116 citations · 1.1k across the 96 of their papers we have counts for
20 papers · 1 filter
SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning
Albert Zhao, Tong He, Yitao Liang +3
We describe a policy learning approach to map visual inputs to driving controls conditioned on turning command that leverages side tasks on semantics and object affordances via a l…
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
Aditya Golatkar, Alessandro Achille, Stefano Soatto
We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidde…
A geometric interpretation of stochastic gradient descent using diffusion metrics
R. Fioresi, P. Chaudhari, S. Soatto
Stochastic gradient descent (SGD) is a key ingredient in the training of deep neural networks and yet its geometrical significance appears elusive. We study a deterministic model i…
Meta-Q-Learning
Rasool Fakoor, Pratik Chaudhari, Stefano Soatto +1
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learnin…
A Baseline for Few-Shot Image Classification
Guneet S. Dhillon, Pratik Chaudhari, Avinash Ravichandran +1
Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current sta…
Toward Understanding Catastrophic Forgetting in Continual Learning
Cuong V. Nguyen, Alessandro Achille, Michael Lam +3
We study the relationship between catastrophic forgetting and properties of task sequences. In particular, given a sequence of tasks, we would like to understand which properties o…
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence
Aditya Golatkar, Alessandro Achille, Stefano Soatto
Regularization is typically understood as improving generalization by altering the landscape of local extrema to which the model eventually converges. Deep neural networks (DNNs),…
Unsupervised Domain Adaptation via Regularized Conditional Alignment
Safa Cicek, Stefano Soatto
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifi…
Where is the Information in a Deep Neural Network?
Alessandro Achille, Giovanni Paolini, Stefano Soatto
Whatever information a deep neural network has gleaned from training data is encoded in its weights. How this information affects the response of the network to future data remains…
Unsupervised Depth Completion from Visual Inertial Odometry
Alex Wong, Xiaohan Fei, Stephanie Tsuei +1
We describe a method to infer dense depth from camera motion and sparse depth as estimated using a visual-inertial odometry system. Unlike other scenarios using point clouds from l…
Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training
Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather than fixing the class…
Meta-Learning with Differentiable Convex Optimization
Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran +1
Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively traine…
The Information Complexity of Learning Tasks, their Structure and their Distance
Alessandro Achille, Giovanni Paolini, Glen Mbeng +1
We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational for the practice of transfer learni…
Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction
Alex Wong, Byung-Woo Hong, Stefano Soatto
Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant…
Zero Shot Learning with the Isoperimetric Loss
Shay Deutsch, Andrea Bertozzi, Stefano Soatto
We introduce the isoperimetric loss as a regularization criterion for learning the map from a visual representation to a semantic embedding, to be used to transfer knowledge to unk…
Task2Vec: Task Embedding for Meta-Learning
Alessandro Achille, Michael Lam, Rahul Tewari +5
We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a d…
Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
Tong He, Stefano Soatto
We present a method to infer 3D pose and shape of vehicles from a single image. To tackle this ill-posed problem, we optimize two-scale projection consistency between the generated…
GeoNet: Deep Geodesic Networks for Point Cloud Analysis
Tong He, Haibin Huang, Li Yi +4
Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we in…
Dense Depth Posterior (DDP) from Single Image and Sparse Range
Yanchao Yang, Alex Wong, Stefano Soatto
We present a deep learning system to infer the posterior distribution of a dense depth map associated with an image, by exploiting sparse range measurements, for instance from a li…
Unsupervised Moving Object Detection via Contextual Information Separation
Yanchao Yang, Antonio Loquercio, Davide Scaramuzza +1
We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from e…