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

Most implemented papers

Object-Centric Learning with Slot Attention

google-research/google-research NeurIPS 2020

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

deepmind/multi_object_datasets 22 Jan 2019

The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.

Learn To Pay Attention

SaoYan/LearnToPayAttention ICLR 2018

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

GuessWhatGame/guesswhat CVPR 2017

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

ruizhaogit/MNIST-GuessNumber 2 Oct 2018

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

mcahny/object_localization_network 15 Aug 2021

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

valeoai/LOST 29 Sep 2021

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

angelvillar96/Unsupervised-Decomposition-PCDNet-1 7 Oct 2021

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?

boschresearch/what-matters-for-meta-learning CVPR 2022

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

vision4robotics/udat CVPR 2022

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.