About
Object Discovery is the task of identifying previously unseen objects.
Source: Unsupervised Object Discovery and Segmentation of RGBD-images
Benchmarks
Datasets
Greatest papers with code
Object-Centric Learning with Slot Attention
NeurIPS 2020
• google-research/google-research
• 
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features.
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms.
MONet: Unsupervised Scene Decomposition and Representation
• deepmind/multi_object_datasets
•
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.
GuessWhat?! Visual object discovery through multi-modal dialogue
CVPR 2017
• GuessWhatGame/guesswhat
•
Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
Entity Abstraction in Visual Model-Based Reinforcement Learning
• jcoreyes/OP3
• 
This paper tests the hypothesis that modeling a scene in terms of entities and their local interactions, as opposed to modeling the scene globally, provides a significant benefit in generalizing to physical tasks in a combinatorial space the learner has not encountered before.
LATENT VARIABLE MODELS MODEL-BASED REINFORCEMENT LEARNING OBJECT DISCOVERY UNSUPERVISED REPRESENTATION LEARNING VARIATIONAL INFERENCE VIDEO PREDICTION
Reconstruction Bottlenecks in Object-Centric Generative Models
A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision.
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
ICLR 2020
• applied-ai-lab/genesis
•
Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning.
Ranked #1 on
Image Generation
on Multi-dSprites
IMAGE GENERATION LATENT VARIABLE MODELS OBJECT DISCOVERY REPRESENTATION LEARNING SCENE GENERATION UNSUPERVISED IMAGE SEGMENTATION UNSUPERVISED OBJECT SEGMENTATION
Deep Patch Learning for Weakly Supervised Object Classification and Discovery
Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background.
CLASSIFICATION MULTIPLE INSTANCE LEARNING OBJECT CLASSIFICATION OBJECT DISCOVERY
Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video
We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform.
Unsupervised Layered Image Decomposition into Object Prototypes
We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models.