Related papers: Unsupervised Object Learning via Common Fate

We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object instances. We propose criteria…

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…

Perceiving a scene most fully requires all the senses. Yet modeling how objects look and sound is challenging: most natural scenes and events contain multiple objects, and the audio track mixes all the sound sources together. We propose to…

We address the problem of learning self-supervised representations from unlabeled image collections. Unlike existing approaches that attempt to learn useful features by maximizing similarity between augmented versions of each input image or…

Scene Graphs are widely applied in computer vision as a graphical representation of relationships between objects shown in images. However, these applications have not yet reached a practical stage of development owing to biased training…

In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo…

Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain…

Research in scene graph generation has quickly gained traction in the past few years because of its potential to help in downstream tasks like visual question answering, image captioning, etc. Many interesting approaches have been proposed…

Annotating a large number of training images is very time-consuming. In this background, this paper focuses on learning from easy-to-acquire web data and utilizes the learned model for fine-grained image classification in labeled datasets.…

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…

Scene graph generation models understand the scene through object and predicate recognition, but are prone to mistakes due to the challenges of perception in the wild. Perception errors often lead to nonsensical compositions in the output…

Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions. In this…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning. Most of the previous models have been shown to work only on scenes with a few objects. In this…

Object Permanence allows people to reason about the location of non-visible objects, by understanding that they continue to exist even when not perceived directly. Object Permanence is critical for building a model of the world, since…

Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets. However, manually labeling viewpoints is notoriously hard, error-prone, and time-consuming. On the other hand, it is relatively…

Semi-supervised learning (SSL) aims to train a machine learning model using both labelled and unlabelled data. While the unlabelled data have been used in various ways to improve the prediction accuracy, the reason why unlabelled data could…

In this thesis we discuss architectural designs and training methods for a neural network to have the ability of dissecting an image into objects of interest without supervision. The main challenge in 2D unsupervised object segmentation is…

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…

To help agents reason about scenes in terms of their building blocks, we wish to extract the compositional structure of any given scene (in particular, the configuration and characteristics of objects comprising the scene). This problem is…