相关论文: Improving Object-centric Learning with Query Optim…

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…

Developing deep learning models that effectively learn object-centric representations, akin to human cognition, remains a challenging task. Existing approaches facilitate object discovery by representing objects as fixed-size vectors,…

Learning object-centric representations from complex natural environments enables both humans and machines with reasoning abilities from low-level perceptual features. To capture compositional entities of the scene, we proposed cyclic walks…

A central goal in AI is to represent scenes as compositions of discrete objects, enabling fine-grained, controllable image and video generation. Yet leading diffusion models treat images holistically and rely on text conditioning, creating…

Unsupervised video segmentation is a challenging computer vision task, especially due to the lack of supervisory signals coupled with the complexity of visual scenes. To overcome this challenge, state-of-the-art models based on slot…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot product between query…

Object-centric learning (OCL) aims to learn representations of individual objects within visual scenes without manual supervision, facilitating efficient and effective visual reasoning. Traditional OCL methods primarily employ bottom-up…

We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objects evolve over…

Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on learning image representation combining local and global…

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…

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Slot attention is a powerful method for object-centric modeling in images and videos. However, its set-equivariance limits its ability to handle videos with a dynamic number of objects because it cannot break ties. To overcome this…

Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which are not observed during the training phase. The existing body of works on ZSL mostly relies on pretrained visual features and lacks the explicit attribute localisation…

Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that…

Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization,…

Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class). Common to all of these approaches is the assumption that…

Unsupervised video Object-Centric Learning (OCL) is promising as it enables object-level scene representation and understanding as we humans do. Mainstream video OCL methods adopt a recurrent architecture: An aggregator aggregates current…

Object-centric representation learning has recently been successfully applied to real-world datasets. This success can be attributed to pretrained non-object-centric foundation models, whose features serve as reconstruction targets for slot…

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…