- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes SlotODE, an ODE-based iterative slot update mechanism for unsupervised object-centric learning. The authors introduce the concept of slot-state collision, where initially distinct slot representations become identical during iterative updates. To address this issue, SlotODE models slot updates as continuous-time dynamics and theoretically guarantees the exclusion of finite-time slot-state collisions under certain assumptions. Experimental results demonstrate improved object discovery performance across multiple benchmarks, including MOVi-C/E, COCO, and CLEVR10.
Critical strengths
-
The proposed method consistently outperforms conventional Slot Attention on MOVi-C, MOVi-E, COCO, and CLEVR10. These improvements across different datasets and training settings provide meaningful evidence of the practical effectiveness of the proposed update mechanism.
-
The paper provides a clear mathematical formulation of slot-state collision and establishes theoretical guarantees on finite-time collision exclusion and pairwise slot separation. This provides an interesting perspective on understanding iterative slot updates in object-centric learning.
Critical weaknesses
1. Empirical Validation of Slot-State Collision
The paper defines slot-state collision as the case where two initially distinct slot representations become exactly identical during iterative updates. However, it remains unclear how frequently such exact collisions occur in conventional Slot Attention (or even this really occurs) and whether they are a significant cause of object-level redundancy or fragmentation.
While the paper provides qualitative visualizations of slot trajectories, additional quantitative evidence would strengthen the motivation.
Here are my suggestions (just suggestions, not requirements, and alternative approaches are welcome if deemed more appropriate) :
- Measuring pairwise slot distances throughout iterative updates and analyzing the frequency of exact or near-collisions could help establish whether this phenomenon occurs in practice.
- Examining the relationship between slot-state collisions and object-level redundancy or fragmentation would help clarify whether preventing such collisions directly contributes to the observed performance improvements.
2. Hyperparameter Sensitivity & Heuristic Choices.
The method involves several hyperparameters that vary across datasets.The paper would benefit from further clarification of how these dataset-specific values were determined and whether the results are sensitive to these choices.
For example, why is the target retention ratio fixed at 0.5, and how sensitive is the model to this choice? A sensitivity analysis over different retention ratios would help establish the robustness of this heuristic. Furthermore, since the method is unsupervised, clarifying how these hyperparameters are selected without relying on ground-truth object annotations would strengthen the experimental evaluation.
Questions for authors
In Table 2, SlotODE achieves strong FG-ARI results, but SPOT with an autoregressive Transformer decoder achieves substantially higher mBO scores. Since SlotODE mainly modifies the slot update mechanism, have the authors considered using a Transformer or autoregressive decoder instead of the MLP decoder? Could this improve mBO and narrow the performance gap?
Additionally, as discussed in Weakness 1, it would be interesting to investigate whether slot-state collisions actually occur under different decoder architectures and whether the collision problem persists regardless of the decoder choice.
6 comments
The results show the following:
- The mean is below 1.0 under Slot Attention (0.65), indicating relative contraction of the final closest pair on average. Under SlotODE, it is above 1.0 (1.82), indicating relative expansion on average.
- While 5.41% of Slot Attention images have , no SlotODE images fall below this threshold. These results indicate that the final closest pair retains stronger relative separation under SlotODE.
- Among images with , the final closest pair’s mean mask IoU is lower under SlotODE than under Slot Attention (0.23 vs. 0.32). Slot Attention images with the more severe have a mean IoU of 0.86, whereas SlotODE’s rare cases have a mean IoU of 0.23. Stronger preservation of relative separation under SlotODE is accompanied by lower mask overlap.
| Method | Mean |
|---|---|
| Slot Attention | 0.65 |
| SlotODE | 1.82 |
| Method | (%) | IoU | (%) | IoU |
|---|---|---|---|---|
| Slot Attention | 5.41% | 0.86$_{\pm .10}$ | 56.99% | 0.32$_{\pm .16}$ |
| SlotODE | 0% | -- | 0.58% | 0.23$_{\pm .15}$ |
We have newly added Appendix B.6 to the revised manuscript. It reports results at each update step and visualizes the image-wise distribution of . We would appreciate the reviewer’s consideration of these additional results.
