- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper studies anomaly-category unlearning in weakly supervised VAD, where masking a category’s fine-grained output in dual-branch detectors leaves the shared binary anomaly score unchanged. It proposes C-DBM, a lightweight adapter on a frozen detector, conditioned on a binary retain vector. It is trained once, and each unlearning request is then served by changing the retain vector, without retraining. On UCF-Crime and XD-Violence, it suppresses forgotten-category predictions and is compared with nine adapted unlearning baselines under a protocol that relabels forgotten-category frames as normal.
Critical strengths
The paper identifies a concrete limitation of dual-branch WSVAD: masking a category’s fine-grained output leaves the shared binary anomaly evidence intact. It addresses this, including the difficult case where retained and forgotten anomalies co-occur in the same video. The design is practical, since a single lightweight adapter serves all unlearning requests without retraining. The evaluation is extensive, with nine unlearning baselines carefully adapted to the MIL setting and per-category results reported for transparency.
Critical weaknesses
The paper frames its contribution as unlearning, but C-DBM adapts outputs on a frozen base model and does not remove learned information. The authors acknowledge this, deferring stronger unlearning guarantees to future work, and report the remaining gap to Exact Retrain as a diagnostic. The method is better understood as controllable category suppression. Under that framing, the privacy-oriented motivation and the comparison with weight-editing unlearning methods should be tempered. The framing also invites comparison with definition-conditioned VAD methods that exclude categories at inference, such as LaGoVAD (ICLR 2026), which would help position the contribution. On the evaluation side, the XD-Violence binary results are mixed relative to several baselines. Clarifying the checkpoint-selection protocol and reporting variance across seeds would make the conclusions more convincing.
Questions for authors
- Given that the base model is unchanged and requests are reversible, would the authors consider framing the work as controllable category suppression? How would this affect the privacy motivation and the choice of unlearning baselines?
- Appendix C states that Table 2 compares C-DBM’s best checkpoint with the baselines’ fixed endpoints, but the selection criterion is not specified. Since no validation split is described and Exact Retrain is selected on the official test metric (Appendix A), was C-DBM’s checkpoint also selected on test data? Do the results hold under the same fixed-endpoint rule used for the baselines?
3 comments
Response to W2 and Q2
W2: Please clarify checkpoint selection and seed variability, especially for binary detection on XD-Violence.
Q2: Please clarify the role of test metrics in checkpoint selection and report results under the baselines' fixed-endpoint rule.
We thank the reviewer for asking us to clarify the reporting protocol and quantify variability across training seeds. We report C-DBM (+ binary supervision), the current formulation with explicit request-conditioned binary supervision. It regenerates binary video targets from the retained annotated categories and replaces the original routing loss with Request-Conditioned Snippet Supervision. We will report this as the final C-DBM formulation in the revised manuscript.
1. Fixed training endpoint. All C-DBM results reported here use the final epoch-20 checkpoint. The reported epoch is fixed by the training schedule and is not chosen using test AUC, AP, forgotten-category probability, or interval-specific metrics. Checkpoints at epochs 5, 10, and 15 are evaluated only to describe training dynamics and do not determine the reported endpoint. C-DBM therefore follows the fixed-endpoint reporting convention of the iterative unlearning baselines. SSD and MUpHT use their edited checkpoints, while Exact Retrain remains a separately identified reference using its native best-checkpoint rule.
The following trajectory uses seed 234 on XD-Violence. AP follows the relabeled full-test protocol, and Fine P. follows the main-table evaluation range. Metrics are percentages and macro-averaged over six single-category requests, except M recall, which averages the four requests with nonempty overlapping intervals. For each checkpoint and request, R90 selects a threshold achieving at least 90% recall on retained-only frames. F@R90 measures forgotten-only alarms, and M-Recall@R90 measures recall where forgotten and retained events overlap.
| Base model | Epoch | Bin AP ↑ | Fine AP ↑ | F@R90 ↓ | M-Recall@R90 ↑ | Fine P. ↓ |
|---|---|---|---|---|---|---|
| VADCLIP | 5 | 77.60 | 81.11 | 59.97 | 100.00 | 1.10 |
| VADCLIP | 10 | 76.64 | 81.33 | 12.20 | 39.15 | 1.06 |
| VADCLIP | 15 | 77.58 | 81.43 | 11.15 | 41.00 | 1.10 |
| VADCLIP | 20 (final) | 77.65 | 81.45 | 10.76 | 46.30 | 1.11 |
| DSANet | 5 | 79.37 | 78.12 | 35.31 | 73.18 | 0.27 |
| DSANet | 10 | 81.71 | 78.71 | 14.46 | 46.20 | 0.24 |
| DSANet | 15 | 82.37 | 78.95 | 12.57 | 47.64 | 0.23 |
| DSANet | 20 (final) | 82.44 | 79.01 | 12.69 | 48.97 | 0.23 |
Strong binary detection holds at the fixed endpoint. Epoch-20 Binary AP reaches 77.65% on VADCLIP and 82.44% on DSANet, exceeding the nine-baseline maxima of 77.33% and 80.97%, respectively. The reporting rule remains fixed across metrics, including DSANet F@R90, whose lowest value among these snapshots occurs at epoch 15.
