Object Discovery
Leaderboards
Greatest papers with code
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.
Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery
To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes.
3D SEMANTIC INSTANCE SEGMENTATION 3D VOLUMETRIC RECONSTRUCTION OBJECT DISCOVERY
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.
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.
Mining Objects: Fully Unsupervised Object Discovery and Localization From a Single Image
To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pre-trained convolutional neural networks (CNNs).
Learn To Pay Attention
ICLR 2018
• caoquanjie/LearnToPayAttention
•
We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification.
Ego-Object Discovery
Given an egocentric video/images sequence acquired by the camera, our algorithm uses both the appearance extracted by means of a convolutional neural network and an object refill methodology that allows to discover objects even in case of small amount of object appearance in the collection of images.
StampNet: unsupervised multi-class object discovery
Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background.
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 Deep Visual Object Models From Noisy Web Data: How to Make it Work
We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy.