Search Results for author:
Found 51 papers, 33 papers with code
Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
The HCR bounds appear to be insufficient on their own to guarantee confidentiality of the inputs to inference with standard deep neural nets, "ResNet-18" and "Swin-T," pre-trained on the data set, "ImageNet-1000," which contains 1000 classes.
Bounding Training Data Reconstruction in Private (Deep) Learning
Differential privacy is widely accepted as the de facto method for preventing data leakage in ML, and conventional wisdom suggests that it offers strong protection against privacy attacks.
A Systematic Study of Bias Amplification
To enable this study, we design a simple image-classification problem in which we can tightly control (synthetic) biases.
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Model pre-training is a cornerstone of modern visual recognition systems.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
(using extra training data)
Fine-Grained Image Classification
Out-of-Distribution Generalization
+3
Omnivore: A Single Model for Many Visual Modalities
Prior work has studied different visual modalities in isolation and developed separate architectures for recognition of images, videos, and 3D data.
Ranked #1 on
Scene Recognition
on SUN-RGBD
(using extra training data)
Submix: Practical Private Prediction for Large-Scale Language Models
Recent data-extraction attacks have exposed that language models can memorize some training samples verbatim.
CrypTen: Secure Multi-Party Computation Meets Machine Learning
To foster adoption of secure MPC in machine learning, we present CrypTen: a software framework that exposes popular secure MPC primitives via abstractions that are common in modern machine-learning frameworks, such as tensor computations, automatic differentiation, and modular neural networks.
Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems
Machine-learning systems such as self-driving cars or virtual assistants are composed of a large number of machine-learning models that recognize image content, transcribe speech, analyze natural language, infer preferences, rank options, etc.
Measuring Data Leakage in Machine-Learning Models with Fisher Information
This information leaks either through the model itself or through predictions made by the model.
Physical Reasoning Using Dynamics-Aware Models
A common approach to solving physical reasoning tasks is to train a value learner on example tasks.
Ranked #1 on
Visual Reasoning
on PHYRE-1B-Within
Making Paper Reviewing Robust to Bid Manipulation Attacks
We develop a novel approach for paper bidding and assignment that is much more robust against such attacks.
Data Appraisal Without Data Sharing
We show that in private, forward influence functions provide an appealing trade-off between high quality appraisal and required computation, in spite of label noise, class imbalance, and missing data.
The Trade-Offs of Private Prediction
This is problematic when the training data needs to remain private.
Forward Prediction for Physical Reasoning
Physical reasoning requires forward prediction: the ability to forecast what will happen next given some initial world state.
Ranked #2 on
Visual Reasoning
on PHYRE-1B-Within
Secure multiparty computations in floating-point arithmetic
Secure multiparty computations enable the distribution of so-called shares of sensitive data to multiple parties such that the multiple parties can effectively process the data while being unable to glean much information about the data (at least not without collusion among all parties to put back together all the shares).
Convolutional Networks with Dense Connectivity
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.
Measuring Dataset Granularity
We also investigate the interplay between dataset granularity with a variety of factors and find that fine-grained datasets are more difficult to learn from, more difficult to transfer to, more difficult to perform few-shot learning with, and more vulnerable to adversarial attacks.
Self-Supervised Learning of Pretext-Invariant Representations
The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images.
Ranked #7 on
Contrastive Learning
on imagenet-1k
SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
Few-shot learners aim to recognize new object classes based on a small number of labeled training examples.
Certified Data Removal from Machine Learning Models
Good data stewardship requires removal of data at the request of the data's owner.
Privacy-Preserving Multi-Party Contextual Bandits
This paper considers a learning setting in which multiple parties aim to train a contextual bandit together in a private way: the parties aim to maximize the total reward but do not want to share any of the relevant information they possess with the other parties.
PHYRE: A New Benchmark for Physical Reasoning
The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles.
Ranked #3 on
Visual Reasoning
on PHYRE-1B-Within
Does Object Recognition Work for Everyone?
The paper analyzes the accuracy of publicly available object-recognition systems on a geographically diverse dataset.
Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search
Empirical evaluations of this defense strategy on ImageNet suggest that it is very effective in attack settings in which the adversary does not have access to the image database.
Evaluating Text-to-Image Matching using Binary Image Selection (BISON)
Providing systems the ability to relate linguistic and visual content is one of the hallmarks of computer vision.
Feature Denoising for Improving Adversarial Robustness
This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks.
Ranked #1 on
Adversarial Defense
on CAAD 2018
Anytime Stereo Image Depth Estimation on Mobile Devices
Many applications of stereo depth estimation in robotics require the generation of accurate disparity maps in real time under significant computational constraints.
Ranked #1 on
Stereo Depth Estimation
on KITTI2012
Exploring the Limits of Weakly Supervised Pretraining
ImageNet classification is the de facto pretraining task for these models.
Ranked #218 on
Image Classification
on ImageNet
(using extra training data)
Learning by Asking Questions
We also show that our model asks questions that generalize to state-of-the-art VQA models and to novel test time distributions.
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
Submanifold sparse convolutional networks
Ranked #5 on
3D Semantic Segmentation
on SensatUrban
Separating Self-Expression and Visual Content in Hashtag Supervision
The variety, abundance, and structured nature of hashtags make them an interesting data source for training vision models.
CondenseNet: An Efficient DenseNet using Learned Group Convolutions
It combines dense connectivity with a novel module called learned group convolution.
Countering Adversarial Images using Input Transformations
This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system.
Memory-Efficient Implementation of DenseNets
A 264-layer DenseNet (73M parameters), which previously would have been infeasible to train, can now be trained on a single workstation with 8 NVIDIA Tesla M40 GPUs.
Submanifold Sparse Convolutional Networks
Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc.
Ranked #34 on
3D Part Segmentation
on ShapeNet-Part
Inferring and Executing Programs for Visual Reasoning
Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes.
Ranked #5 on
Visual Question Answering (VQA)
on CLEVR-Humans
Multi-Scale Dense Networks for Resource Efficient Image Classification
In this paper we investigate image classification with computational resource limits at test time.
Learning Visual N-Grams from Web Data
Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts.
Ranked #2 on
Zero-Shot Transfer Image Classification
on aYahoo
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings.
Densely Connected Convolutional Networks
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.
Ranked #1 on
Classification
on XImageNet-12
Revisiting Visual Question Answering Baselines
Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding.
Persistent self-supervised learning principle: from stereo to monocular vision for obstacle avoidance
We study this persistent form of SSL in the context of a flying robot that has to avoid obstacles based on distance estimates from the visual cue of stereo vision.
Robotics
Modeling Time Series Similarity with Siamese Recurrent Networks
Traditional techniques for measuring similarities between time series are based on handcrafted similarity measures, whereas more recent learning-based approaches cannot exploit external supervision.
Approximated and User Steerable tSNE for Progressive Visual Analytics
Progressive Visual Analytics aims at improving the interactivity in existing analytics techniques by means of visualization as well as interaction with intermediate results.
Learning Visual Features from Large Weakly Supervised Data
We train convolutional networks on a dataset of 100 million Flickr photos and captions, and show that these networks produce features that perform well in a range of vision problems.
Time Series Classification using the Hidden-Unit Logistic Model
We present a new model for time series classification, called the hidden-unit logistic model, that uses binary stochastic hidden units to model latent structure in the data.
Speeding Up Tracking by Ignoring Features
Most modern object trackers combine a motion prior with sliding-window detection, using binary classifiers that predict the presence of the target object based on histogram features.
Marginalizing Corrupted Features
In this paper, we propose a third, alternative approach to combat overfitting: we extend the training set with infinitely many artificial training examples that are obtained by corrupting the original training data.
Structure Preserving Object Tracking
We also show that SPOT can improve the performance of single-object trackers by simultaneously tracking different parts of the object.
Barnes-Hut-SNE
The paper presents an O(N log N)-implementation of t-SNE -- an embedding technique that is commonly used for the visualization of high-dimensional data in scatter plots and that normally runs in O(N^2).
Visualizing Data using t-SNE
The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
