Search Results for author:
Found 28 papers, 18 papers with code
Multimodal Distillation for Egocentric Action Recognition
The goal of this work is to retain the performance of such a multimodal approach, while using only the RGB frames as input at inference time.
Document Understanding Dataset and Evaluation (DUDE)
We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks.
Understanding metric-related pitfalls in image analysis validation
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice.
Students taught by multimodal teachers are superior action recognizers
Our approach is based on multimodal knowledge distillation, featuring a multimodal teacher (in the current experiments trained only using object detections, optical flow and RGB frames) and a unimodal student (using only RGB frames as input).
Metrics reloaded: Recommendations for image analysis validation
The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint - a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output.
Predicting Physical World Destinations for Commands Given to Self-Driving Cars
However, surveys have shown that giving more control to an AI in self-driving cars is accompanied by a degree of uneasiness by passengers.
Common Limitations of Image Processing Metrics: A Picture Story
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation.
Learning to ground medical text in a 3D human atlas
In this paper, we develop a method for grounding medical text into a physically meaningful and interpretable space corresponding to a human atlas.
R-GAP: Recursive Gradient Attack on Privacy
However, recent optimization-based gradient attacks show that raw data can often be accurately recovered from gradients.
Commands 4 Autonomous Vehicles (C4AV) Workshop Summary
In this work, we deviate from recent, popular task settings and consider the problem under an autonomous vehicle scenario.
Ranked #3 on
Referring Expression Comprehension
on Talk2Car
Self-supervised context-aware COVID-19 document exploration through atlas grounding
In this paper, we aim to develop a self-supervised grounding of Covid-related medical text based on the actual spatial relationships between the referred anatomical concepts.
Semixup: In- and Out-of-Manifold Regularization for Deep Semi-Supervised Knee Osteoarthritis Severity Grading from Plain Radiographs
Finally, when compared to a well-tuned fully supervised baseline that yielded a balanced accuracy (BA) of $70. 9\pm0. 8%$ on the test set, Semixup had comparable performance -- BA of $71\pm0. 8%$ $(p=0. 368)$ while requiring $6$ times less labeled data.
Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice
First, we investigate the theoretical differences in a risk minimization framework and question the existence of a weighted cross-entropy loss with weights theoretically optimized to surrogate Dice or Jaccard.
Generating superpixels using deep image representations
Superpixel algorithms are a common pre-processing step for computer vision algorithms such as segmentation, object tracking and localization.
Scattering Networks for Hybrid Representation Learning
In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning tasks, while making progress towards constructing more interpretable CNNs.
Learning to Discover Sparse Graphical Models
Learning this function brings two benefits: it implicitly models the desired structure or sparsity properties to form suitable priors, and it can be tailored to the specific problem of edge structure discovery, rather than maximizing data likelihood.
A Convex Surrogate Operator for General Non-Modular Loss Functions
This convex surro-gate is based on a submodular-supermodular decomposition for which the existence and uniqueness is proven in this paper.
A U-statistic Approach to Hypothesis Testing for Structure Discovery in Undirected Graphical Models
For some class of probability distributions, an edge between two variables is present if and only if the corresponding entry in the precision matrix is non-zero.
The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses
The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling.
A low variance consistent test of relative dependency
Such a test enables us to determine whether one source variable is significantly more dependent on a first target variable or a second.
B-test: A Non-parametric, Low Variance Kernel Two-sample Test
We propose a family of maximum mean discrepancy (MMD) kernel two-sample tests that have low sample complexity and are consistent.
B-tests: Low Variance Kernel Two-Sample Tests
A family of maximum mean discrepancy (MMD) kernel two-sample tests is introduced.
Fine-Grained Visual Classification of Aircraft
This paper introduces FGVC-Aircraft, a new dataset containing 10, 000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy.
A Note on k-support Norm Regularized Risk Minimization
The k-support norm has been recently introduced to perform correlated sparsity regularization.
Perceptron Learning of SAT
Provided this mapping is based on polynomial time computable statistics of a sentence, we show that the existance of a margin between these data points implies the existance of a polynomial time solver for that SAT subset based on the Davis-Putnam-Logemann-Loveland algorithm.
Simultaneous Object Detection and Ranking with Weak Supervision
A standard approach to learning object category detectors is to provide strong supervision in the form of a region of interest (ROI) specifying each instance of the object in the training images.
Augmenting Feature-driven fMRI Analyses: Semi-supervised learning and resting state activity
Resting state activity is brain activation that arises in the absence of any task, and is usually measured in awake subjects during prolonged fMRI scanning sessions where the only instruction given is to close the eyes and do nothing.
Learning Taxonomies by Dependence Maximization
We introduce a family of unsupervised algorithms, numerical taxonomy clustering, to simultaneously cluster data, and to learn a taxonomy that encodes the relationship between the clusters.
