- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Keeping Past Knowledge at Work (KPKW), an exemplar-free framework for lifelong person re-identification. The method preserves domain-specific transformations as frozen LoRA updates and records layer-wise input second moments and between-class scatter before historical data become unavailable. These statistics are subsequently used to coordinate the accumulated LoRA updates through channel-wise composition, historical response and output-structure preservation, and identity-related gradient adjustment.
Critical strengths
S1. A coherent approach to preserving and reusing historical knowledge without exemplar replay.
The paper addresses a meaningful challenge in lifelong ReID: maintaining the utility of previously acquired knowledge when historical images are no longer accessible. Preserving domain-specific transformations together with statistical references is a reasonable design. In particular, the relationship between retained input second moments and historical linear-response discrepancies provides a clear mathematical motivation for the proposed coordination objective.
S2. Competitive empirical performance with relatively extensive supporting analyses.
The method achieves strong results on both seen and unseen domains under two training orders. The supplementary material further includes forgetting analysis, multiple random seeds, component ablations, statistical compression, and computational-cost measurements. These experiments provide useful evidence for the effectiveness of the proposed approach and make its practical trade-offs more transparent.
Critical weaknesses
W1. Insufficient justification for the choice of historical statistics
In Sec. 3.5 (Eqs. 12–15), the authors use the principal directions of between-class scatter () to preserve historical identity-related information. However, mainly captures differences between identity means and does not explicitly model within-identity variations, which are important for ReID, as highlighted by DKP (CVPR 2024). The paper does not sufficiently explain why is preferred over alternatives such as within-class scatter () or identity-level covariance.
The experimental evidence is also limited. In Table A1 (supplementary, p. 22), the final soft projection is compared with alternatives using hard projection, making it difficult to isolate the effect of the chosen statistic. Furthermore, Table A16 (supplementary, p. 36) shows only marginal and inconsistent gains from guidance. These results leave the necessity and effectiveness of this particular statistical choice insufficiently established.
W2. Inconsistency in the reported experimental results.
The supplementary material contains an inconsistency between the description on p. 22 and the results in Table A18. The former reports different performance values for the full KPKW configuration from those shown in the table. This raises concerns about the clarity and consistency of the experimental reporting, particularly regarding which runs were used for the efficiency comparisons.
W3. Limited evidence for reduced catastrophic forgetting.
Although KPKW achieves strong final Seen-Avg performance in Tables 2–3 and Fig. 4, higher average accuracy does not necessarily indicate less forgetting. Table A3 reports AF and BWT only for KPKW, without corresponding results from competing methods. As a result, it remains unclear whether the reported improvements mainly come from better historical knowledge retention or stronger initial performance on individual domains.
W4. Limited validation of the historical response constraint.
The proposed response preservation objective is derived from historical layer-input statistics, but its effectiveness in preserving end-to-end identity representations is less clear. Fig. 5 relates the optimized response drift to historical performance, yet this does not directly show whether the original identity features or retrieval relationships are preserved after subsequent learning stages. More direct evidence is needed to support the connection between the proposed statistical constraint and actual historical ReID knowledge retention.
Questions for authors
Q1. Choice of historical statistics (Sec. 3.5, Table A16).
Why do the authors use between-class scatter () rather than alternatives such as within-class scatter () or identity-level covariance, which could better capture within-identity variations? A comparison under the same gradient adjustment strategy and projection strength would help justify this choice. Also, given the limited gains from in Table A16, how much does this component actually contribute to preserving historical ReID knowledge?
Q2. Inconsistent results in the supplementary material (p. 22, Table A18).
The results stated for Table A18 on p. 22 of the supplementary material do not match the values reported in the table itself. Could the authors clarify which random seed, checkpoint, and experimental configuration were used for Table A18, and explain the discrepancy?
Q3. Evaluation of catastrophic forgetting (Fig. 4, Tables 2–3, and Table A3).
Fig. 4 and Tables 2–3 mainly report average performance, but a higher Seen-Avg does not necessarily imply less forgetting. Although Table A3 reports AF and BWT for KPKW, corresponding results for competing methods are missing. Could the authors provide a direct comparison under the same protocol to show whether the improvements come from better knowledge retention rather than stronger initial performance on individual domains?
Q4. Validity of the historical response constraint (Fig. 5).
Fig. 5 relates the statistics-weighted response drift to historical-domain performance. However, this drift is also the quantity directly optimized by the proposed method. Could the authors evaluate the actual feature drift or retrieval relationship changes between the original domain-specific models and the final unified model? This would help establish whether the statistical constraint preserves historical identity-discriminative information at the level of the full network.
3 comments
Response to Reviewer MwC7 (2/3): Acquisition and forgetting
Thank you for highlighting the need to distinguish stronger initial acquisition from better historical knowledge retention. Our response is provided below:
W3 / Q3. Forgetting
We directly compare initial acquisition and subsequent forgetting with PAEMA, DRE, and DKUA under both training orders. To distinguish stronger acquisition from better retention, we report the average performance immediately after learning each of the first four historical domains, their final average performance, AF, and BWT. The fifth domain experiences no subsequent task and is excluded from these four historical-retention measures. Each cell reports mAP/R@1, with AF and BWT expressed as absolute differences (%).
