- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes Routable Parameter Memories (RPM) for exemplar-free lifelong person re-identification. It introduces two components: Subspace-Guided Writing (SGW) to reduce interference when learning new domain-specific LoRA memories, and Prototype-Guided Reading (PGR) to adaptively retrieve and combine memories for each test image. Experiments show improved retention of previously learned domains and generalization to unseen domains.
Critical strengths
Strength 1: RPM separates the problem into writing, storing, and reading domain-specific LoRA memories. SGW is intended to reduce overlap with historical activation subspaces, while PGR uses prototype similarities to compose memories for each query. This decomposition is easy to understand and directly targets the tension between retaining prior knowledge and adapting to new domains without keeping historical images.
Strength 2: The paper evaluates two domain orders, seen-domain retention, and generalization to unseen datasets, and includes ablations of the writing and reading mechanisms. The reported results show consistent improvements over the listed baselines, while the ablations provide evidence that prototype-guided soft reading and subspace-guided writing contribute complementary benefits.
Critical weaknesses
Weakness 1: SGW shares the idea of using historical activation subspaces to reduce interference with prior tasks, as in GPM [1], while LoDA [2] also explores activation-based subspace decomposition for LoRA continual learning. KeepLoRA [3] is particularly relevant, as it uses residual-subspace projection, SVD-based initialization, and freezes one LoRA factor while training the other. SGW differs in using projected current-domain activation statistics to construct the input directions of new LoRA memories, rather than projecting task gradients to constrain updates. However, the paper does not sufficiently demonstrate the advantages of this design over these related approaches. At the framework level, RPM's incremental parameter memories and input-dependent retrieval are also related to MoRAM [4], although their memory representations and retrieval mechanisms differ. The authors should more clearly establish the distinct contributions of SGW and PGR beyond these existing ideas.
Weakness 2: The evidence on forgetting and efficiency is incomplete. SGW's near-zero subspace overlap does not necessarily imply less forgetting on previously learned domains. Moreover, some AF/BWT results in the appendix are reconstructed estimates rather than direct measurements, making their reliability difficult to assess without the underlying per-domain, per-stage results.
Weakness 3: RPM also has substantially higher inference latency than some baselines, raising concerns about its computational efficiency as the memory bank grows.
Questions for authors
Question 1: How does SGW differ technically from GPM [1], LoDA [2], and KeepLoRA [3] in constructing and constraining the LoRA writing subspace? In particular, what advantages does SGW's activation-based subspace projection and SVD-based LoRA-A initialization over existing subspace-constrained LoRA methods? Can the authors provide direct or appropriately adapted comparisons under the same ReID evaluation protocol?
Question 2: How does RPM's domain-level memory design and prototype-guided retrieval differ from MoRAM's [4] rank-1 memory expansion and self-activated retrieval, and what advantages does it provide?
Question 3: Forgetting evaluation and efficiency. Can the authors provide actual per-domain, per-stage performance matrices underlying the AF/BWT metrics?
Question 4:How does inference latency scale with the number of stored memories, and can sparse Top-k retrieval improve efficiency without substantially compromising accuracy?
References
[1] G. Saha, I. Garg, and K. Roy. "Gradient Projection Memory for Continual Learning." ICLR, 2021. https://openreview.net/forum?id=3AOj0RCNC2
[2] L. He, D. Cheng, H. Wang, X. Yang, N. Wang, and X. Gao. "Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning." ICML, 2026. https://proceedings.mlr.press/v306/he26f.html
[3] "KeepLoRA: Continual Learning with Residual Gradient Adaptation." ICLR, 2026. https://proceedings.iclr.cc/paper_files/paper/2026/hash/dc3ca8bcd613e43ce540352b58d55d6d-Abstract-Conference.html
[4] H. Lu, C. Zhao, J. Xue, L. Yao, K. Moore, and D. Gong. "Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts." ICML, 2026. https://proceedings.mlr.press/v306/lu26au.html
9 comments
Response to Reviewer bgrh (2/4): Domain-level memories and prototype-guided reading compared with MoRAM
Thank you for asking about the differences between RPM and MoRAM in memory organization and retrieval. Our response is provided below:
W1 / Q2. Domain-level memory and prototype-guided retrieval versus MoRAM.
RPM and MoRAM differ in both memory granularity and the source of their retrieval weights. MoRAM expands rank-1 key–value atoms and obtains token-level mixture weights through sparse self-activation of their intrinsic keys. RPM preserves each domain’s learned, multilayer LoRA transformations as a domain-level memory. Multiple prototype anchors, computed with LoRA disabled, provide visual references for addressing that memory.
For each image, RPM computes a query in the same frozen-backbone feature space as the anchors. Prototype similarities produce image-level soft weights shared across the inserted layers, while layer-wise amplitudes modulate each memory’s contribution at different depths. This separates visual addressing from the LoRA factors used for constrained writing. The input factors can serve the writing constraint, while the anchors provide independent reading cues. Each domain’s learned transformation remains available as a unit for image-dependent composition.
Table 5 supports the proposed reading choice within RPM: multi-anchor soft reading achieves 65.2/76.7 Seen-Avg and 73.3/67.6 Unseen-Avg, compared with 61.0/72.3 and 52.8/45.2 for hard prototype reading. Single-anchor reading reaches 64.7/76.1 and 72.4/66.1, supporting the use of multiple visual references per domain.
