Related papers: Visual Recognition Using Directional Distribution …
Video-based vehicle detection has received considerable attention over the last ten years and there are many deep learning based detection methods which can be applied to it. However, these methods are devised for still images and applying…
This paper introduces a novel approach to securing machine learning model deployments against potential distribution shifts in practical applications, the Total Variation Out-of-Distribution (TV-OOD) detection method. Existing methods have…
We propose a novel particle filter for convolutional-correlation visual trackers. Our method uses correlation response maps to estimate likelihood distributions and employs these likelihoods as proposal densities to sample particles.…
Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation…
In Digital Holography (DH), it is crucial to extract the object distance from a hologram in order to reconstruct its amplitude and phase. This step is called auto-focusing and it is conventionally solved by first reconstructing a stack of…
The detection of out of distribution samples for image classification has been widely researched. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing the image to…
A recent popular approach to out-of-distribution (OOD) detection is based on a self-supervised learning technique referred to as contrastive learning. There are two main variants of contrastive learning, namely instance and class…
Previous work has shown that feature maps of deep convolutional neural networks (CNNs) can be interpreted as feature representation of a particular image region. Features aggregated from these feature maps have been exploited for image…
How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two…
Visual place recognition is challenging because there are so many factors that can cause the appearance of a place to change, from day-night cycles to seasonal change to atmospheric conditions. In recent years a large range of approaches…
Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to…
3D convolutional networks is a good means to perform tasks such as video segmentation into coherent spatio-temporal chunks and classification of them with regard to a target taxonomy. In the chapter we are interested in the classification…
Detecting out-of-distribution inputs for visual recognition models has become critical in safe deep learning. This paper proposes a novel hierarchical visual category modeling scheme to separate out-of-distribution data from in-distribution…
Deep learning models often rely only on a small set of features even when there is a rich set of predictive signals in the training data. This makes models brittle and sensitive to distribution shifts. In this work, we first examine vision…
Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…
We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of…
Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms. Existing approaches…
Deep Convolutional Neural Networks (DCNN) have been proven to be effective for various computer vision problems. In this work, we demonstrate its effectiveness on a continuous object orientation estimation task, which requires prediction of…
This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually learns regional visual patterns in each intermediate layer…
Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos. However, one limitation of applying 2D CNN to analyze videos is…