Related papers: Classifying Novel 3D-Printed Objects without Retra…

The state of the art in human-centric computer vision achieves high accuracy and robustness across a diverse range of tasks. The most effective models in this domain have billions of parameters, thus requiring extremely large datasets,…

Current 3D scene segmentation methods are heavily dependent on manually annotated 3D training datasets. Such manual annotations are labor-intensive, and often lack fine-grained details. Importantly, models trained on this data typically…

While state-of-the-art general object detectors are getting better and better, there are not many systems specifically designed to take advantage of the instance detection problem. For many applications, such as household robotics, a system…

Object-based Novelty Detection (ND) aims to identify unknown objects that do not belong to classes seen during training by an object detection model. The task is particularly crucial in real-world applications, as it allows to avoid…

Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training…

We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…

Large-scale pre-training holds the promise to advance 3D medical object detection, a crucial component of accurate computer-aided diagnosis. Yet, it remains underexplored compared to segmentation, where pre-training has already demonstrated…

Creating computer vision datasets requires careful planning and lots of time and effort. In robotics research, we often have to use standardized objects, such as the YCB object set, for tasks such as object tracking, pose estimation,…

Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information. Though this issue can be…

Creative processes such as painting often involve creating different components of an image one by one. Can we build a computational model to perform this task? Prior works often fail by making global changes to the image, inserting objects…

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a…

Re-ranking is the second stage of a visual place recognition task, in which the system chooses the best-matching images from a pre-selected subset of candidates. Model-free approaches compute the image pair similarity based on a spatial…

While today's robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably see new objects in unconstrained settings, and thus will…

Object recognition is a key function in both human and machine vision. While recent studies have achieved fMRI decoding of seen and imagined contents, the prediction is limited to training examples. We present a decoding approach for…

The task of detecting 3D objects is important to various robotic applications. The existing deep learning-based detection techniques have achieved impressive performance. However, these techniques are limited to run with a graphics…

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…

Recent advancements in Artificial intelligence, especially deep learning, has changed many fields irreversibly by introducing state of the art methods for automation. Construction monitoring has not been an exception; as a part of…

Noninvasive optical imaging modalities can probe patient's tissue in 3D and over time generate gigabytes of clinically relevant data per sample. There is a need for AI models to analyze this data and assist clinical workflow. The lack of…

Training object class detectors typically requires a large set of images in which objects are annotated by bounding-boxes. However, manually drawing bounding-boxes is very time consuming. We propose a new scheme for training object…

We present an end-to-end framework for fast retraining of object detection models in human-robot-collaboration. Our Faster R-CNN based setup covers the whole workflow of automatic image generation and labeling, model retraining on-site as…