Search Results for author:
Found 35 papers, 24 papers with code
ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images
We apply it to weakly supervised medical image segmentation by training the 2D encoder to output high values for slices containing the regions of interest.
SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots.
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets.
What to Hide from Your Students: Attention-Guided Masked Image Modeling
In this work, we argue that image token masking differs from token masking in text, due to the amount and correlation of tokens in an image.
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image.
Ranked #18 on
Semi-Supervised Image Classification
on ImageNet - 1% labeled data
(Top 5 Accuracy metric)
Learning Representations by Predicting Bags of Visual Words
Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts, here called visual words.
QUEST: Quantized embedding space for transferring knowledge
Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network.
Deep Tone Mapping Operator for High Dynamic Range Images
In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output.
Boosting Few-Shot Visual Learning with Self-Supervision
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data.
Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning
The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes.
Exploring Weight Symmetry in Deep Neural Networks
We propose several ways to impose local symmetry in recurrent and convolutional neural networks, and show that our symmetry parameterizations satisfy universal approximation property for single hidden layer networks.
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.
Dynamic Few-Shot Visual Learning without Forgetting
In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories).
Ranked #2 on
Few-Shot Image Classification
on ImageNet (1-shot)
Unsupervised Representation Learning by Predicting Image Rotations
However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale.
Ranked #126 on
Self-Supervised Image Classification
on ImageNet
GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
Deep learning on graphs has become a popular research topic with many applications.
Newton-type Methods for Inference in Higher-Order Markov Random Fields
Linear programming relaxations are central to {\sc map} inference in discrete Markov Random Fields.
DiracNets: Training Very Deep Neural Networks Without Skip-Connections
Deep neural networks with skip-connections, such as ResNet, show excellent performance in various image classification benchmarks.
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
A number of problems can be formulated as prediction on graph-structured data.
Rotation equivariant vector field networks
In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image.
Ranked #8 on
Multi-tissue Nucleus Segmentation
on Kumar
Breast Tumour Classification
Colorectal Gland Segmentation:
+5
Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling
Instead, we propose a generic architecture that decomposes the label improvement task to three steps: 1) detecting the initial label estimates that are incorrect, 2) replacing the incorrect labels with new ones, and finally 3) refining the renewed labels by predicting residual corrections w. r. t.
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
Attention plays a critical role in human visual experience.
Ranked #39 on
Knowledge Distillation
on ImageNet
A Deep Metric for Multimodal Registration
Multimodal registration is a challenging problem in medical imaging due the high variability of tissue appearance under different imaging modalities.
OnionNet: Sharing Features in Cascaded Deep Classifiers
The focus of our work is speeding up evaluation of deep neural networks in retrieval scenarios, where conventional architectures may spend too much time on negative examples.
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization
We extensively evaluate our AttractioNet approach on several image datasets (i. e. COCO, PASCAL, ImageNet detection and NYU-Depth V2 datasets) reporting on all of them state-of-the-art results that surpass the previous work in the field by a significant margin and also providing strong empirical evidence that our approach is capable to generalize to unseen categories.
Wide Residual Networks
Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance.
Ranked #12 on
Image Classification
on SVHN
HARF: Hierarchy-Associated Rich Features for Salient Object Detection
This leads to a rich feature representation, which is able to represent the context of the whole object/background and is much more discriminative as well as robust for salient object detection.
Object Detection via a Multi-Region and Semantic Segmentation-Aware CNN Model
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features.
LocNet: Improving Localization Accuracy for Object Detection
We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems.
Object detection via a multi-region & semantic segmentation-aware CNN model
We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features.
Learning to Compare Image Patches via Convolutional Neural Networks
In this paper we show how to learn directly from image data (i. e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems.
Inference by Learning: Speeding-up Graphical Model Optimization via a Coarse-to-Fine Cascade of Pruning Classifiers
We propose a general and versatile framework that significantly speeds-up graphical model optimization while maintaining an excellent solution accuracy.
Playing with Duality: An Overview of Recent Primal-Dual Approaches for Solving Large-Scale Optimization Problems
Optimization methods are at the core of many problems in signal/image processing, computer vision, and machine learning.
Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching
While machine learning has been instrumental to the ongoing progress in most areas of computer vision, it has not been applied to the problem of stereo matching with similar frequency or success.
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.
Clustering via LP-based Stabilities
To deal with the most critical issue in a center-based clustering algorithm (selection of cluster centers), we also introduce the notion of stability of a cluster center, which is a well defined LP-based quantity that plays a key role to our algorithm's success.
