• Publications
  • Influence
Label Refinery: Improving ImageNet Classification through Label Progression
TLDR
The effects of various properties of labels are studied, an iterative procedure that updates the ground truth labels after examining the entire dataset is introduced, and significant gain is shown using refined labels across a wide range of models. Expand
Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects
TLDR
This paper introduces a method to automatically infer object sizes, leveraging visual and textual information from web, and shows that the method outperforms competitive textual and visual baselines in reasoning about size comparisons. Expand
Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
TLDR
This paper defines intermediate physical abstractions called Newtonian scenarios and introduces Newtonian Neural Network (N3) that learns to map a single image to a state in a Newtonian scenario. Expand
LCNN: Lookup-Based Convolutional Neural Network
TLDR
This paper introduces LCNN, a lookup-based convolutional neural network that encodes convolutions by few lookups to a dictionary that is trained to cover the space of weights in CNNs and shows the benefits of LCNN in few-shot learning and few-iteration learning, two crucial aspects of on-device training of deep learning models. Expand
An optimal time algorithm for minimum linear arrangement of chord graphs
TLDR
This paper shows that the label of each node equals to the reverse of binary representation of its id in the optimal arrangement, and designs an O(n) algorithm to solve the minimum linear arrangement problem of Chord graphs. Expand
Who Let the Dogs Out? Modeling Dog Behavior from Visual Data
TLDR
This model takes visual information as input and directly predicts the actions of the agent, and the representation learned by the model encodes distinct information compared to representations trained on image classification, and this learned representation can generalize to other domains. Expand
CSE 521 : Design and Analysis of Algorithms I Spring 2016 Lecture 6 : Curse of Dimensionality , Dimension Reduction
High dimensional vectors appear frequently in recent development in CS, examples of which are user-movie ratings of netflix, DNA strings of patients, and images pixel values. In this lecture we studyExpand