QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning

Tianran Ouyang; Xingping Dong; Jing Zhang; Mang Ye; Kaihao Zhang; Bo Du

cs.CVJan 19, 2026

QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning

Authors: Tianran Ouyang, Xingping Dong, Jing Zhang, Mang Ye, Kaihao Zhang, Bo Du

Organizations: Wuhan University · Australian National University

Abstract

Slot Attention, an approach that binds different objects in a scene to a set of "slots", has become a leading method in unsupervised object-centric learning. Most methods assume a fixed slot count K, and to better accommodate the dynamic nature of object cardinality, a few works have explored K-adaptive variants. However, existing K-adaptive methods still suffer from two limitations. First, they do not explicitly constrain slot-binding quality, so low-quality slots lead to ambiguous feature attribution. Second, adding a slot-count penalty to the reconstruction objective creates conflicting optimization goals between reducing the number of active slots and maintaining reconstruction fidelity. As a result, they still lag significantly behind strong K-fixed baselines. To address these challenges, we propose Quality-Guided K-Adaptive Slot Attention (QASA). First, we decouple slot selection from reconstruction, eliminating the mutual constraints between the two objectives. Then, we propose an unsupervised Slot-Quality metric to assess per-slot quality, providing a principled signal for fine-grained slot--object binding. Based on this metric, we design a Quality-Guided Slot Selection scheme that dynamically selects a subset of high-quality slots and feeds them into our newly designed gated decoder for reconstruction during training. At inference, token-wise competition on slot attention yields a K-adaptive outcome. Experiments show that QASA substantially outperforms existing K-adaptive methods on both real and synthetic datasets. Moreover, on real-world datasets QASA surpasses K-fixed methods.

Figures & tables

Figure 1: mBOi vs. slot count $K$ on COCO [ 25 ] . $K$ -fixed methods, such as SPOT [ 20 ] and DINOSAUR [ 33 ] , show large performance fluctuations as $K$ varies. By contrast, $K$ -adaptive methods do not rely on a carefully tuned $K$ . Our method substantially outperforms existing $K$ -adaptive baselines, including MetaSlot [ 26 ] and AdaSlot [ 16 ] , and even surpasses strong $K$ -fixed baselines.

Figure 2: Framework of Quality-Guided $K$ -Adaptive Slot Attention (QASA). The overall training pipeline follows the canonical Slot Attention architecture: an image is encoded by the encoder, fed into the Slot Attention module, and then decoded; the reconstruction loss is computed against embeddings produced by a frozen encoder. The key difference is that we compute a slot-quality metric from the Slot Attention maps $A^{\text{slot}}$ and use it to select a subset of slots, allowing only the selected slots to participate in decoding. At inference, no slot selection is applied. All slots compete via $A^{\text{slot}}$ for each token, yielding a $K$ -adaptive result.

Figure 3: Visualizations on COCO. The MetaSlot examples of AdaSlot [ 16 ] and MetaSlot [ 26 ] are generated using the released checkpoint. ”SPOT-7” and ”SPOT-20” denote SPOT [ 20 ] with $K=7$ and $K=20$ , respectively. The SPOT-7 examples are generated using the released checkpoint. The SPOT-20 examples are generated by training a model under the same settings as in the original paper.

			COCO		VOC		MOVi-C	MOVi-E
Method	Dec.	$K$ -type	mBOi	mIoU	mBOi	mIoU	mBOi	mBOi
AdaSlot [ 16 ]	MLP	adaptive	27.4	–	–	–	35.6	29.8
MetaSlot [ 26 ]	MLP	adaptive	29.5	27.9	43.9	42.1	35.0	–
QASA	Trans.	adaptive	36.7	35.0	49.7	47.9	46.9	39.1
QASA ${}_{\text{MLP}}$	MLP	adaptive	33.6	32.5	47.3	45.5	42.2	34.6

Table 1: Comparison of

K

-adaptive methods. Results for AdaSlot and MetaSlot are taken from their original papers [ 16 , 26 ] . Dashes indicate results not reported.

			COCO			VOC			MOVi-C		MOVi-E
Method	Dec.	$K$ -type	mBOc	mBOi	mIoU	mBOc	mBOi	mIoU	mBOi	mIoU	mBOi	mIoU
SLATE [ 34 ]	–	–	33.6	29.1	–	41.5	35.9	–	39.4	37.8	30.2	28.6
DINOSAUR [ 33 ]	Trans.	fixed	39.7	31.6	–	51.2	44.0	–	42.4	–	–	–
DINOSAUR ${}_{\text{MLP}}$ [ 33 ]	MLP	fixed	30.9	27.7	–	40.9	39.5	–	39.1	–	35.5	–
SPOT [ 20 ]	Trans.	fixed	44.7	35.0	33.0	55.6	48.3	–	47.3	46.7	40.1	39.3
SPOT+FS+RC [ 36 ]	Trans.	fixed	45.3	35.7	–	56.5	49.3	–	49.0	47.8	–	–

Table 2: Comparison with

K

-fixed methods on COCO [ 25 ] , PASCAL VOC [ 15 ] , and MOVi-C/E [ 17 ] . Results for SLATE, DINOSAUR, DINOSAUR

{}_{\text{MLP}}

, and SPOT are taken from SPOT [ 20 ] . Results for the remaining methods are taken from their original papers [ 36 ] . Dashes indicate results not reported.