| Order | Method | Acquisition | Final historical performance | AF ↓ | BWT ↑ |
|---|---|---|---|---|---|
| Order-1 | PAEMA | 68.9/80.8 | 61.9/74.4 | 7.0/6.4 | −7.0/−6.4 |
| Order-1 | DRE | 74.3/84.5 | 61.5/74.0 | 12.8/10.6 | −12.8/−10.6 |
| Order-1 | DKUA | 70.5/81.7 | 58.0/70.1 | 12.5/11.6 | −12.5/−11.6 |
| Order-1 | KPKW | 68.7/81.3 | 63.8/78.4 | 5.4/3.4 | −4.9/−3.0 |
| Order-2 | PAEMA | 69.3/86.7 | 61.4/75.3 | 7.9/11.4 | −7.9/−11.4 |
| Order-2 | DRE | 74.7/85.9 | 61.1/75.0 | 13.6/10.9 | −13.6/−10.9 |
| Order-2 | DKUA | 70.2/81.8 | 59.6/72.7 | 10.7/9.1 | −10.7/−9.1 |
| Order-2 | KPKW | 70.2/83.4 | 63.2/77.9 | 7.0/5.5 | −7.0/−5.5 |
AF measures the decline from historical peak performance, while BWT measures the change from acquisition-stage to final performance. Both are computed from each method’s stage-by-domain results, rather than using final Seen-Avg as a substitute for forgetting.
KPKW achieves lower AF and higher BWT under both training orders. Its advantage therefore includes better historical knowledge retention and cannot be explained solely by stronger initial acquisition. The frozen updates retain learned transformations, while historical statistical constraints limit changes in their responses during subsequent composition. This comparison provides direct evidence for the retention benefit of this design.
Response to Reviewer MwC7 (3/3): End-to-end preservation
Thank you for suggesting direct measurements of end-to-end feature drift and changes in retrieval relationships. Our response is provided below:
W4 / Q4. End-to-end preservation
We directly measure the actual final-feature drift and changes in Query–Gallery retrieval relationships from the original domain-specific models to the final unified model on the same historical images. We quantify these changes using feature cosine drift and Top-10 retrieval overlap, together with historical mAP/R@1 to assess the preservation of identity-discriminative retrieval performance. Each training order is reported separately, with equal-weight averages over its first four domains. denotes the final unified model’s mAP/R@1 minus that of the corresponding original domain-specific model.
| Order | Configuration | Feature cosine drift ↓ | Top-10 overlap ↑ | mAP/R@1 | mAP/R@1 |
|---|---|---|---|---|---|
| 1 | No historical statistical constraints | 0.6352 | 48.0% | 59.6/75.7 | −13.3/−8.7 |
| 1 | Response preservation | 0.2927 | 55.3% | 63.8/78.1 | −9.3/−6.3 |
| 1 | Full KPKW | 0.3005 | 55.0% | 63.9/78.4 | −9.2/−6.1 |
| 2 | No historical statistical constraints | 0.4972 | 45.5% | 57.6/72.9 | −15.5/−11.9 |
| 2 | Response preservation | 0.3069 | 54.8% | 62.4/77.0 | −10.8/−7.8 |
| 2 | Full KPKW | 0.3199 | 54.1% | 63.2/78.0 | −10.1/−6.9 |
Under matched settings, adding response preservation reduces final-feature drift, increases Top-10 retrieval overlap, and improves historical-domain mAP/R@1 compared with composition without historical statistical constraints. Response preservation yields the lowest drift and highest overlap, while Full KPKW achieves the highest mAP and R@1 under both orders. These end-to-end measurements are independent of the optimized response drift in Fig. 5 and support the role of the response constraint in preserving historical identity representations and retrieval relationships.
Response to Reviewer MwC7 (1/3): Historical statistics and Table A18 correction
Thank you for your questions about the choice of historical statistics and for identifying the Table A18 reporting discrepancy. Our response is provided below:
We use SB to guide coefficient optimization with directions that distinguish historical identity means. During Coordination, the LoRA updates are frozen, and only their channel-wise composition coefficients are optimized. The principal directions of SB describe differences among historical identity means and provide a reference for reducing interference with these directions during composition.
SW describes within-identity variation, which is also important for ReID. However, directions with large within-identity variation do not necessarily distinguish different identities. The choice of statistic therefore depends on the purpose of the adjustment. Here, SB supplies identity-related directions for gradient guidance. Historical knowledge is retained jointly through the frozen LoRA updates, Σ-based response and output-structure preservation, and this directional guidance.
We compare the statistics under the same adjustment strategy and strength. To avoid the soft-versus-hard difference in Table A1, we compare no guidance, SB, and SW using the same sequential soft-adjustment rule, β=0.75, and matched subspace ranks. The remaining losses, initialization, statistical sampling, and training budget are fixed. Each cell reports mAP/R@1.
Among these configurations, SB is best on all four Order-1 metrics. Under Order-2, it achieves the highest Seen mAP and ties the highest Seen R@1, while no guidance gives the highest Unseen-Avg. Thus, its benefit depends on the training order and evaluation domains.
The corrected Table A16 also clarifies the contribution of SB within the complete method. Checking the experimental logs revealed a copy-and-paste error in the original Full-row accuracy entries. The correct results are:
Adding SB without Output produces mixed changes. With Output enabled, adding SB improves Seen-Avg by 0.3%/0.7% and Unseen-Avg by 1.0%/1.4%. Thus, on Order-1, SB improves all four retrieval metrics in the complete configuration, and its contribution interacts with output-structure preservation.
The Table A18 Discrepancy Is a Copy-and-Paste Error, Not a Seed Difference
The Full-model scores attributed to Table A18 in the overview of Appendix D were incorrectly copied. The correct values are 62.2/74.2 Seen-Avg and 73.9/68.0 Unseen-Avg, in mAP/R@1. Table A18 itself reports these values correctly.
Task-only composition, Response preservation, and KPKW Full in Table A18 all use Training Order-1 and seed 3407. For each configuration, the retrieval accuracy, training time, and Coordination peak memory come from the same training record. The accuracy and resource entries therefore correspond to the same run for each configuration.