Object Discovery
50 papers with code • 0 benchmarks • 2 datasets
Object Discovery is the task of identifying previously unseen objects.
Source: Unsupervised Object Discovery and Segmentation of RGBD-images
Benchmarks
These leaderboards are used to track progress in Object Discovery
Most implemented papers
Object-Centric Learning with Slot Attention
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features.
MONet: Unsupervised Scene Decomposition and Representation
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.
Learn To Pay Attention
We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification.
GuessWhat?! Visual object discovery through multi-modal dialogue
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.
Efficient Dialog Policy Learning via Positive Memory Retention
This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning.
Learning Open-World Object Proposals without Learning to Classify
In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
Localizing Objects with Self-Supervised Transformers and no Labels
We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points.
Unsupervised Image Decomposition with Phase-Correlation Networks
The ability to decompose scenes into their object components is a desired property for autonomous agents, allowing them to reason and act in their surroundings.
What Matters For Meta-Learning Vision Regression Tasks?
To this end, we (i) exhaustively evaluate common meta-learning techniques on these tasks, and (ii) quantitatively analyze the effect of various deep learning techniques commonly used in recent meta-learning algorithms in order to strengthen the generalization capability: data augmentation, domain randomization, task augmentation and meta-regularization.
Unsupervised Domain Adaptation for Nighttime Aerial Tracking
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications.