English
Related papers

Related papers: Learning Instance Representation Banks for Aerial …

200 papers

Multiple Instance Learning (MIL) is widely used in medical imaging classification to reduce the labeling effort. While only bag labels are available for training, one typically seeks predictions at both bag and instance levels…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Francisco M. Castro-Macías , Pablo Morales-Álvarez , Yunan Wu , Rafael Molina , Aggelos K. Katsaggelos

Despite recent advancements in computer vision research, object detection in aerial images still suffers from several challenges. One primary challenge to be mitigated is the presence of multiple types of variation in aerial images, for…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Sungjune Park , Hyunjun Kim , Beomchan Park , Yong Man Ro

Multi-UAV collaborative 3D detection enables accurate and robust perception by fusing multi-view observations from aerial platforms, offering significant advantages in coverage and occlusion handling, while posing new challenges for…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Zhongyao Li , Peirui Cheng , Liangjin Zhao , Chen Chen , Yundu Li , Zhechao Wang , Xue Yang , Xian Sun , Zhirui Wang

We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images by lifting noisy 2D labels to 3D. This is a challenging problem due to two primary reasons. Firstly, objects in…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Yuqi Zhang , Guanying Chen , Jiaxing Chen , Shuguang Cui

Multi-instance learning (MIL) deals with tasks where data is represented by a set of bags and each bag is described by a set of instances. Unlike standard supervised learning, only the bag labels are observed whereas the label for each…

Machine Learning · Computer Science 2021-04-27 Weijia Zhang , Jiuyong Li , Lin Liu

Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. However, they often struggle to recover fine-grained details…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Zixin Guo , Kai Zhao , Luyan Zhang

Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on…

The ability for a machine learning model to cope with differences in training and deployment conditions--e.g. in the presence of distribution shift or the generalization to new classes altogether--is crucial for real-world use cases.…

Machine Learning · Computer Science 2023-12-14 Jenny Hamer , Eleni Triantafillou , Bart van Merriënboer , Stefan Kahl , Holger Klinck , Tom Denton , Vincent Dumoulin

Joint representation of geometry, colour and semantics using a 3D neural field enables accurate dense labelling from ultra-sparse interactions as a user reconstructs a scene in real-time using a handheld RGB-D sensor. Our iLabel system…

Computer Vision and Pattern Recognition · Computer Science 2021-12-06 Shuaifeng Zhi , Edgar Sucar , Andre Mouton , Iain Haughton , Tristan Laidlow , Andrew J. Davison

Multi-modal models have shown appealing performance in visual recognition tasks, as free-form text-guided training evokes the ability to understand fine-grained visual content. However, current models cannot be trivially applied to scene…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Yongkun Du , Zhineng Chen , Yuchen Su , Caiyan Jia , Yu-Gang Jiang

Image-text multimodal representation learning aligns data across modalities and enables important medical applications, e.g., image classification, visual grounding, and cross-modal retrieval. In this work, we establish a connection between…

Computer Vision and Pattern Recognition · Computer Science 2023-06-14 Peiqi Wang , William M. Wells , Seth Berkowitz , Steven Horng , Polina Golland

Geometric shape features have been widely used as strong predictors for image classification. Nevertheless, most existing classifiers such as deep neural networks (DNNs) directly leverage the statistical correlations between these shape…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Tonmoy Hossain , Jing Ma , Jundong Li , Miaomiao Zhang

We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised…

Machine Learning · Computer Science 2018-07-09 Shabnam Ghaffarzadegan

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Marc-André Carbonneau , Veronika Cheplygina , Eric Granger , Ghyslain Gagnon

Modelling individual objects in a scene as Neural Radiance Fields (NeRFs) provides an alternative geometric scene representation that may benefit downstream robotics tasks such as scene understanding and object manipulation. However, we…

Robotics · Computer Science 2022-10-10 Jad Abou-Chakra , Feras Dayoub , Niko Sünderhauf

Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for…

Machine Learning · Computer Science 2023-10-24 Siyuan Li , Xun Wang , Rongchang Zuo , Kewu Sun , Lingfei Cui , Jishiyu Ding , Peng Liu , Zhe Ma

\textit{Multiple Instance Learning} (MIL) is concerned with learning from bags of instances, where only bag labels are given and instance labels are unknown. Existent approaches in this field were mainly designed for the bag-level label…

Machine Learning · Computer Science 2019-05-30 Minlong Peng , Qi Zhang

Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model. To address this problem, existing generalizable NeRF methods simply…

Computer Vision and Pattern Recognition · Computer Science 2024-03-20 Ganlin Yang , Guoqiang Wei , Zhizheng Zhang , Yan Lu , Dong Liu

We introduce a graphical framework for multiple instance learning (MIL) based on Markov networks. This framework can be used to model the traditional MIL definition as well as more general MIL definitions. Different levels of ambiguity --…

Machine Learning · Computer Science 2013-09-27 Hossein Hajimirsadeghi , Jinling Li , Greg Mori , Mohammad Zaki , Tarek Sayed

Aerial scene recognition is a fundamental visual task and has attracted an increasing research interest in the last few years. Most of current researches mainly deploy efforts to categorize an aerial image into one scene-level label, while…

Computer Vision and Pattern Recognition · Computer Science 2021-04-23 Yuansheng Hua , Lichao Moua , Jianzhe Lin , Konrad Heidler , Xiao Xiang Zhu