Related papers: Knowledge is Never Enough: Towards Web Aided Deep …
Most object detectors operate under a closed-world assumption, recognizing only the classes annotated in the training dataset and failing when encountering novel objects. Open-World Object Detection (OWOD) relaxes this assumption by…
The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that…
Image classification methods are usually trained to perform predictions taking into account a predefined group of known classes. Real-world problems, however, may not allow for a full knowledge of the input and label spaces, making failures…
We investigate the use of deep neural networks for the novel task of class generic object detection. We show that neural networks originally designed for image recognition can be trained to detect objects within images, regardless of their…
Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data,…
Open World Object Detection(OWOD) addresses realistic scenarios where unseen object classes emerge, enabling detectors trained on known classes to detect unknown objects and incrementally incorporate the knowledge they provide. While…
Despite the remarkable progress in recent years, detecting objects in a new context remains a challenging task. Detectors learned from a public dataset can only work with a fixed list of categories, while training from scratch usually…
In robot sensing scenarios, instead of passively utilizing human captured views, an agent should be able to actively choose informative viewpoints of a 3D object as discriminative evidence to boost the recognition accuracy. This task is…
Selection of appropriate tools and use of them when performing daily tasks is a critical function for introducing robots for domestic applications. In previous studies, however, adaptability to target objects was limited, making it…
Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training. However, in the dynamic world, new or unseen class examples may appear constantly. A model working in such…
Humans leverage multiple sensor modalities when interacting with objects and discovering their intrinsic properties. Using the visual modality alone is insufficient for deriving intuition behind object properties (e.g., which of two boxes…
Deep learning's success in perception, natural language processing, etc. inspires hopes for advancements in autonomous robotics. However, real-world robotics face challenges like variability, high-dimensional state spaces, non-linear…
Although deep learning has made significant progress on fixed large-scale datasets, it typically encounters challenges regarding improperly detecting unknown/unseen classes in the open-world scenario, over-parametrized, and overfitting…
Adversarial attacks can easily fool object recognition systems based on deep neural networks (DNNs). Although many defense methods have been proposed in recent years, most of them can still be adaptively evaded. One reason for the weak…
Tremendous progress in deep learning over the last years has led towards a future with autonomous vehicles on our roads. Nevertheless, the performance of their perception systems is strongly dependent on the quality of the utilized training…
How can a robot quickly identify and recognize new objects shown to it during a human demonstration? Existing closed-set object detectors frequently fail at this because the objects are out-of-distribution. While open-set detectors (e.g.,…
In this paper, we propose a concept learning architecture that enables a robot to build symbols through self-exploration by interacting with a varying number of objects. Our aim is to allow a robot to learn concepts without constraints,…
Deep learning has recently demonstrated its ability to rival the human brain for visual object recognition. As datasets get larger, a natural question to ask is if existing deep learning architectures can be extended to handle the 50+K…
Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships among objects remains a challenging task.…
One of the challenges of full autonomy is to have a robot capable of manipulating its current environment to achieve another environment configuration. This paper is a step towards this challenge, focusing on the visual understanding of the…