule for new datasets.
Q5: Sensitive semantic features
When useful and nuisance features have overlapping sensitivity, NCSP cannot generally distinguish them. A high score marks a pruning candidate without establishing its semantic role. Row-specific masks avoid deleting a coordinate from every class indiscriminately, but they do not guarantee that the selected connections are dispensable. Refit cannot restore a useful connection that is permanently masked. If stable alternatives are missing, the method can fail.
Useful features can also be sensitive. The estimation and optimization results still apply under their stated assumptions, while shortcut recovery requires the additional separation condition.
Q6: Initialization, training details, and EvA provenance
The paper specifies an ImageNet-initialized ResNet-18 for the main experiments, followed by ERM training and a frozen backbone during NCSP. Its hyperparameter table gives the following head-refit settings:
| Setting | Waterbirds | BAR | MetaShift | FB-CMNIST |
|---|---|---|---|---|
| Optimizer | Adam | SGD | Adam | SGD |
| Learning rate | 0.01 | 0.01 | 0.001 | 0.01 |
| Epochs | 30 | 30 | 50 | 30 |
| Batch size | 64 | 128 | 128 | 128 |
| Sensitivity examples per class | 100 | 100 | 500 | 100 |
| Noise level | 0.2 | 0.2 | 0.2 | 0.1 |
| Pruning ratio | 0.25 | 0.25 | 0.25 | 0.25 |
These settings are already reported in the manuscript. We will expand the initialization details to identify the ImageNet weights and starting checkpoints for the comparisons, and distinguish initial ERM training from head refitting.
Our EvA entries are in-house implementations. We requested code from the authors but did not receive it. We will label the entries “our implementation” and explain the settings used. This will distinguish our experimental results from the original publication and make the baseline sources and settings clear.
Q7: Isolating the contribution of the score
Table G.1 already addresses the comparison with head-only refitting and alternative masks. It shows the gains and trade-offs discussed in Q2 and helps separate the complete pipeline's improvement from the effect of selecting coordinates by sensitivity. The main-table EvA entries provide an additional method comparison.
The two comparisons serve complementary purposes: Table G.1 examines the contribution of masking and refitting, while the main table compares the complete methods, including EvA-E. As explained in Q1, NCSP contributes a paired perturbation score, a guarantee for estimating its ranking, and an analysis linking the constrained refit to output stability. We will present these comparisons together with their experimental settings so that the role of the sensitivity score is clear.
NCSP contributes a distinct perturbation-based selection signal and a mathematical account of how that signal relates to the refitted classifier. We believe this is a strong foundation for work on frozen-model adaptation and for studying alternatives to confidence- or activation-based feature selection. The comparison table and question-by-question responses make that contribution explicit while crediting the shared ideas from prior work. We would be happy to provide further explanation of the EvA distinction, recovery conditions, or experimental setup if the reviewer would find it helpful.
Dear Reviewer h3jm,
Thank you for the seven focused questions. Our response answers each, and we summarise the main points here:
- Q1 and Q7, contribution beyond EvA, DFR and AFR. A comparison table separates the signal each method uses from how it adapts the head. NCSP's score is a paired clean/noisy response that does not depend on head weights or confidence, and the paper adds an estimation bound for the ranking and stability bounds for the constrained refit. Table G.1 isolates the score's contribution against refit-only and alternative masks.
- Q2, Q3 and Q5, evidence and the sensitivity assumption. We reported Table G.1 as it stands, including where refit-only and random masks are stronger, and stated that the sensitivity gap is an assumption (Assumption 4.2) rather than a consequence of Lemma 4.1. When useful and nuisance features are both sensitive, NCSP cannot separate them, and the paper reports such failures.
- Q4, verification without shortcut labels. Label-only diagnostics can reject an intervention but cannot certify it, and we do not claim the abstention rule is validated.
- Q6, checkpoints and EvA provenance. The full head-refit settings are in the paper; we will add the exact ImageNet weights and starting checkpoints. The EvA entries are our own implementation; we requested the authors' code and did not receive it, and we will label the entries as ours.
These responses address all seven questions. With two days left in the discussion period, we kindly ask you to reconsider your score in light of them, and we remain available for any further question.
Best regards, The Authors
We thank the reviewer for the questions and for highlighting NCSP's lightweight head-only intervention, its evaluation of both average and worst-group performance, and its careful distinction between noise sensitivity and shortcut identity. We also appreciate the acknowledgement that the paper reports competitive refitting and random-pruning controls. The reviewer’s questions ask us to sharpen the methodological comparison and explain the evidence, assumptions, and settings. We respond point by point below and will add an explicit paragraph describing the differences from EvA.
Q1: Contribution beyond EvA, DFR, and AFR
NCSP shares head adaptation with these methods and class-specific erasure with EvA. Its contribution has three parts:
For fixed features and class labels, the score Sc,j=E[∣ϕj(X+ε)−ϕj(X)∣∣Y=c] does not depend on the current head weights or confidence. Two coordinates can contribute similarly to clean predictions while responding differently to small input changes. NCSP measures that difference. This provides a distinct, measurable basis for selecting connections, supported by the estimation and stability analysis.
Q2: What evidence supports Gaussian sensitivity?
Table G.1 supports a useful, metric-dependent contribution from the sensitivity constraint. We reproduce its results below; entries are percentages.
Relative to refit-only, NCSP adds 4.83 points in Waterbirds WGA and 1.04 points in MetaShift average accuracy. It also exceeds random masking by 0.60 points in MetaShift average accuracy. Random masking achieves higher Waterbirds WGA, and refit-only is stronger on BAR and MetaShift WGA. These are descriptive comparisons; Table G.1 supplies no uncertainty estimates for these differences.
The reverse-pruning and predictive-drift experiments test whether the score identifies removable features and whether the intervention reduces response to the probe. Together, they support using sensitivity to study feature removability and predictor stability, complementing the downstream comparisons in Table G.1.
Q3: The sensitivity-gap assumption
Section 3.1 defines the target shift through changes in P(Z∣Y) that preserve label semantics. An attribute can predict Y in training and still be unreliable under that shift. The definition depends on the target task and shift; identifying causal attributes requires additional evidence.
Assumption 4.2 requires a head-accessible nuisance support Bc satisfying minj∈BcSc,j>maxj∈/BcSc,j+γc. If the uniform estimation error is at most ϵN, the gap exceeds 2ϵN, and the budget covers Bc, Proposition 4.3 establishes nuisance-support coverage. Without nuisance alignment, the same proposition still bounds retained sensitivity relative to its population optimum.
Lemma 4.1 provides a local-gradient interpretation of the finite-noise score. It does not prove that Gaussian noise selectively changes nuisance information, or that a given architecture or training recipe inevitably creates the gap. The recovery claim therefore depends on the stated gap assumption.