computer-vision-10

Object Discovery

3260 papers • 126 benchmarks • 313 datasets

Object Discovery is the task of identifying previously unseen objects. Source: Unsupervised Object Discovery and Segmentation of RGBD-images

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in object-discovery-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find object-discovery-10 models and implementations

Datasets

UVO

ShapeStacks

Subtasks

No subtasks available.

Most implemented papers

Object-Centric Learning with Slot Attention

Francesco Locatello, Thomas Unterthiner, Alexey Dosovitskiy, Jakob Uszkoreit, Dirk Weissenborn, G. Heigold, Aravindh Mahendran, Thomas Kipf•Thu Jun 25 2020

An architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention is presented.

Content

1027

0

Paper Graph

MONet: Unsupervised Scene Decomposition and Representation

M. Botvinick, Christopher P. Burgess, L. Matthey, Nicholas Watters, Rishabh Kabra, I. Higgins, Alexander Lerchner•Mon Jan 21 2019

The Multi-Object Network (MONet) is developed, which is capable of learning to decompose and represent challenging 3D scenes into semantically meaningful components, such as objects and background elements.

574 0

Paper Graph

GuessWhat?! Visual Object Discovery through Multi-modal Dialogue

H. Larochelle, Aaron C. Courville, O. Pietquin, H. D. Vries, Florian Strub, A. Chandar•Tue Nov 22 2016

This work introduces GuessWhat?

436 0

Paper Graph

Learn To Pay Attention

Philip H. S. Torr, Namhoon Lee, Nicholas A. Lord, Saumya Jetley•Wed Feb 14 2018

An end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification that is able to bootstrap standard CNN architectures for the task of image classification, demonstrating superior generalisation over 6 unseen benchmark datasets.

463 0

Paper Graph

Learning Open-World Object Proposals without Learning to Classify

Tsung-Yi Lin, In-So Kweon, Weicheng Kuo, A. Angelova, Dahun Kim•Sat Aug 14 2021

A classification-free Object Localization Network (OLN) is proposed which estimates the objectness of each region purely by how well the location and shape of a region overlap with any ground-truth object.

155 0

Paper Graph

Efficient Dialog Policy Learning via Positive Memory Retention

Volker Tresp, Rui Zhao•Mon Oct 01 2018

This paper describes an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency and shows state-of-the-art performance in a real-word visual object discovery game.

10 0

Paper Graph

Vision Transformers Need Registers

Piotr Bojanowski, J. Mairal, Timothée Darcet, Maxime Oquab•Wed Sep 27 2023

This paper identifies and characterize artifacts in feature maps of both supervised and self-supervised ViT networks, and proposes a simple yet effective solution based on providing additional tokens to the input sequence of the Vision Transformer to fill that role.

639 0

Paper Graph

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

I. Posner, Martin Engelcke, Adam R. Kosiorek, Oiwi Parker Jones•Mon Jul 29 2019

Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, decompose scenes into objects in an unsupervised fashion. Their underlying generative processes, however, do not account for component interactions. Hence, neither of them allows for principled sampling of novel scenes. Here we present GENESIS, the first object-centric generative model of 3D visual scenes capable of both decomposing and generating scenes by capturing relationships between scene components. GENESIS parameterises a spatial GMM over images which is decoded from a set of object-centric latent variables that are either inferred sequentially in an amortised fashion or sampled from an autoregressive prior. We train GENESIS on several publicly available datasets and evaluate its performance on scene generation, decomposition, and semi-supervised learning.

327 0

Paper Graph

Localizing Objects with Self-Supervised Transformers and no Labels

P. P'erez, J. Ponce, Huy V. Vo, Renaud Marlet, Oriane Siméoni, Gilles Puy, Spyros Gidaris, Andrei Bursuc, Simon Roburin•Tue Sep 28 2021

This work proposes a simple approach, LOST, that leverages the activation features of a vision transformer pre-trained in a self-supervised manner, that outperform state-of-the-art object discovery methods by up to 8 CorLoc points on PASCAL VOC 2012.

253 0

Paper Graph

Unsupervised Image Decomposition with Phase-Correlation Networks

Sven Behnke, Angel Villar-Corrales•Wed Oct 06 2021

The Phase-Correlation Decomposition Network (PCDNet), a novel model that decomposes a scene into its object components, which are represented as transformed versions of a set of learned object prototypes, is proposed.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.