相关论文: Unsupervised Object Keypoint Learning using Local …

Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder…

While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important. Recognizing object parts and attributes has been extensively studied before, yet…

Most existing approaches to training object detectors rely on fully supervised learning, which requires the tedious manual annotation of object location in a training set. Recently there has been an increasing interest in developing weakly…

Extracting informative representations from videos is fundamental for effectively learning various downstream tasks. We present a novel approach for unsupervised learning of meaningful representations from videos, leveraging the concept of…

Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of…

This paper describes recent developments in object specific pose and shape prediction from single images. The main contribution is a new approach to camera pose prediction by self-supervised learning of keypoints corresponding to locations…

We focus on the task of future frame prediction in video governed by underlying physical dynamics. We work with models which are object-centric, i.e., explicitly work with object representations, and propagate a loss in the latent space.…

Prediction is a fundamental capability of all living organisms, and has been proposed as an objective for learning sensory representations. Recent work demonstrates that in primate visual systems, prediction is facilitated by neural…

Adaptive control for real-time manipulation requires quick estimation and prediction of object properties. While robot learning in this area primarily focuses on using vision, many tasks cannot rely on vision due to object occlusion. Here,…

This paper proposes a method to ease the unsupervised learning of object landmark detectors. Similarly to previous methods, our approach is fully unsupervised in a sense that it does not require or make any use of annotated landmarks for…

While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this in scenarios where annotating data is…

We present a novel unsupervised framework for instance-level image-to-image translation. Although recent advances have been made by incorporating additional object annotations, existing methods often fail to handle images with multiple…

In the Vision-and-Language Navigation task, the embodied agent follows linguistic instructions and navigates to a specific goal. It is important in many practical scenarios and has attracted extensive attention from both computer vision and…

We characterize the problem of pose estimation for rigid objects in terms of determining viewpoint to explain coarse pose and keypoint prediction to capture the finer details. We address both these tasks in two different settings - the…

A visual system has to learn both which features to extract from images and how to group locations into (proto-)objects. Those two aspects are usually dealt with separately, although predictability is discussed as a cue for both. To…

Incorporating domain-specific priors in search and navigation tasks has shown promising results in improving generalization and sample complexity over end-to-end trained policies. In this work, we study how object embeddings that capture…

A key challenge in fine-grained recognition is how to find and represent discriminative local regions. Recent attention models are capable of learning discriminative region localizers only from category labels with reinforcement learning.…

We propose KeypointGAN, a new method for recognizing the pose of objects from a single image that for learning uses only unlabelled videos and a weak empirical prior on the object poses. Video frames differ primarily in the pose of the…

We present a new technique for deep reinforcement learning that automatically detects moving objects and uses the relevant information for action selection. The detection of moving objects is done in an unsupervised way by exploiting…

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…