We have additionally compared our method with ReID-adapted MoRAM under the same protocol, preserving MoRAM’s rank-1 memory expansion and sparse intrinsic-key self-activation. Both methods produce retrieval embeddings without ground-truth test-domain labels. The Ours row uses the same matched evaluation as in Q1.
The comparison uses the same ImageNet-1K-pretrained TransReID ViT-B/16 initialization, two training orders, five seen domains, seven unseen domains, query/gallery splits, identity-classification and triplet objectives, epoch budget, and ten paired training seeds. Hyperparameters are selected through independent source-domain validation.
This comparison directly evaluates the practical effects of domain-level memories with separate prototype addressing versus rank-1 memories with intrinsic-key self-activation, complementing the reading-strategy ablations in Table 5. Each entry reports mean ± standard deviation over ten training seeds, in mAP/R@1 format:
| Method | Order-1 Seen-Avg | Order-1 Unseen-Avg | Order-2 Seen-Avg | Order-2 Unseen-Avg |
|---|---|---|---|---|
| MoRAM, ReID-adapted | ||||
| Ours |
Response to Reviewer bgrh (3/4): Actual stage-by-domain performance matrices for AF/BWT
Thank you for requesting the stage-by-domain performance matrices underlying AF/BWT. Our response is provided below:
W2 / Q3. Actual per-domain, per-stage performance matrices.
We have conducted additional stage-by-domain retrieval evaluations for RPM under both training orders. Below, we provide the actual performance matrices used to calculate AF/BWT. Each row corresponds to the model after completing a training stage, and each column corresponds to a domain. Each entry reports that stage model’s mAP/R@1 on the corresponding domain. “n/a” denotes a domain not yet learned.
RPM, Training Order-1: Market → SYSU → LPW-s2 → MSMT17-V2 → CUHK03.
| Stage | Market | SYSU | LPW-s2 | MSMT17-V2 | CUHK03 |
|---|---|---|---|---|---|
| 1 | 82.0/92.8 | n/a | n/a | n/a | n/a |
| 2 | 74.9/89.2 | 90.0/90.6 | n/a | n/a | n/a |
| 3 | 71.8/89.2 | 95.0/92.6 | 70.0/86.0 | n/a | n/a |
| 4 | 69.6/87.5 | 89.0/90.0 | 75.0/80.0 | 52.3/84.4 | n/a |
| 5 | 69.7/86.9 | 89.7/90.8 | 61.0/71.9 | 45.5/71.8 | 59.9/62.0 |
RPM, Training Order-2: LPW-s2 → MSMT17-V2 → Market → SYSU → CUHK03.
| Stage | LPW-s2 | MSMT17-V2 | Market | SYSU | CUHK03 |
|---|---|---|---|---|---|
| 1 | 49.0/65.0 | n/a | n/a | n/a | n/a |
| 2 | 56.5/70.0 | 29.3/61.0 | n/a | n/a | n/a |
| 3 | 58.8/73.0 | 39.9/69.9 | 63.0/84.2 | n/a | n/a |
| 4 | 55.8/72.5 | 37.0/67.0 | 78.2/93.3 | 91.3/94.7 | n/a |
| 5 | 56.8/69.0 | 38.4/65.9 | 77.2/90.3 | 90.6/91.7 | 59.5/61.6 |
AF/BWT are calculated directly from these measured results. RPM achieves low AF and favorable BWT under both training orders while maintaining strong final retrieval performance. These results demonstrate RPM’s effectiveness in mitigating forgetting and preserving previously learned knowledge during sequential learning.
Response to Reviewer bgrh (1/4): SGW writing subspaces compared with GPM, LoDA, and KeepLoRA
Thank you for asking how SGW differs from GPM, LoDA, and KeepLoRA in constructing and constraining writing subspaces. Our response is provided below:
SGW constructs current-domain-informed input directions before optimization and maintains the selected subspace by freezing LoRA-A. With all LoRA updates disabled, we compute the current-domain activation statistic Ctl, project it using the historical writing state as Ctl=Pt−1lCtl, and initialize LoRA-A from its leading left singular directions. LoRA-A remains fixed while LoRA-B is optimized.
The technical distinctions from the three related approaches are:
The distinction lies in how the writing directions are selected and constrained. SGW combines current-domain statistical information with historical directional constraints; fixing LoRA-A prevents the selected input subspace from drifting during optimization. Table 3 supports its contribution within RPM: adding SGW to the PGR configuration improves Seen-Avg from 64.1/76.0 to 65.2/76.7 and Unseen-Avg from 72.7/65.9 to 73.3/67.6, in mAP/R@1.
We have added ReID-adapted comparisons with GPM, LoDA, and KeepLoRA under the same evaluation protocol. The comparison uses the same ImageNet-1K-pretrained TransReID ViT-B/16 initialization, two training orders, five seen domains, seven unseen domains, query/gallery splits, identity-classification and triplet objectives, epoch budget, and ten paired training seeds. Hyperparameters are selected through independent source-domain validation. Each adaptation preserves the corresponding method’s defining constraints, optimization, and update-integration rules, with actual trainable parameters and retained states reported.
These method-level ReID comparisons directly evaluate the practical performance of the different approaches under a common task protocol. Together with the internal ablation in Table 3, they provide complementary evidence for assessing SGW’s contribution. Each entry below reports mean ± standard deviation over ten training seeds, in mAP/R@1 format: