Related papers: ESC: Exploration with Soft Commonsense Constraints…
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…
Identifying user intents from natural language utterances is a crucial step in conversational systems that has been extensively studied as a supervised classification problem. However, in practice, new intents emerge after deploying an…
Zero-shot learning deals with the ability to recognize objects without any visual training sample. To counterbalance this lack of visual data, each class to recognize is associated with a semantic prototype that reflects the essential…
Small aerial robots are particularly well-suited for search and rescue in confined and hazardous environments due to their agility, low cost, and ability to traverse through cluttered spaces that are inaccessible to larger platforms.…
Visual language navigation (VLN) is an embodied task demanding a wide range of skills encompassing understanding, perception, and planning. For such a multifaceted challenge, previous VLN methods totally rely on one model's own thinking to…
Recent advancements in 3D object detection and novel category detection have made significant progress, yet research on learning generalized 3D objectness remains insufficient. In this paper, we delve into learning open-world 3D objectness,…
Zero-Shot Object Navigation (ZSON) requires agents to navigate to objects specified via open-ended natural language without predefined categories or prior environmental knowledge. While recent methods leverage foundation models or…
Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes…
Effective communication is an important skill for enabling information exchange in multi-agent settings and emergent communication is now a vibrant field of research, with common settings involving discrete cheap-talk channels. Since, by…
Cooperative visual semantic navigation is a foundational capability for aerial robot teams operating in unknown environments. However, achieving robust open-vocabulary object-goal navigation remains challenging due to the computational…
Exploration in an unknown environment is the core functionality for mobile robots. Learning-based exploration methods, including convolutional neural networks, provide excellent strategies without human-designed logic for the feature…
Few-shot Learning (FSL) aims to classify new concepts from a small number of examples. While there have been an increasing amount of work on few-shot object classification in the last few years, most current approaches are limited to images…
Object detection is a critical field in computer vision focusing on accurately identifying and locating specific objects in images or videos. Traditional methods for object detection rely on large labeled training datasets for each object…
Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…
Detecting novel objects without class information is not trivial, as it is difficult to generalize from a small training set. This is an interesting problem for underwater robotics, as modeling marine objects is inherently more difficult in…
Inspired by the human ability to perform complex manipulation in the complete absence of vision (like retrieving an object from a pocket), the robotic manipulation field is motivated to develop new methods for tactile-based object…
Learning to infer labels in an open world, i.e., in an environment where the target "labels" are unknown, is an important characteristic for achieving autonomy. Foundation models pre-trained on enormous amounts of data have shown remarkable…
Navigating unfamiliar environments presents significant challenges for household robots, requiring the ability to recognize and reason about novel decoration and layout. Existing reinforcement learning methods cannot be directly transferred…
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also…
Spatial memory, or the ability to remember and recall specific locations and objects, is central to autonomous agents' ability to carry out tasks in real environments. However, most existing artificial memory modules are not very adept at…