-
Article
Open AccessOn Measuring and Controlling the Spectral Bias of the Deep Image Prior
The deep image prior showed that a randomly initialized network with a suitable architecture can be trained to solve inverse imaging problems by simply optimizing it’s parameters to reconstruct a single degrad...
-
Chapter and Conference Paper
Improving Few-Shot Part Segmentation Using Coarse Supervision
A significant bottleneck in training deep networks for part segmentation is the cost of obtaining detailed annotations. We propose a framework to exploit coarse labels such as figure-ground masks and keypoint ...
-
Chapter and Conference Paper
Cross-modal 3D Shape Generation and Manipulation
Creating and editing the shape and color of 3D objects require tremendous human effort and expertise. Compared to direct manipulation in 3D interfaces, 2D interactions such as sketches and scribbles are usuall...
-
Chapter and Conference Paper
MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation
We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. This is inspired by the observation that view-based surface representations are more effective at...
-
Article
Inferring 3D Shapes from Image Collections Using Adversarial Networks
We investigate the problem of learning a probabilistic distribution over three-dimensional shapes given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called projective gene...
-
Article
Phenology of nocturnal avian migration has shifted at the continental scale
Climate change induced phenological shifts in primary productivity result in trophic mismatches for many organisms1–4, with broad implications for ecosystem structure and function. For birds that have a synchroni...
-
Chapter and Conference Paper
Describing Textures Using Natural Language
Textures in natural images can be characterized by color, shape, periodicity of elements within them, and other attributes that can be described using natural language. In this paper, we study the problem of d...
-
Chapter and Conference Paper
When Does Self-supervision Improve Few-Shot Learning?
We investigate the role of self-supervised learning (SSL) in the context of few-shot learning. Although recent research has shown the benefits of SSL on large unlabeled datasets, its utility on small datasets ...
-
Chapter and Conference Paper
Label-Efficient Learning on Point Clouds Using Approximate Convex Decompositions
The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. Both of these problems, however, suffer from relatively small training ...
-
Chapter and Conference Paper
ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds
We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives. ParSeNet ...
-
Chapter and Conference Paper
A Deeper Look at 3D Shape Classifiers
We investigate the role of representations and architectures for classifying 3D shapes in terms of their computational efficiency, generalization, and robustness to adversarial transformations. By varying the ...
-
Chapter and Conference Paper
Multiresolution Tree Networks for 3D Point Cloud Processing
We present multiresolution tree-structured networks to process point clouds for 3D shape understanding and generation tasks. Our network represents a 3D shape as a set of locality-preserving 1D ordered list of...
-
Chapter and Conference Paper
Second-Order Democratic Aggregation
Aggregated second-order features extracted from deep convolutional networks have been shown to be effective for texture generation, fine-grained recognition, material classification, and scene understanding. I...
-
Chapter
A Taxonomy of Part and Attribute Discovery Techniques
This chapter surveys recent techniques for discovering a set of Parts and Attributes (PnAs) in order to enable fine-grained visual discrimination between its instances. Part and Attribute (PnA)-based representati...
-
Article
Open AccessDeep Filter Banks for Texture Recognition, Description, and Segmentation
Visual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner hav...
-
Article
Part and Attribute Discovery from Relative Annotations
Part and attribute based representations are widely used to support high-level search and retrieval applications. However, learning computer vision models for automatically extracting these from images require...
-
Chapter and Conference Paper
Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection
Collections of filters based on histograms of oriented gradients (HOG) are common for several detection methods, notably, poselets and exemplar SVMs. The main bottleneck in training such systems is the selecti...
-
Chapter and Conference Paper
Discovering a Lexicon of Parts and Attributes
We propose a framework to discover a lexicon of visual attributes that supports fine-grained visual discrimination. It consists of a novel annotation task where annotators are asked to describe differences bet...
-
Chapter and Conference Paper
Linearized Smooth Additive Classifiers
We consider a framework for learning additive classifiers based on regularized empirical risk minimization, where the regularization favors “smooth” functions. We present representations of classifiers for whi...
-
Chapter
Multiple-View Object Recognition in Smart Camera Networks
We study object recognition in low-power, low-bandwidth smart camera networks. The ability to perform robust object recognition is crucial for applications such as visual surveillance to track and identify obj...
