Search Results for author:
Found 14 papers, 4 papers with code
Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space
However, fine-tuning a transfer model with data augmentation in the raw input space has a high computational cost to run the full network for every augmented input.
Coarse2Fine: A Two-stage Training Method for Fine-grained Visual Classification
Small inter-class and large intra-class variations are the main challenges in fine-grained visual classification.
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
Few-shot learning is an important area of research.
Gradient Agreement as an Optimization Objective for Meta-Learning
Therefore, the degree of the contribution of a task to the parameter updates is controlled by introducing a set of weights on the loss function of the tasks.
A Meta-Learning Approach for Custom Model Training
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks.
End-to-End Integration of a Convolution Network, Deformable Parts Model and Non-Maximum Suppression
In this paper, we propose a new model that combines these two approaches, obtaining the advantages of each.
Unsupervised Feature Learning from Temporal Data
Current state-of-the-art classification and detection algorithms rely on supervised training.
Unsupervised Learning of Spatiotemporally Coherent Metrics
Current state-of-the-art classification and detection algorithms rely on supervised training.
End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression
In this paper, we propose a new model that combines these two approaches, obtaining the advantages of each.
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling.
Ranked #71 on
Monocular Depth Estimation
on NYU-Depth V2
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
Predicting depth is an essential component in understanding the 3D geometry of a scene.
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very competitive results for the detection and classifications tasks.
Learning Factored Representations in a Deep Mixture of Experts
In addition, we see that the different combinations are in use when the model is applied to a dataset of speech monophones.
Understanding Deep Architectures using a Recursive Convolutional Network
A key challenge in designing convolutional network models is sizing them appropriately.