W2 Hyperparameter sensitivity
We agree that showing how sensitive the results are to these choices would help readers assess the method.
We use across all datasets as a simple, shared target that encourages the model to retain approximately half of the candidate slots in expectation. This value was not chosen from ground-truth object annotations or a dataset-specific estimate of object counts.
We agree, however, that the most suitable retention ratio may differ across datasets depending on scene complexity and object composition. To examine sensitivity to this choice, we varied on MOVi-C while keeping the other SlotODE settings fixed. We used two runs for each additional setting; the row reports the original result.
| FG-ARI | mBO$_i$ | |
|---|---|---|
| 0.3 | 40.44$_{\pm 8.5}$ | 15.21$_{\pm 5.8}$ |
| 0.4 | 57.48$_{\pm 3.3}$ | 25.69$_{\pm 0.7}$ |
| 0.5 | 79.15$_{\pm 0.2}$ | 38.62$_{\pm 0.1}$ |
| 0.6 | 78.63$_{\pm 0.2}$ | 38.30$_{\pm 0.1}$ |
| 0.7 | 75.78$_{\pm 0.3}$ | 36.87$_{\pm 0.2}$ |
The results are similar at and , but performance declines at 0.3 and 0.4. The comparable result at suggests that 0.5 is not a narrowly tuned choice on MOVi-C, while the decline at lower ratios shows that the choice of target still matters.
The improvement from SlotODE is also observed without the adaptive slot-selection loss, as shown in Appendix B.1 (Table 8). The autoregressive Transformer decoding results presented below likewise show an FG-ARI improvement without this loss. Thus, the observed benefit of the SlotODE update does not rely solely on the choice of and adaptive slot selection. Determining the most suitable number of slots for different scenes remains an important question in object-centric learning, and we have added this sensitivity analysis to Appendix C.3 of the revised manuscript, with the new text highlighted in magenta.
Q1 SlotODE with autoregressive decoder
During the rebuttal period, we conducted additional experiments with an autoregressive Transformer decoder (Auto.) on MOVi-C and COCO. We used a DINOSAUR setup with a pretrained ViT encoder and compared SlotODE with conventional Slot Attention under the same decoder. Each new configuration was run twice.
AdaSlot's adaptive slot-selection mechanism suppresses unselected slots through the alpha masks produced by a mixture decoder. Its direct application to segmentation masks derived from autoregressive decoder attention has not been established. We therefore conducted this comparison without adaptive slot selection for either method.
- With the autoregressive decoder held fixed, SlotODE achieves higher FG-ARI but lower mBO$_i$ than Slot Attention on both MOVi-C and COCO.
- Compared with SlotODE with MLP decoder, SlotODE with the autoregressive Transformer decoder achieves higher mBO$_i$ but lower FG-ARI on both datasets. Conventional Slot Attention also shows the same direction of change relative to its MLP-decoder results in Appendix B.1 (Table 8).
| Method | Decoder | Adaptive slot selection | Dataset | FG-ARI | mBO$_i$ |
|---|---|---|---|---|---|
| Slot Attention (new) | Auto. | X | MOVi-C | 54.76$_{\pm 2.0}$ | 45.93$_{\pm 1.0}$ |
| SlotODE (new) | Auto. | X | MOVi-C | 62.75$_{\pm 0.5}$ | 42.89$_{\pm 0.2}$ |
| SlotODE (reported) | MLP | X | MOVi-C | 67.27$_{\pm 0.3}$ | 36.51$_{\pm 0.4}$ |
| Slot Attention (new) | Auto. | X | COCO | 31.99$_{\pm 0.6}$ | 31.95$_{\pm 0.6}$ |
| SlotODE (new) | Auto. | X | COCO | 33.62$_{\pm 0.1}$ | 31.79$_{\pm 0.4}$ |
| SlotODE (reported) | MLP | X | COCO | 40.81$_{\pm 0.1}$ | 28.55$_{\pm 0.3}$ |
The results show the following:
These findings suggest that decoder choice can reduce the mBO$_i$ gap raised by the reviewer while retaining SlotODE’s slot update mechanism.