Figure 4: Visualizations on MOVi-C/E. The AdaSlot examples are taken from its original paper [ 16 ] . the SPOT examples are generated by training a model under the same settings as in the original paper.

			MLP predictor				Linear predictor
Method	Dec.	$K$ -type	class-top1	class-top5	$R^{2}$ -X	$R^{2}$ -Y	class-top1	class-top5	$R^{2}$ -X	$R^{2}$ -Y
DINOSAUR [ 33 ]	Trans.	fixed	47.1	75.5	55.4	59.1	39.7	68.0	48.8	52.0
DINOSAUR ${}_{\text{MLP}}$ [ 33 ]	MLP	fixed	46.9	75.4	62.9	63.3	39.1	67.5	59.2	59.9
SPOT [ 20 ]	Trans.	fixed	45.9	72.7	51.9	56.4	45.2	72.1	49.2	53.4
AdaSlot [ 16 ]	MLP	adaptive	49.3	79.0	72.7	69.8	33.9	66.3	58.6	53.3
MetaSlot [ 26 ]	MLP	adaptive	40.9	70.0	55.0	55.3	37.9	66.7	52.0	53.2

Table 3: Object property prediction results. We report classification accuracy and

R^{2}

scores using an MLP predictor and a linear predictor. DINOSAUR [ 33 ] and MetaSlot [ 26 ] are trained with their official code. SPOT [ 20 ] and AdaSlot [ 16 ] are evaluated using slots extracted from their official checkpoints. All baselines use the same backbone and evaluation setup as our model.

Table 8

Figure 5: Influence of $\rho$ , $\tau$ and $\mu$ . All results are evaluated on MOVi-C.

MOVi-C	$K_{\max}$	15	18	20	22	24	32
	mBOi	44.4	46.5	46.9	46.4	46.3	45.4
	mIoU	43.4	45.7	46.1	45.6	45.7	45.0
MOVi-E	$K_{\max}$	24	28	30	32	34	64
	mBOi	38.3	39.1	39.1	39.3	39.5	38.7
	mIoU	36.8	37.8	37.8	38.0	38.3	38.3

Table 6: Effect of

K_{\max}

on MOVi-C and MOVi-E [ 17 ] .

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: Object number distribution on COCO and MOVi-C/E.

Figure 7: Active slot count distribution.

Figure 8: Slot-Quality distribution on COCO.

Method	Train time	Train space	Eval time
SPOT	5m 27s	15.8 GiB	30 s
Ours	5m 47s	17.2 GiB	32 s

Appendix

Table 7: Cost comparison. We report time and per-GPU memory usage for 1-epoch COCO training on 4x RTX 4090s.

Figure 9: Additional examples of QASA on COCO.

Figure 10: Additional examples of QASA on PASCAL VOC.

Figure 11: Additional examples of QASA on MOVi-C.

Figure 12: Additional examples of QASA on MOVi-E.

Object-Centric Representation Learning

Object-Centric Representation Learning studies visual models that organize scenes into distinct objects and their properties, positions, and relations.

See all 93 papers

When Slots Compete: Slot Merging in Object-Centric Learning
Mar 11, 2026Christos Chatzisavvas, Panagiotis Rigas, George Ioannakis +2Object-Centric Representation Learning Slot Attention
Department of Electrical and Computer Engineering, Democritus University of Thrace, Greece · Institute for Language and Speech Processing, Athena Research Center, Greece · Department of Informatics & Telecommunications, National and Kapodistrian University of Athens, Greece +1
Understanding Clustering in Slot Attention via Particle Dynamics
Oct 3, 2026Vasudev Joy, Rajat Rasal, Avinash Kori +2Slot Attention Object-Centric Representation Learning
Imperial College London
Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning
Jun 10, 2026Sieu Tran, Duc Nguyen, Hao Vo +2Object-Centric Representation Learning Video Object-Centric Learning
University of Arkansas, Fayetteville, AR, USA

Mar 11, 2026J/K move · Enter open · S save

When Slots Compete: Slot Merging in Object-Centric Learning

Christos Chatzisavvas, Panagiotis Rigas, George Ioannakis, Vassilis Katsouros+1

Department of Electrical and Computer Engineering, Democritus University of Thrace, Greece · Institute for Language and Speech Processing, Athena Research Center, Greece · Department of Informatics & Telecommunications, National and Kapodistrian University of Athens, Greece+1

Object-Centric Representation Learning Slot Attention Unsupervised Image Segmentation

Open paper AskPDF arXiv

Slot-based object-centric learning represents an image as a set of latent slots with a decoder that combines them into an image or features. The decoder specifies how slots are combined into an output, but the slot set is typically fixed: the number of slots is chosen upfront and slots are only refined. This can lead to multiple slots competing for overlapping regions of the same entity rather than focusing on distinct regions. We introduce slot merging: a drop-in, lightweight operation on the slot set that merges overlapping slots during training. We quantify overlap with a Soft-IoU score between slot-attention maps and combine selected pairs via a barycentric update that preserves gradient flow. Merging follows a fixed policy, with the decision threshold inferred from overlap statistics, requiring no additional learnable modules. Integrated into the established feature-reconstruction pipeline of DINOSAUR, the proposed method improves object factorization and mask quality, surpassing other adaptive methods in object discovery and segmentation benchmarks.

Abstract

Object-Centric Representation Learning

Explore similar work

When Slots Compete: Slot Merging in Object-Centric Learning

Understanding Clustering in Slot Attention via Particle Dynamics

Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning