116 citations · 1.1k across the 96 of their papers we have counts for
23 papers · 1 filter
Stereoscopic Universal Perturbations across Different Architectures and Datasets
Zachary Berger, Parth Agrawal, Tian Yu Liu +2
We study the effect of adversarial perturbations of images on deep stereo matching networks for the disparity estimation task. We present a method to craft a single set of perturba…
DIVA: Dataset Derivative of a Learning Task
Yonatan Dukler, Alessandro Achille, Giovanni Paolini +3
We present a method to compute the derivative of a learning task with respect to a dataset. A learning task is a function from a training set to the validation error, which can be…
Learned Uncertainty Calibration for Visual Inertial Localization
Stephanie Tsuei, Stefano Soatto, Paulo Tabuada +1
The widely-used Extended Kalman Filter (EKF) provides a straightforward recipe to estimate the mean and covariance of the state given all past measurements in a causal and recursiv…
Small Lesion Segmentation in Brain MRIs with Subpixel Embedding
Alex Wong, Allison Chen, Yangchao Wu +4
We present a method to segment MRI scans of the human brain into ischemic stroke lesion and normal tissues. We propose a neural network architecture in the form of a standard encod…
SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots
Alexander Schperberg, Stephanie Tsuei, Stefano Soatto +1
We present an end-to-end online motion planning framework that uses a data-driven approach to navigate a heterogeneous robot team towards a global goal while avoiding obstacles in…
Unsupervised Depth Completion with Calibrated Backprojection Layers
Alex Wong, Stefano Soatto
We propose a deep neural network architecture to infer dense depth from an image and a sparse point cloud. It is trained using a video stream and corresponding synchronized sparse…
ARCH++: Animation-Ready Clothed Human Reconstruction Revisited
Tong He, Yuanlu Xu, Shunsuke Saito +2
We present ARCH++, an image-based method to reconstruct 3D avatars with arbitrary clothing styles. Our reconstructed avatars are animation-ready and highly realistic, in both the v…
Uniform Sampling over Episode Difficulty
Sébastien M. R. Arnold, Guneet S. Dhillon, Avinash Ravichandran +1
Episodic training is a core ingredient of few-shot learning to train models on tasks with limited labelled data. Despite its success, episodic training remains largely understudied…
Learning Hierarchical Graph Neural Networks for Image Clustering
Yifan Xing, Tong He, Tianjun Xiao +6
We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated…
Representation Consolidation for Training Expert Students
Zhizhong Li, Avinash Ravichandran, Charless Fowlkes +3
Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is…
Dynamically Grown Generative Adversarial Networks
Lanlan Liu, Yuting Zhang, Jia Deng +1
Recent work introduced progressive network growing as a promising way to ease the training for large GANs, but the model design and architecture-growing strategy still remain under…
Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers
Stephanie Tsuei, Aditya Golatkar, Stefano Soatto
We propose a method to estimate the uncertainty of the outcome of an image classifier on a given input datum. Deep neural networks commonly used for image classification are determ…
Harnessing Unrecognizable Faces for Improving Face Recognition
Siqi Deng, Yuanjun Xiong, Meng Wang +2
The common implementation of face recognition systems as a cascade of a detection stage and a recognition or verification stage can cause problems beyond failures of the detector.…
An Adaptive Framework for Learning Unsupervised Depth Completion
Alex Wong, Xiaohan Fei, Byung-Woo Hong +1
We present a method to infer a dense depth map from a color image and associated sparse depth measurements. Our main contribution lies in the design of an annealing process for det…
Learning Topology from Synthetic Data for Unsupervised Depth Completion
Alex Wong, Safa Cicek, Stefano Soatto
We present a method for inferring dense depth maps from images and sparse depth measurements by leveraging synthetic data to learn the association of sparse point clouds with dense…
Compatibility-aware Heterogeneous Visual Search
Rahul Duggal, Hao Zhou, Shuo Yang +4
We tackle the problem of visual search under resource constraints. Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery i…
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Yuqing Xie, Yi-an Lai, Yuanjun Xiong +2
Behavior of deep neural networks can be inconsistent between different versions. Regressions during model update are a common cause of concern that often over-weigh the benefits in…
Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries
Qi Dong, Zhuowen Tu, Haofu Liao +3
Computer vision applications such as visual relationship detection and human object interaction can be formulated as a composite (structured) set detection problem in which both th…
A linearized framework and a new benchmark for model selection for fine-tuning
Aditya Deshpande, Alessandro Achille, Avinash Ravichandran +6
Fine-tuning from a collection of models pre-trained on different domains (a "model zoo") is emerging as a technique to improve test accuracy in the low-data regime. However, model…
Supervised Momentum Contrastive Learning for Few-Shot Classification
Orchid Majumder, Avinash Ravichandran, Subhransu Maji +3
Few-shot learning aims to transfer information from one task to enable generalization on novel tasks given a few examples. This information is present both in the domain and the cl…
Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
Zhaowei Cai, Avinash Ravichandran, Subhransu Maji +3
We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher bas…
Estimating informativeness of samples with Smooth Unique Information
Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini +4
We define a notion of information that an individual sample provides to the training of a neural network, and we specialize it to measure both how much a sample informs the final w…
Structured Prediction as Translation between Augmented Natural Languages
Giovanni Paolini, Ben Athiwaratkun, Jason Krone +6
We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extractio…