Q2 Collision in different decoders
We agree that decoder architecture can affect the slot states learned through reconstruction and may change how closely they approach one another during refinement. However, replacing the decoder does not guarantee that initially distinct slots remain distinct under conventional Slot Attention’s discrete update. SlotODE focuses on preserving slot separation through its update mechanism.
We additionally analyze slot separation with the autoregressive Transformer decoder (Auto.) on MOVi-C. Following W1, we compute at each update step and report its final value together with the mask IoU of the closest pair. With the same autoregressive decoder, SlotODE has a higher final minimum-to-mean distance ratio (0.40 vs. 0.23) and lower closest-pair mask IoU (0.15 vs. 0.47) than Slot Attention.
| () | IoU of closest pair () | |
|---|---|---|
| Slot Attention | 0.23 | 0.47$_{\pm .05}$ |
| SlotODE | 0.40 | 0.15$_{\pm .03}$ |
We examine whether the benefit of changing the slot update persists across decoder architectures.
- Autoregressive Transformer (new,
Q1): With the decoder held fixed, SlotODE achieves higher FG-ARI than Slot Attention on MOVi-C and COCO without adaptive slot selection. - CNN decoder: On CLEVR10, SlotODE also improves FG-ARI (96.64 vs. 94.72) and mBO$_i$ (22.45 vs. 21.04) over conventional Slot Attention (Table 1).
Together with the MLP-decoder analysis in W1, these measurements show that conventional Slot Attention produces close slot pairs with overlapping masks under both MLP and autoregressive Transformer decoders. SlotODE shows greater relative separation and lower mask overlap in both settings. The CLEVR10 result further shows that its performance benefit extends to a CNN decoder.
We appreciate Reviewer S1d3 for the insightful comments and constructive feedback.
W1 Quantitative evidence of slot separation and mask overlap during Euler updates
To address both concerns, we compare Slot Attention and SlotODE on MOVi-C under the same adaptive slot-selection mechanism. Our two numerical analyses show that SlotODE better preserves the relative separation of the final closest slot pair and exhibits less mask overlap than Slot Attention, consistent with its better segmentation performance.
(1) Quantitative analysis of slot separation
We quantify slot proximity at the final update using the ratio of the minimum pairwise distance to the mean pairwise distance, and assess whether the closest pair’s predicted segmentation masks overlap.
For each image Xn and update step t, we compute the Euclidean distance between every pair of selected slots:
dn,ij(t)=sn,i(t)−sn,j(t)2,(i,j)∈Cn,
where Cn contains all unordered pairs of selected slots in image n. We then calculate the mean pairwise distance and the minimum pairwise distance for each image:
dˉn(t)=∣Cn∣1∑(i,j)∈Cndn,ij(t),dn,min(t)=min(i,j)∈Cndn,ij(t).
We average the mean and minimum pairwise distances across images as Dpair(T),Dmin(T). At the final update, we report their ratio, Dmin(T)/Dpair(T), to measure the closest-pair distance relative to the overall pairwise distance.
At the final update T, we identify the pair attaining the minimum distance in each image and compute the IoU between their predicted segmentation masks. This measures whether the closest latent pair also has overlapping masks.
The results show the following:We have newly added Appendix B.5 to the revised manuscript. It summarizes the analysis above and reports Dpair(t) and Dmin(t) , and their ratio at initialization and every update step.
(2) Slot separation preservation during updates
We also present an additional analysis that measures how the distance between the final closest pair changes from initialization to the final output. At each step, we measure its distance relative to the mean pairwise distance. The following results show stronger preservation of relative slot separation under SlotODE than under Slot Attention.
To measure how the final closest pair’s relative separation changes from initialization to the final update, we compute an image-wise relative separation change ratio Rn. For each image Xn, we identify the pair with the minimum distance at the final update and track this pair across all update steps. We normalize its distance at each step by the mean pairwise distance among the selected slots in that image:
(in∗,jn∗)=argmin(i,j)∈Cndn,ij(T),rn(t)=dˉn(t)dn,in∗jn∗(t),Rn=rn(0)rn(T).
Rn<1 indicates that the pair’s distance has decreased relative to the other selected pairs, while Rn>1 indicates that its relative distance has increased. We report the mean Rn, the fraction of images for which Rn falls below each threshold, and the mean IoU of the final masks for those images.