Search Results for author:
Found 31 papers, 19 papers with code
Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
Adversarial training is widely used to make classifiers robust to a specific threat or adversary, such as $\ell_p$-norm bounded perturbations of a given $p$-norm.
Back to the Source: Diffusion-Driven Adaptation To Test-Time Corruption
We update the target data instead, and project all test inputs toward the source domain with a generative diffusion model.
Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods
Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training.
Back to the Source: Diffusion-Driven Test-Time Adaptation
We instead update the target data, by projecting all test inputs toward the source domain with a generative diffusion model.
Object discovery and representation networks
The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks.
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
Adaptive defenses, which optimize at test time, promise to improve adversarial robustness.
HiP: Hierarchical Perceiver
This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video.
On-target Adaptation
Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain.
Perceiver IO: A General Architecture for Structured Inputs & Outputs
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015
(Average End-Point Error metric)
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
Adversarial attacks optimize against models to defeat defenses.
Anytime Dense Prediction with Confidence Adaptivity
A cascade of "exits" is attached to the model to make multiple predictions.
It Is Likely That Your Loss Should be a Likelihood
Joint optimization of these "likelihood parameters" with model parameters can adaptively tune the scales and shapes of losses in addition to the strength of regularization.
Tent: Fully Test-time Adaptation by Entropy Minimization
A model must adapt itself to generalize to new and different data during testing.
Exploring Simple and Transferable Recognition-Aware Image Processing
Interestingly, the processing model's ability to enhance recognition quality can transfer when evaluated on models of different architectures, recognized categories, tasks and training datasets.
Blurring Structure and Learning to Optimize and Adapt Receptive Fields
Adapting receptive fields by dynamic Gaussian structure further improves results, equaling the accuracy of free-form deformation while improving efficiency.
Dynamic Scale Inference by Entropy Minimization
Given the variety of the visual world there is not one true scale for recognition: objects may appear at drastically different sizes across the visual field.
Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields
Adapting receptive fields by dynamic Gaussian structure further improves results, equaling the accuracy of free-form deformation while improving efficiency.
Efficient Receptive Field Learning by Dynamic Gaussian Structure
The visual world is vast and varied, but its variations divide into structured and unstructured factors.
Infinite Mixture Prototypes for Few-Shot Learning
We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning.
Variadic Learning by Bayesian Nonparametric Deep Embedding
On the standard few-shot learning benchmarks of Omniglot and mini-ImageNet, BANDE equals or improves on the state-of-the-art for semi-supervised classification.
Few-Shot Segmentation Propagation with Guided Networks
Learning-based methods for visual segmentation have made progress on particular types of segmentation tasks, but are limited by the necessary supervision, the narrow definitions of fixed tasks, and the lack of control during inference for correcting errors.
Zero-Shot Visual Imitation
In our framework, the role of the expert is only to communicate the goals (i. e., what to imitate) during inference.
Deep Layer Aggregation
We augment standard architectures with deeper aggregation to better fuse information across layers.
Loss is its own Reward: Self-Supervision for Reinforcement Learning
Reinforcement learning optimizes policies for expected cumulative reward.
Clockwork Convnets for Video Semantic Segmentation
Recent years have seen tremendous progress in still-image segmentation; however the na\"ive application of these state-of-the-art algorithms to every video frame requires considerable computation and ignores the temporal continuity inherent in video.
Fully Convolutional Networks for Semantic Segmentation
Convolutional networks are powerful visual models that yield hierarchies of features.
Ranked #2 on
Semantic Segmentation
on NYU Depth v2
(Mean Accuracy metric)
Fine-grained pose prediction, normalization, and recognition
Pose variation and subtle differences in appearance are key challenges to fine-grained classification.
Fully Convolutional Multi-Class Multiple Instance Learning
We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network.
Fully Convolutional Networks for Semantic Segmentation
Convolutional networks are powerful visual models that yield hierarchies of features.
Ranked #2 on
Semantic Segmentation
on SkyScapes-Lane
cuDNN: Efficient Primitives for Deep Learning
To address this problem, we have created a library similar in intent to BLAS, with optimized routines for deep learning workloads.
Caffe: Convolutional Architecture for Fast Feature Embedding
The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.
