research
∙
08/09/2023
Which Tokens to Use? Investigating Token Reduction in Vision Transformers
Since the introduction of the Vision Transformer (ViT), researchers have...
share
research
∙
07/03/2023
Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data
Conformal prediction has emerged as a rigorous means of providing deep l...
research
∙
03/24/2023
Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers
Vision Transformers (ViT) have shown their competitive advantages perfor...
research
∙
02/10/2023
GCNet: Probing Self-Similarity Learning for Generalized Counting Network
The class-agnostic counting (CAC) problem has caught increasing attentio...
research
∙
01/19/2023
Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition
Binary neural networks, i.e., neural networks whose parameters and activ...
research
∙
07/19/2022
Bounding generalization error with input compression: An empirical study with infinite-width networks
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) ...
research
∙
06/27/2022
Monitoring Shortcut Learning using Mutual Information
The failure of deep neural networks to generalize to out-of-distribution...
research
∙
04/29/2022
Understanding the impact of image and input resolution on deep digital pathology patch classifiers
We consider annotation efficient learning in Digital Pathology (DP), whe...
research
∙
01/29/2022
DeepRNG: Towards Deep Reinforcement Learning-Assisted Generative Testing of Software
Although machine learning (ML) has been successful in automating various...
research
∙
01/24/2022
On Evaluation Metrics for Graph Generative Models
In image generation, generative models can be evaluated naturally by vis...
research
∙
01/07/2022
Learning with less labels in Digital Pathology via Scribble Supervision from natural images
A critical challenge of training deep learning models in the Digital Pat...
research
∙
11/23/2021
Domain-Agnostic Clustering with Self-Distillation
Recent advancements in self-supervised learning have reduced the gap bet...
research
∙
11/05/2021
An Empirical Study of Neural Kernel Bandits
Neural bandits have enabled practitioners to operate efficiently on prob...
research
∙
10/29/2021
Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning
Discovering a solution in a combinatorial space is prevalent in many rea...
research
∙
10/25/2021
Parameter Prediction for Unseen Deep Architectures
Deep learning has been successful in automating the design of features i...
research
∙
04/01/2021
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
We tackle the challenge of learning a distribution over complex, realist...
research
∙
03/31/2021
The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation
We consider the task of semi-supervised semantic segmentation, where we ...
research
∙
03/05/2021
LOHO: Latent Optimization of Hairstyles via Orthogonalization
Hairstyle transfer is challenging due to hair structure differences in t...
research
∙
01/21/2021
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
In this paper we introduce a Transformer-based approach to video object ...
research
∙
12/21/2020
Building LEGO Using Deep Generative Models of Graphs
Generative models are now used to create a variety of high-quality digit...
research
∙
11/12/2020
Evaluating Curriculum Learning Strategies in Neural Combinatorial Optimization
Neural combinatorial optimization (NCO) aims at designing problem-indepe...
research
∙
11/05/2020
Identifying and interpreting tuning dimensions in deep networks
In neuroscience, a tuning dimension is a stimulus attribute that account...
research
∙
07/30/2020
Instance Selection for GANs
Recent advances in Generative Adversarial Networks (GANs) have led to th...
research
∙
07/11/2020
Generative Graph Perturbations for Scene Graph Prediction
Inferring objects and their relationships from an image is useful in man...
research
∙
06/30/2020
Enabling Continual Learning with Differentiable Hebbian Plasticity
Continual learning is the problem of sequentially learning new tasks or ...
research
∙
05/17/2020
Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
Scene graph generation (SGG) aims to predict graph-structured descriptio...
research
∙
04/28/2020
Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task
Human-computer interactive systems that rely on machine learning are bec...
research
∙
04/02/2020
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis
We consider the problem of distance metric learning (DML), where the tas...
research
∙
11/27/2019
Learning with less data via Weakly Labeled Patch Classification in Digital Pathology
In Digital Pathology (DP), labeled data is generally very scarce due to ...
research
∙
10/28/2019
Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking
Deep neural networks require collecting and annotating large amounts of ...
research
∙
10/11/2019
A Nonparametric Bayesian Model for Sparse Temporal Multigraphs
As the availability and importance of temporal interaction data–such as ...
research
∙
09/23/2019
Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions
Graphs evolving over time are a natural way to represent data in many do...
research
∙
07/21/2019
Image Classification with Hierarchical Multigraph Networks
Graph Convolutional Networks (GCNs) are a class of general models that c...
research
∙
07/11/2019
On the Evaluation of Conditional GANs
Conditional Generative Adversarial Networks (cGANs) are finding increasi...
research
∙
05/08/2019
Understanding attention in graph neural networks
We aim to better understand attention over nodes in graph neural network...
research
∙
05/06/2019
Batch Normalization is a Cause of Adversarial Vulnerability
Batch normalization (batch norm) is often used in an attempt to stabiliz...
research
∙
02/21/2019
Similarity Learning Networks for Animal Individual Re-Identification - Beyond the Capabilities of a Human Observer
The ability of a researcher to re-identify (re-ID) an animal individual ...
research
∙
01/15/2019
SISC: End-to-end Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells
Objective: Lung cancer is the leading cause of cancer-related death worl...
research
∙
11/30/2018
Adversarial Examples as an Input-Fault Tolerance Problem
We analyze the adversarial examples problem in terms of a model's fault ...
research
∙
11/24/2018
Keep Drawing It: Iterative language-based image generation and editing
Conditional text-to-image generation approaches commonly focus on genera...
research
∙
11/23/2018
Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
Spectral Graph Convolutional Networks (GCNs) are a generalization of con...
research
∙
11/19/2018
Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data
The ability of a researcher to re-identify (re-ID) an individual animal ...
research
∙
07/24/2018
Self-Paced Learning with Adaptive Deep Visual Embeddings
Selecting the most appropriate data examples to present a deep neural ne...
research
∙
07/03/2018
Stochastic Layer-Wise Precision in Deep Neural Networks
Low precision weights, activations, and gradients have been proposed as ...
research
∙
07/02/2018
Leveraging Uncertainty Estimates for Predicting Segmentation Quality
The use of deep learning for medical imaging has seen tremendous growth ...
research
∙
04/10/2018
Adversarial Training Versus Weight Decay
Performance-critical machine learning models should be robust to input p...
research
∙
03/28/2018
Deep Learning Object Detection Methods for Ecological Camera Trap Data
Deep learning methods for computer vision tasks show promise for automat...
research
∙
03/26/2018
Generalized Hadamard-Product Fusion Operators for Visual Question Answering
We propose a generalized class of multimodal fusion operators for the ta...
research
∙
02/23/2018
Real-Time End-to-End Action Detection with Two-Stream Networks
Two-stream networks have been very successful for solving the problem of...
research
∙
02/22/2018