Related papers: Grounded Object Centric Learning
The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes. However, despite the high expressiveness of diffusion models in…
The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning. In the recent culmination of unsupervised object-centric learning, the Slot-Attention module has…
Contrastive, self-supervised learning of object representations recently emerged as an attractive alternative to reconstruction-based training. Prior approaches focus on contrasting individual object representations (slots) against one…
Several accounts of human cognition posit that our intelligence is rooted in our ability to form abstract composable concepts, ground them in our environment, and reason over these grounded entities. This trifecta of human thought has…
Unsupervised video object segmentation aims to segment the most prominent object in a video sequence. However, the existence of complex backgrounds and multiple foreground objects make this task challenging. To address this issue, we…
Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object-centric representations have raised growing interest. In…
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…
Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL…
Object-centric learning (OCL) aspires general and compositional understanding of scenes by representing a scene as a collection of object-centric representations. OCL has also been extended to multi-view image and video datasets to apply…
Learning a latent dynamics model provides a task-agnostic representation of an agent's understanding of its environment. Leveraging this knowledge for model-based reinforcement learning (RL) holds the potential to improve sample efficiency…
Object-centric understanding is fundamental to human vision and required for complex reasoning. Traditional methods define slot-based bottlenecks to learn object properties explicitly, while recent self-supervised vision models like DINO…
Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder…
Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limiting robustness and contractility in manipulation tasks. We propose STORM (Slot-based…
Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…
Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision. Despite its object-centric binding ability brought by compositional modelling, as a…
Object-centric slot attention is an emerging paradigm for unsupervised learning of structured, interpretable object-centric representations (slots). This enables effective reasoning about objects and events at a low computational cost and…
Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require features that are jointly informative across clients while…
Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features…
Humans excel at abstracting data and constructing \emph{reusable} concepts, a capability lacking in current continual learning systems. The field of object-centric learning addresses this by developing abstract representations, or slots,…
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant…