Related papers: Efficient pedestrian detection by directly optimiz…

In this paper, we propose a design methodology for one-class classifiers using an ensemble-of-classifiers approach. The objective is to select the best structures created during the training phase using an ensemble of spanning trees. It…

The Receiver Operating Characteristic (ROC) curve is a useful tool that measures the discriminating power of a continuous variable or the accuracy of a pharmaceutical or medical test to distinguish between two conditions or classes. In…

Deep learning methods have achieved great success in pedestrian detection, owing to its ability to learn features from raw pixels. However, they mainly capture middle-level representations, such as pose of pedestrian, but confuse positive…

Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the "perfect single frame detector". We enable our analysis by creating a human baseline for pedestrian detection…

In semantic segmentation datasets, classes of high importance are oftentimes underrepresented, e.g., humans in street scenes. Neural networks are usually trained to reduce the overall number of errors, attaching identical loss to errors of…

Pedestrian detection has been heavily studied in the last decade due to its wide application. Despite incremental progress, crowd occlusion and hard negatives are still challenging current state-of-the-art pedestrian detectors. In this…

During deployment, an object detector is expected to operate at a similar performance level reported on its testing dataset. However, when deployed onboard mobile robots that operate under varying and complex environmental conditions, the…

In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train…

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed…

A key component of cognitive radar is the ability to generalize, or achieve consistent performance across a range of sensing environments, since aspects of the physical scene may vary over time. This presents a challenge for learning-based…

Recent region-based object detectors are usually built with separate classification and localization branches on top of shared feature extraction networks. In this paper, we analyze failure cases of state-of-the-art detectors and observe…

Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints. Instead, in many real-world applications, the constraints are derived from side information, such as…

Top-k error has become a popular metric for large-scale classification benchmarks due to the inevitable semantic ambiguity among classes. Existing literature on top-k optimization generally focuses on the optimization method of the top-k…

This paper presents a novel method for detecting pedestrians under adverse illumination conditions. Our approach relies on a novel cross-modality learning framework and it is based on two main phases. First, given a multimodal dataset, a…

Adversarial machine learning attacks on video action recognition models is a growing research area and many effective attacks were introduced in recent years. These attacks show that action recognition models can be breached in many ways.…

Recent advances in object detectors have led to their adoption for industrial uses. However, their deployment in safety-critical applications is hindered by the inherent lack of reliability of neural networks and the complex structure of…

Semi-supervised learning (SSL) addresses the critical challenge of training accurate models when labeled data is scarce but unlabeled data is abundant. Graph-based SSL (GSSL) has emerged as a popular framework that captures data structure…

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…

In practical applications, machine learning algorithms are often needed to learn classifiers that optimize domain specific performance measures. Previously, the research has focused on learning the needed classifier in isolation, yet…

Connecting multiple machine learning models into a pipeline is effective for handling complex problems. By breaking down the problem into steps, each tackled by a specific component model of the pipeline, the overall solution can be made…