Instance Prediction

Instance prediction focuses on accurately identifying and characterizing individual objects or instances within a larger dataset, aiming to improve upon the limitations of bag-level predictions. Current research emphasizes developing efficient and robust models, often employing transformer architectures or convolutional neural networks, to handle challenges like overlapping instances, temporal dynamics (e.g., in autonomous driving), and limited labeled data (e.g., in medical image analysis). These advancements have significant implications for various fields, including autonomous driving, medical image analysis, and scene understanding, by enabling more precise and reliable object detection and prediction.

Papers

November 9, 2024

Weak to Strong Learning from Aggregate Labels
Yukti Makhija, Rishi Saket
Multiple Instance Learning Weak Learner Strong Learner Instance Level Label Instance Prediction Aggregated Label

July 9, 2024

Joint prototype and coefficient prediction for 3D instance segmentation
Remco Royen, Leon Denis, Adrian Munteanu
3D Scene Understanding Fast Inference 3D Instance Segmentation Coefficient Prediction Sampling Algorithm Instance Prediction

April 19, 2024

FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous Driving
Xingtai Gui, Tengteng Huang, Haonan Shao, Haotian Yao, Chi Zhang
Autonomous Driving Bird'S Eye View Map Segmentation Effective Transformer Instance Prediction BEV Feature Instance Level Motion

June 19, 2023

PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View
Peizheng Li, Shuxiao Ding, Xieyuanli Chen, Niklas Hanselmann, Marius Cordts, Juergen Gall
Convolutional Neural Network Autonomous Driving Autonomous Vehicle Eye View Lightweight Framework Instance Prediction

April 7, 2023

Domain Adaptive Multiple Instance Learning for Instance-level Prediction of Pathological Images
Shusuke Takahama, Yusuke Kurose, Yusuke Mukuta, Hiroyuki Abe, Akihiko Yoshizawa, Tetsuo Ushiku, Masashi Fukayama, Masanobu Kitagawa, Masaru Kitsuregawa, Tatsuya Harada
Domain Adaptation Multiple Instance Learning Pathology Image Cell Image Pathological Image Instance Prediction

March 25, 2023

DoNet: Deep De-overlapping Network for Cytology Instance Segmentation
Hao Jiang, Rushan Zhang, Yanning Zhou, Yumeng Wang, Hao Chen
Instance Segmentation Transparent Object Overlap Detection Region Segmentation Instance Prediction

November 15, 2022

Forecasting Future Instance Segmentation with Learned Optical Flow and Warping
Andrea Ciamarra, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo
Semantic Segmentation Autonomous Vehicle Optical Flow Instance Prediction Learning Based Optical FLow

June 12, 2022

Balancing Bias and Variance for Active Weakly Supervised Learning
Hitesh Sapkota, Qi Yu
Weakly Supervised Learning Variance Information Balanced Approach Robust Bayesian Instance Prediction Deep Multiple Instance

April 14, 2022

Joint Forecasting of Panoptic Segmentations with Difference Attention
Colin Graber, Cyril Jazra, Wenjie Luo, Liangyan Gui, Alexander Schwing
Panoptic Segmentation Joint predictioN Instance Prediction Vertical Attention

March 25, 2022

StretchBEV: Stretching Future Instance Prediction Spatially and Temporally
Adil Kaan Akan, Fatma Güney
Time Series Temporal Dynamic Future Prediction Multiple Prediction Instance Prediction

March 8, 2022

Contrastive Conditional Neural Processes
Zesheng Ye, Lina Yao
Generative Model Contrastive Estimation Conditional Neural Process Meta Representation Instance Prediction

February 25, 2022

Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization
Weijia Zhang, Xuanhui Zhang, Han-Wen Deng, Min-Ling Zhang
Distribution Generalization Instance Learning Multiple Instance Instance Prediction Instance Level Causal