3.7k citations · 11.8k across the 85 of their papers we have counts for
13 papers · 1 filter
Can I see an Example? Active Learning the Long Tail of Attributes and Relations
Tyler L. Hayes, Maximilian Nickel, Christopher Kanan +2
There has been significant progress in creating machine learning models that identify objects in scenes along with their associated attributes and relationships; however, there is…
Learning to Visually Navigate in Photorealistic Environments Without any Supervision
Lina Mezghani, Sainbayar Sukhbaatar, Arthur Szlam +2
Learning to navigate in a realistic setting where an agent must rely solely on visual inputs is a challenging task, in part because the lack of position information makes it diffic…
Low-shot learning with large-scale diffusion
Matthijs Douze, Arthur Szlam, Bharath Hariharan +1
This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-sho…
Hard Mixtures of Experts for Large Scale Weakly Supervised Vision
Sam Gross, Marc'Aurelio Ranzato, Arthur Szlam
Training convolutional networks (CNN's) that fit on a single GPU with minibatch stochastic gradient descent has become effective in practice. However, there is still no effective m…
Geometric deep learning: going beyond Euclidean data
Michael M. Bronstein, Joan Bruna, Yann LeCun +2
Many scientific fields study data with an underlying structure that is a non-Euclidean space. Some examples include social networks in computational social sciences, sensor network…
Simple Baseline for Visual Question Answering
Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar +2
We describe a very simple bag-of-words baseline for visual question answering. This baseline concatenates the word features from the question and CNN features from the image to pre…
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
Emily Denton, Soumith Chintala, Arthur Szlam +1
In this paper we introduce a generative parametric model capable of producing high quality samples of natural images. Our approach uses a cascade of convolutional networks within a…
Better Feature Tracking Through Subspace Constraints
Bryan Poling, Gilad Lerman, Arthur Szlam
Feature tracking in video is a crucial task in computer vision. Usually, the tracking problem is handled one feature at a time, using a single-feature tracker like the Kanade-Lucas…
Fast approximations to structured sparse coding and applications to object classification
Arthur Szlam, Karol Gregor, Yann LeCun
We describe a method for fast approximation of sparse coding. The input space is subdivided by a binary decision tree, and we simultaneously learn a dictionary and assignment of al…
Convolutional Matching Pursuit and Dictionary Training
Arthur Szlam, Koray Kavukcuoglu, Yann LeCun
Matching pursuit and K-SVD is demonstrated in the translation invariant setting
Hybrid Linear Modeling via Local Best-fit Flats
Teng Zhang, Arthur Szlam, Yi Wang +1
We present a simple and fast geometric method for modeling data by a union of affine subspaces. The method begins by forming a collection of local best-fit affine subspaces, i.e.,…
Randomized hybrid linear modeling by local best-fit flats
Teng Zhang, Arthur Szlam, Yi Wang +1
The hybrid linear modeling problem is to identify a set of d-dimensional affine sets in a D-dimensional Euclidean space. It arises, for example, in object tracking and structure fr…
Median K-flats for hybrid linear modeling with many outliers
Teng Zhang, Arthur Szlam, Gilad Lerman
We describe the Median K-Flats (MKF) algorithm, a simple online method for hybrid linear modeling, i.e., for approximating data by a mixture of flats. This algorithm simultaneously…