27 accepted papers
Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models. However, similarity is typically computed with a generic off-the-shelf embedding model that has been trained for tasks such as retrieval. Whether these embeddi…
This work studies a novel subset selection problem called *max-min diversification with monotone submodular utility* (MDMS), which has a wide range of applications in machine learning, e.g., data sampling and feature selection. Given a set of points in a metric space, the goal of MDMS is to maximize…
Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However this quality comes at significant computational cost: nearly all of these models are iterative and require running sampling multiple times with large models. This…
As with many machine learning problems the progress of image generation methods hinges on good evaluation metrics. One of the most popular is the Frechet Inception Distance (FID). FID estimates the distance between a distribution of Inception-v3 features of real images and those of images generated…
We present a subset selection algorithm designed to work with arbitrary model families in a practical batch setting. In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i.e. further train model weights) once a lar…
Representational learning forms the backbone of most deep learning applications, and the value of a learned representation is intimately tied to its information content regarding different factors of variation. Finding good representations depends on the nature of supervision and the learning algori…
Neural networks tend to achieve better accuracy with training if they are larger {—} even if the resulting models are overparameterized. Nevertheless, carefully removing such excess of parameters before, during, or after training may also produce models with similar or even improved accuracy. In man…
In the deep learning era, the vast majority of methods to predict pose from a single image are trained to classify or regress to a single given ground truth pose per image. Such methods have two main shortcomings, i) they cannot represent uncertainty about the predictions, and ii) they cannot handle…
We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable. However, current approaches to determine the stability of neurons with Rectified Linear Unit (ReLU) activations require solving or finding…
We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans. Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the…
We explore the possibility of using line intersection constraints for 3D scan registration. Typical 3D registration algorithms exploit point and plane correspondences, while line intersection constraints have not been used in the context of 3D scan registration before. Constraints from a match of pa…
3D scan registration is a classical, yet a highly useful problem in the context of 3D sensors such as Kinect and Velodyne. While there are several existing methods, the techniques are usually incremental where adjacent scans are registered first to obtain the initial poses, followed by motion averag…
We propose a minimal solution for pose estimation using both points and lines for a multi-perspective camera. In this paper, we treat the multi-perspective camera as a collection of rigidly attached perspective cameras. These type of imaging devices are useful for several computer vision application…
Vanishing points and vanishing lines are classical geometrical concepts in perspective cameras that have a lineage dating back to 3 centuries. A vanishing point is a point on the image space where parallel lines in 3D space appear to converge, whereas a vanishing line passes through 2 or more vanish…
We investigate the complexity of deep neural networks (DNN) that represent piecewise linear (PWL) functions. In particular, we study the number of linear regions, i.e. pieces, that a PWL function represented by a DNN can attain, both theoretically and empirically. We present (i) tighter upper and lo…
A family of super deep networks, referred to as residual networks or ResNet~cite{he2016deep}, achieved record-beating performance in various visual tasks such as image recognition, object detection, and semantic segmentation. The ability to train very deep networks naturally pushed the researchers t…
Edge detection is among the most fundamental vision problems for its role in perceptual grouping and its wide applications. Recent advances in representation learning have led to considerable improvements in this area. Many state of the art edge detection models are learned with fully convolutional…
We propose VLASE, a framework to use semantic edge features from images to achieve on-road localization. Semantic edge features denote edge contours that separate pairs of distinct objects such as building-sky, road-sidewalk, and building-ground. While prior work has shown promising results by utili…
Boundary and edge cues are highly beneficial in improving a wide variety of vision tasks such as semantic segmentation, object recognition, stereo, and object proposal generation. Recently, the problem of edge detection has been revisited and significant progress has been made with deep learning. Wh…
RGBD SLAM systems have shown impressive results, but the limited field of view (FOV) and depth range of typical RGBD cameras still cause problems for registering distant frames. Monocular SLAM systems, in contrast, can exploit wide-angle cameras and do not have the depth range limitation, but are un…
We present a new image feature detection method. Our method selects features based on segmenting points with high local intensity variations across different scales using a robust rank order statistics approach. Our method produces a large number of repeatable features that are invariant to several…
The success of many robotics applications hinges on the speed at which the underlying sensing and inference tasks are carried out. Many high-speed applications such as autonomous driving and evasive maneuvering of quadrotors require high run time performance, which traditional cameras can seldom pro
Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance. Robots, on the other hand, require quick maneuverability and effective computation to observe its immediate environment and perform tasks within it. In t
Binary descriptors allow fast detection and matching algorithms in computer vision problems. Though binary descriptors can be computed at almost two orders of magnitude faster than traditional gradient based descriptors, they suffer from poor matching accuracy in challenging conditions. In this pape…
Conventional SLAM systems with an RGB-D sensor use depth measurements only in a limited depth range due to hardware limitation and noise of the sensor, ignoring regions that are too far or too close from the sensor. Such systems introduce registration errors especially in scenes with large depth var
We propose a layered street view model to encode both depth and semantic information on street view images for autonomous driving. Recently, stixels, stix-mantics, and tiered scene labeling methods have been proposed to model street view images. We propose a 4-layer street view model, a compact repr…
We propose a simple and useful idea based on cross-ratio constraint for wide-baseline matching and 3D reconstruction. Most existing methods exploit feature points and planes from images. Lines have always been considered notorious for both matching and reconstruction due to the lack of good line des…