116 citations · 1.1k across the 96 of their papers we have counts for
19 papers · 1 filter
LQF: Linear Quadratic Fine-Tuning
Alessandro Achille, Aditya Golatkar, Avinash Ravichandran +2
Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial c…
Mixed-Privacy Forgetting in Deep Networks
Aditya Golatkar, Alessandro Achille, Avinash Ravichandran +2
We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks,…
Positive-Congruent Training: Towards Regression-Free Model Updates
Sijie Yan, Yuanjun Xiong, Kaustav Kundu +5
Reducing inconsistencies in the behavior of different versions of an AI system can be as important in practice as reducing its overall error. In image classification, sample-wise i…
Spectral Embedding of Graph Networks
Shay Deutsch, Stefano Soatto
We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure. The embedding is based on a generalized graph Laplacian,…
Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations
Alex Wong, Mukund Mundhra, Stefano Soatto
We study the effect of adversarial perturbations of images on the estimates of disparity by deep learning models trained for stereo. We show that imperceptible additive perturbatio…
Predicting Training Time Without Training
Luca Zancato, Alessandro Achille, Avinash Ravichandran +2
We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. To do so, we leverage…
DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping
Yanchao Yang, Brian Lai, Stefano Soatto
We describe an unsupervised method to detect and segment portions of images of live scenes that, at some point in time, are seen moving as a coherent whole, which we refer to as ob…
Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance
Alexander Schperberg, Kenny Chen, Stephanie Tsuei +5
In this paper, we propose an online path planning architecture that extends the model predictive control (MPC) formulation to consider future location uncertainties for safer navig…
Targeted Adversarial Perturbations for Monocular Depth Prediction
Alex Wong, Safa Cicek, Stefano Soatto
We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to s…
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
Tong He, John Collomosse, Hailin Jin +1
We propose Geo-PIFu, a method to recover a 3D mesh from a monocular color image of a clothed person. Our method is based on a deep implicit function-based representation to learn l…
Stochastic batch size for adaptive regularization in deep network optimization
Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong
We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive re…
FDA: Fourier Domain Adaptation for Semantic Segmentation
Yanchao Yang, Stefano Soatto
We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectru…
Learning to Manipulate Individual Objects in an Image
Yanchao Yang, Yutong Chen, Stefano Soatto
We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects onl…
Phase Consistent Ecological Domain Adaptation
Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi +1
We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a differe…
Towards Backward-Compatible Representation Learning
Yantao Shen, Yuanjun Xiong, Wei Xia +1
We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network ar…
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations
Aditya Golatkar, Alessandro Achille, Stefano Soatto
We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout fu…
Rethinking the Hyperparameters for Fine-tuning
Hao Li, Pratik Chaudhari, Hao Yang +4
Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad…
Multi-Task Incremental Learning for Object Detection
Xialei Liu, Hao Yang, Avinash Ravichandran +2
Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementa…
Incremental Meta-Learning via Indirect Discriminant Alignment
Qing Liu, Orchid Majumder, Alessandro Achille +3
Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation b…