Related papers: Learning Instance Representation Banks for Aerial …

Box-supervised instance segmentation has recently attracted lots of research efforts while little attention is received in aerial image domain. In contrast to the general object collections, aerial objects have large intra-class variances…

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to…

We tackle the problem of learning an implicit scene representation for 3D instance segmentation from a sequence of posed RGB images. Towards this, we introduce 3DIML, a novel framework that efficiently learns a neural label field which can…

Multiple-instance learning (MIL) has served as an important tool for a wide range of vision applications, for instance, image classification, object detection, and visual tracking. In this paper, we propose a novel method to solve the…

Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those…

Humans have a natural ability to perform semantic associations with the surrounding objects in the environment. This allows them to create a mental map of the environment, allowing them to navigate on-demand when given linguistic…

Training the multi-label image recognition models with partial labels, in which merely some labels are known while others are unknown for each image, is a considerably challenging and practical task. To address this task, current algorithms…

Existing open set recognition (OSR) methods are typically designed for static scenarios, where models aim to classify known classes and identify unknown ones within fixed scopes. This deviates from the expectation that the model should…

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across…

Constructing 3D representations of object geometry is critical for many robotics tasks, particularly manipulation problems. These representations must be built from potentially noisy partial observations. In this work, we focus on the…

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…

Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…

Multiple Instance Learning (MIL) has demonstrated promise in Whole Slide Image (WSI) classification. However, a major challenge persists due to the high computational cost associated with processing these gigapixel images. Existing methods…

Learning accurate and parsimonious point cloud representations of scene surfaces from scratch remains a challenge in 3D representation learning. Existing point-based methods often suffer from the vanishing gradient problem or require a…

Traditional Scene Understanding problems such as Object Detection and Semantic Segmentation have made breakthroughs in recent years due to the adoption of deep learning. However, the former task is not able to localise objects at a pixel…

Data scarcity and weak supervision continue to limit the performance of machine learning models in many real-world applications, such as mammography, where Multiple Instance Learning (MIL) often offers the best formulation. While recent…

Multi-Instance Learning(MIL) aims to learn the mapping between a bag of instances and the bag-level label. Therefore, the relationships among instances are very important for learning the mapping. In this paper, we propose an MIL algorithm…

We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our…

Multi-instance learning (MIL) has a wide range of applications due to its distinctive characteristics. Although many state-of-the-art algorithms have achieved decent performances, a plurality of existing methods solve the problem only in…

Multiple Instance Learning is the predominant method for Whole Slide Image classification in digital pathology, enabling the use of slide-level labels to supervise model training. Although MIL eliminates the tedious fine-grained annotation…