The trajectory also shows why detection AP and binary selectivity should be examined separately. On VADCLIP, Binary AP changes from 77.60% at epoch 5 to 77.65% at epoch 20, while F@R90 falls from 59.97% to 10.76%. Substantial changes in forgotten-only alarms can therefore occur after aggregate detection AP changes little. M recall separately exposes the accompanying tradeoff in preserving overlapping events.
2. Three-seed evaluation on XD-Violence. We evaluated the same formulation with seeds 234, 235, and 236 on both XD-Violence base models, always using the final epoch-20 checkpoint. Each seed's result is first macro-averaged over six single-category requests. We report the mean ± sample standard deviation across the three seed-level results, not variation across categories. All metrics are percentages.
| Base model / dataset | Binary AP ↑ | Fine AP ↑ | F@R90 ↓ | Fine P. ↓ |
|---|---|---|---|---|
| VADCLIP / XD-Violence | 77.61 ± 0.60 | 81.41 ± 0.04 | 8.68 ± 1.80 | 1.110 ± 0.003 |
| DSANet / XD-Violence | 82.51 ± 0.10 | 79.16 ± 0.18 | 11.21 ± 1.28 | 0.231 ± 0.001 |
Detection AP and Fine P. vary modestly across these training runs, while F@R90 shows greater variability. The mean F@R90 remains low on both base models, supporting consistent forgotten-only suppression across the evaluated seeds under the fixed-endpoint protocol. We will state the epoch-20 reporting rule explicitly in Table 2 and Appendix C and report these three-seed statistics alongside the XD-Violence results.
Post Rebuttal
Thank you for the detailed rebuttal. I have reviewed the additional results and comments and will keep my score accordingly. I encourage the authors to incorporate the new details into the final manuscript.
Response to W1 and Q1
W1: Please clarify C-DBM's behavioral scope and its relationship to definition-conditioned VAD methods such as LaGoVAD.
Q1: How would a controllable category-suppression framing affect the motivation and choice of baselines?
We thank the reviewer for highlighting the connection to definition-conditioned VAD and asking us to clarify the scope of C-DBM. Our starting point is a base WSVAD model already trained with all available anomaly categories. C-DBM studies anomaly-category unlearning in this existing detector, aiming to suppress selected learned categories while preserving retained-anomaly detection. We freeze the base WSVAD model and train a single request-conditioned adapter under simulated category-unlearning requests. After this one-time adapter training, deployment requests change only the retain vector, without request-specific optimization.
The distinction from LaGoVAD lies in the detector training and adaptation setting. LaGoVAD learns to detect anomalies conditioned on user-specified language definitions and evaluates zero-shot generalization across datasets. Its formulation permits both expanding and narrowing anomaly definitions, so the connection extends beyond detecting previously unseen anomalies. Both works address changing anomaly definitions, while C-DBM studies how to equip an already-trained base WSVAD model with selective control over its existing anomaly categories.
This adaptation setting makes the existing detector's shared binary anomaly response central to our problem. The binary branch has already learned to respond to categories that may subsequently be forgotten. Masking their fine-grained logits leaves that binary response unchanged. CTR reads category-conditioned temporal states, while FSM and BEM modulate fine-grained semantic and shared binary responses according to the retain vector. The objective is to change both responses under the category-unlearning request, with forgotten-only suppression and retained-event detection evaluated separately. The base model need not have been trained to change its anomaly definition from one request to another.
This scope clarifies the motivation and baselines. We agree that controllable category suppression accurately describes C-DBM's behavioral scope. We will make this scope explicit when presenting anomaly-category unlearning and center the motivation on changing operational anomaly definitions. Since the base WSVAD model remains unchanged and requests are reversible, we will remove wording that implies irreversible information erasure or associated privacy guarantees.
The nine adapted unlearning baselines compare request-specific parameter updates or parameter editing with C-DBM's shared request-conditioned adapter. They compare alternative adaptation mechanisms under the same category-unlearning requests and request-dependent evaluation protocol. Hard Closure, logit calibration, soft masking, an MLP replacement for CTR, and uniform routing provide direct controls for the architecture's contribution. We will discuss LaGoVAD explicitly in Related Work and clarify the distinction between learning definition-conditioned detection and adapting an existing base WSVAD model.