Related papers: NOCTA: Non-Greedy Objective Cost-Tradeoff Acquisit…

We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our…

Curating an informative and representative dataset is essential for enhancing the performance of 2D object detectors. We present a novel active learning sampling strategy that addresses both the informativeness and diversity of the…

To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. Multi-modal data introduces new opportunities and challenges for…

Continual Test-Time Adaptation (CTTA) enables pre-trained models to adapt to continuously evolving domains. Existing methods have improved robustness but typically rely on fixed or batch-level thresholds, which cannot account for varying…

3D Multi-Object Tracking (MOT) has achieved tremendous achievement thanks to the rapid development of 3D object detection and 2D MOT. Recent advanced works generally employ a series of object attributes, e.g., position, size, velocity, and…

Deep learning has been successfully applied to OCT segmentation. However, for data from different manufacturers and imaging protocols, and for different regions of interest (ROIs), it requires laborious and time-consuming data annotation…

Existing deep multi-object tracking (MOT) approaches first learn a deep representation to describe target objects and then associate detection results by optimizing a linear assignment problem. Despite demonstrated successes, it is…

In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because they cause domain changes. Previously, nuisance disentangled…

In many real-world scenarios, acquiring all features of a data instance can be expensive or impractical due to monetary cost, latency, or privacy concerns. Active Feature Acquisition (AFA) addresses this challenge by dynamically selecting a…

Robust object tracking requires knowledge of tracked objects' appearance, motion and their evolution over time. Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent…

Classification systems are often deployed in resource-constrained settings where labels must be assigned to inputs on a budget of time, memory, etc. Budgeted, sequential classifiers (BSCs) address these scenarios by processing inputs…

Autonomous driving systems require a quick and robust perception of the nearby environment to carry out their routines effectively. With the aim to avoid collisions and drive safely, autonomous driving systems rely heavily on object…

Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation…

Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the…

Online advertising auctions are fundamental to internet commerce, demanding solutions that not only maximize revenue but also ensure incentive compatibility, high-quality user experience, and real-time efficiency. While recent…

In many practical machine learning applications, there are two objectives: one is to maximize predictive accuracy and the other is to minimize costs of the resulting model. These costs of individual features may be financial costs, but can…

Transmission optical coherence tomography (OCT) enables analysis of biological specimens in vitro through detection of forward scattered light. Up to now, transmission OCT was considered as a technique that cannot directly retrieve…

This paper proposes an inverse optimal control method which enables a robot to incrementally learn a control objective function from a collection of trajectory segments. By saying incrementally, it means that the collection of trajectory…

We consider the problem of active feature acquisition, where we sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way. In this work, we formulate this active feature…

We address the problem of learning a decision policy from observational data of past decisions in contexts with features and associated outcomes. The past policy maybe unknown and in safety-critical applications, such as medical decision…