Related papers: Self-Supervised Velocity Estimation for Automotive…

When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a…

Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data. This paper studies how to automatically fine-tune a pre-existing object detector while exploring…

We present our approach to unsupervised domain adaptation for single-stage object detectors on top-view grid maps in automated driving scenarios. Our goal is to train a robust object detector on grid maps generated from custom sensor data…

Optical aerial images change detection is an important task in earth observation and has been extensively investigated in the past few decades. Generally, the supervised change detection methods with superior performance require a large…

Although visual navigation has been extensively studied using deep reinforcement learning, online learning for real-world robots remains a challenging task. Recent work directly learned from offline dataset to achieve broader generalization…

In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train…

This paper introduces a novel perception framework that has the ability to identify and track objects in autonomous vehicle's field of view. The proposed algorithms don't require any training for achieving this goal. The framework makes use…

In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…

A major bottleneck to scaling-up training of self-driving perception systems are the human annotations required for supervision. A promising alternative is to leverage "auto-labelling" offboard perception models that are trained to…

Accurate identification of important objects in the scene is a prerequisite for safe and high-quality decision making and motion planning of intelligent agents (e.g., autonomous vehicles) that navigate in complex and dynamic environments.…

Training of object detection models using less data is currently the focus of existing N-shot learning models in computer vision. Such methods use object-level labels and takes hours to train on unseen classes. There are many cases where we…

The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of…

Accurate object segmentation is a crucial task in the context of robotic manipulation. However, creating sufficient annotated training data for neural networks is particularly time consuming and often requires manual labeling. To this end,…

Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera…

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

The capability to detect objects is a core part of autonomous driving. Due to sensor noise and incomplete data, perfectly detecting and localizing every object is infeasible. Therefore, it is important for a detector to provide the amount…

Obstacle Detection is a central problem for any robotic system, and critical for autonomous systems that travel at high speeds in unpredictable environment. This is often achieved through scene depth estimation, by various means. When fast…

This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1…

In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection. Our method directly trained on unlabeled non-iconic image dataset like COCO, instead of commonly used iconic-object image…