SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
Ioannis Kakogeorgiou, Spyros Gidaris, Konstantinos Karantzalos, Nikos Komodakis
2024Year
27Top-tier citations
Abstract
4 IACM-Forth 5 Archimedes/Athena RC Figure 1. SPOT: Our novel framework enhances unsupervised object-centric learning in slot-based autoencoders using self-training and sequence permutations in the transformer decoder. It improves object-specific slot generation, excelling in complex real-world images.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 35ea967e-d59b-4310-bc74-2cbdaf5113c1Cited by top-tier papers27
- DINO-Foresight: Looking into the Future with DINOEfstathios Karypidis, Ioannis Kakogeorgiou, Spyridon Gidaris, Nikos KomodakisNeurIPS 2025 · 52 citations
- Multi-Token Prediction Needs RegistersAnastasios Gerontopoulos, Spyridon Gidaris, Nikos KomodakisNeurIPS 2025 · 13 citations
- Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics ModelingTal Daniel, Carl Qi, Dan Haramati, Amir Zadeh et al.ICLR 2026 · 12 citations
- MetaSlot: Break Through the Fixed Number of Slots in Object-Centric LearningHongjia Liu, Rongzhen Zhao, Haohan Chen, Joni PajarinenNeurIPS 2025 · 12 citations
- Identifiable Object-Centric Representation Learning via Probabilistic Slot AttentionAvinash Kori, Francesco Locatello, Ainkaran Santhirasekaram, Francesca Toni et al.NeurIPS 2024 · 11 citations
Builds on40
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou et al.ICCV 2021 · 8,921 citations
- An Empirical Study of Training Self-Supervised Vision TransformersXinlei Chen, Saining Xie, Kaiming HeICCV 2021 · 2,340 citations
- Generative Pretraining From PixelsMark Chen, Alec Radford, Rewon Child, Jeffrey Wu et al.ICML 2020 · 1,773 citations
Related papers
- Adaptive Slot Attention: Object Discovery with Dynamic Slot NumberKe Fan, Zechen Bai, Tianjun Xiao, Tong He et al.CVPR 2024
- SlotDiffusion: Object-Centric Generative Modeling with Diffusion ModelsZiyi Wu, Jingyu Hu, Wuyue Lu, Igor Gilitschenski et al.NeurIPS 2023 · 106 citations
- Learning to Compose: Improving Object Centric Learning by Injecting CompositionalityWhie Jung, Jaehoon Yoo, Sungjin Ahn, Seunghoon HongICLR 2024 · 10 citations
- Illiterate DALL-E Learns to ComposeGautam Singh, Fei Deng, Sungjin AhnICLR 2022 · 182 citations
- From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric LearningHyun Seok Seong, WonJun Moon, Jae-Pil HeoICLR 2026 · 5 citations
