Simple Online Visual Object Tracker Fusion based on Distributed Kalman Filtering

Tracker-level fusion (TLF) is recognized as an effective approach to comprehensively improve visual object tracking performance by combining the capabilities of multiple baseline trackers. Although there is considerable interest in TLF, there are still challenges related to insufficient understanding, high cost, and unstable performance that...

Optical Flow Upsamplers Ignore Details: Neighborhood Attention Transformers for Convex Upsampling

Most recent works on optical flow use convex upsampling as the last step to obtain high-resolution flow. In this work, we show and discuss several issues and limitations of this currently widely adopted convex upsampling approach. We propose a series of changes, inspired by the observation that convex upsampling as currently implemented performs...

Optimizing Event-Based Vision by Realizing Super-Resolution in Event-Space: an Experimental Approach

An event-based camera enables capturing a video at a high temporal resolution, high dynamical range, reduced power consumption and minimal data bandwidth while the camera has minimal physical dimensions compared to a frame-based camera with the same vision properties. The limiting factor, however, of an event-based camera is the spatial...

The effect of recurrence on adversarial robustness

Traditionally, convolutional neural networks are feedforward networks with a deep and complex hierarchy. Conversely, the human brain has a relatively shallow hierarchy with recurrent connections. Replicating this recurrence may allow for shallower and easier to understand computer vision models that may possess characteristics usually attributed...

Full Color Deep Networks

Color information has been shown to provide useful information during image classification. Yet current popular deep convolutional neural networks use 2-dimensional convolutional layers. The first 2-dimensional convolutional layer in the network combines the color channels of the input images, which produces feature maps per channel with only...

A Survey on Accelerating Sparse CNN Inference on GPUs

Convolutional neural networks (CNNs) are often pruned to achieve faster training and inference speed while also requiring less memory. Nevertheless, during computation, most modern GPUs cannot take advantage of the sparsity automatically, especially on networks with unstructured sparsity. Therefore, many libraries that exploit sparsity, have...

EV-Mask-RCNN: Instance Segmentation in Event-based Videos

Instance segmentation on data from Dynamic Vision Sensors (DVS) is an important computer vision task that needs to be tackled in order to push the research forward on these types of inputs. This paper aims to show that deep learning based techniques can be used to solve the task of instance segmentation on DVS data. A high performing model was...

Accuracy-efficiency trade-off for using event-based data when performing bounding box-based object detection

Event-based cameras do not capture frames like an RGB camera, only data from pixels that detect a change in light intensity, making it a better alternative for processing videos. The sparse data acquired from event-based video only captures movement in an asynchronous way. In this paper an evaluation is made on the efficiency and accuracy of...

Analysis of object tracking algorithms performance on event-based datasets

The event-based camera represents a revolutionary concept, having an asynchronous output. The pixels of dynamic vision sensors react to the brightness change, resulting in streams of events at very small intervals of time. This paper provides a model to track objects in neuromorphic datasets, using clustering. In addition, a non-linear filter is...

Constructing and Evaluating Complex Event-based Datasets for Increasing Performance of Instance Segmentation Models

Event-based cameras represent a new alternative to traditional frame based sensors, with advantages in lower output bandwidth, lower latency and higher dynamic range, thanks to their independent, asynchronous pixels. These advantages prompted the development of computer vision methods on event data in the last decade, however event-based...

Feasibility study of "Invariant Information Clustering for Unsupervised Image Segmentation"

In this paper we analyze the performance of a novel clustering objective that optimizes a neural network to predict segmentation. We challenge the reported results by replicating the original experiments and conducting additional tests to gain an insight into the algorithm. We analyzed the efficiency of the clustering objective on a different...

Frequency learning for structured CNN filters with Gaussian fractional derivatives

A structured CNN filter basis allows incorporating priors about natural image statistics and thus require less training examples to learn, saving valuable annotation time. Here, we build on the Gaussian derivative CNN filter basis that learn both the orientation and scale of the filters. However, this Gaussian filter basis definition depends on...

Using object-specific frequency information from labeled data to improve a CNN’s robustness to adversarial attacks

Convolutional Neural Networks are particularly vulnerable to attacks that manipulate their data, which are usually called adversarial attacks. In this paper, a method of filtering images using the Fast Fourier Transform is explored, along with its potential to be used as a defense mechanism to such attacks. The main contribution that differs...