no code implementations • 30 Apr 2024 • Benet Oriol Sabat, Alessandro Achille, Matthew Trager, Stefano Soatto
We propose NeRF-Insert, a NeRF editing framework that allows users to make high-quality local edits with a flexible level of control.
no code implementations • 20 Mar 2024 • Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto
In particular, we show that as more tokens are generated, the reliance on the visual prompt decreases, and this behavior strongly correlates with the emergence of hallucinations.
no code implementations • 14 Feb 2024 • Alessandro Achille, Greg Ver Steeg, Tian Yu Liu, Matthew Trager, Carson Klingenberg, Stefano Soatto
Quantifying the degree of similarity between images is a key copyright issue for image-based machine learning.
1 code implementation • 23 Oct 2023 • Tian Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto
We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text.
no code implementations • 6 Jun 2023 • Chethan Parameshwara, Alessandro Achille, Xiaolong Li, Jiawei Mo, Matthew Trager, Ashwin Swaminathan, Cj Taylor, Dheera Venkatraman, Xiaohan Fei, Stefano Soatto
We describe a first step towards learning general-purpose visual representations of physical scenes using only image prediction as a training criterion.
no code implementations • 1 Jun 2023 • Pramuditha Perera, Matthew Trager, Luca Zancato, Alessandro Achille, Stefano Soatto
We investigate whether prompts learned independently for different tasks can be later combined through prompt algebra to obtain a model that supports composition of tasks.
no code implementations • 12 Apr 2023 • Kathlén Kohn, Guido Montúfar, Vahid Shahverdi, Matthew Trager
We study the geometry of linear networks with one-dimensional convolutional layers.
no code implementations • CVPR 2023 • Luca Zancato, Alessandro Achille, Tian Yu Liu, Matthew Trager, Pramuditha Perera, Stefano Soatto
Second, we apply ${\rm T^3AR}$ for test-time adaptation and show that exploiting a pool of external images at test-time leads to more robust representations over existing methods on DomainNet-126 and VISDA-C, especially when few adaptation data are available (up to 8%).
no code implementations • ICCV 2023 • Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille, Parminder Bhatia, Stefano Soatto
These vectors can be seen as "ideal words" for generating concepts directly within the embedding space of the model.
no code implementations • 15 Feb 2023 • Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto
During inference, models can be assembled based on arbitrary selections of data sources, which we call "\`a-la-carte learning".
no code implementations • CVPR 2023 • Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto
During inference, models can be assembled based on arbitrary selections of data sources, which we call a-la-carte learning.
no code implementations • 3 Aug 2021 • Kathlén Kohn, Thomas Merkh, Guido Montúfar, Matthew Trager
We study the family of functions that are represented by a linear convolutional neural network (LCN).
no code implementations • 10 Mar 2021 • Yossi Arjevani, Joan Bruna, Michael Field, Joe Kileel, Matthew Trager, Francis Williams
In this note, we consider the highly nonconvex optimization problem associated with computing the rank decomposition of symmetric tensors.
1 code implementation • CVPR 2021 • Francis Williams, Matthew Trager, Joan Bruna, Denis Zorin
We present Neural Splines, a technique for 3D surface reconstruction that is based on random feature kernels arising from infinitely-wide shallow ReLU networks.
no code implementations • ICLR 2020 • Matthew Trager, Kathlén Kohn, Joan Bruna
The critical locus of the loss function of a neural network is determined by the geometry of the functional space and by the parameterization of this space by the network's weights.
no code implementations • NeurIPS 2019 • Francis Williams, Matthew Trager, Claudio Silva, Daniele Panozzo, Denis Zorin, Joan Bruna
We show that the gradient dynamics of such networks are determined by the gradient flow in a non-redundant parameterization of the network function.
no code implementations • CVPR 2019 • Matthew Trager, Martial Hebert, Jean Ponce
We present a coordinate-free description of Carlsson-Weinshall duality between scene points and camera pinholes and use it to derive a new characterization of primal/dual multi-view geometry.
1 code implementation • NeurIPS 2019 • Joe Kileel, Matthew Trager, Joan Bruna
We study deep neural networks with polynomial activations, particularly their expressive power.
1 code implementation • ECCV 2018 • Matthew Trager, Brian Osserman, Jean Ponce
A set of fundamental matrices relating pairs of cameras in some configuration can be represented as edges of a "viewing graph".
no code implementations • 16 Mar 2018 • Boris Bukh, Xavier Goaoc, Alfredo Hubard, Matthew Trager
We consider incidences among colored sets of lines in $\mathbb{R}^d$ and examine whether the existence of certain concurrences between lines of $k$ colors force the existence of at least one concurrence between lines of $k+1$ colors.
no code implementations • 6 Jul 2017 • Kathlén Kohn, Bernd Sturmfels, Matthew Trager
Visual events in computer vision are studied from the perspective of algebraic geometry.
no code implementations • CVPR 2017 • Matthew Trager, Bernd Sturmfels, John Canny, Martial Hebert, Jean Ponce
The rational camera model recently introduced in [19] provides a general methodology for studying abstract nonlinear imaging systems and their multi-view geometry.
no code implementations • 21 Aug 2016 • Jean Ponce, Bernd Sturmfels, Matthew Trager
We present a new framework for multi-view geometry in computer vision.
no code implementations • CVPR 2016 • Matthew Trager, Martial Hebert, Jean Ponce
Silhouettes provide rich information on three-dimensional shape, since the intersection of the associated visual cones generates the "visual hull", which encloses and approximates the original shape.
no code implementations • ICCV 2015 • Matthew Trager, Martial Hebert, Jean Ponce
Given multiple perspective photographs, point correspondences form the "joint image", effectively a replica of three dimensional space distributed across its two-dimensional projections.