Search Results for author:
Found 18 papers, 10 papers with code
DARTS: Double Attention Reference-based Transformer for Super-resolution
Our work demonstrates how the attention mechanism can be adapted for the particular requirements of reference-based image super-resolution, significantly simplifying the architecture and training pipeline.
Extending the WILDS Benchmark for Unsupervised Adaptation
Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data and can often be obtained from distributions beyond the source distribution as well.
Global Wheat Head Dataset 2021: more diversity to improve the benchmarking of wheat head localization methods
We now release a new version of the Global Wheat Head Detection (GWHD) dataset in 2021, which is bigger, more diverse, and less noisy than the 2020 version.
Global Wheat Challenge 2020: Analysis of the competition design and winning models
Data competitions have become a popular approach to crowdsource new data analysis methods for general and specialized data science problems.
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild.
Pruning Convolutional Filters using Batch Bridgeout
However, the huge size of contemporary models results in large inference costs and limits their use on resource-limited devices.
Unsupervised Domain Adaptation For Plant Organ Counting
Supervised learning is often used to count objects in images, but for counting small, densely located objects, the required image annotations are burdensome to collect.
AutoCount: Unsupervised Segmentation and Counting of Organs in Field Images
Counting plant organs such as heads or tassels from outdoor imagery is a popular benchmark computer vision task in plant phenotyping, which has been previously investigated in the literature using state-of-the-art supervised deep learning techniques.
Multi-Scale Weight Sharing Network for Image Recognition
In this paper, we explore the idea of weight sharing over multiple scales in convolutional networks.
Crop Lodging Prediction from UAV-Acquired Images of Wheat and Canola using a DCNN Augmented with Handcrafted Texture Features
In this paper, we propose a deep convolutional neural network (DCNN) architecture for lodging classification using five spectral channel orthomosaic images from canola and wheat breeding trials.
Sparseout: Controlling Sparsity in Deep Networks
We found that sparsity of the activations is favorable for language modelling performance while image classification benefits from denser activations.
Global Sum Pooling: A Generalization Trick for Object Counting with Small Datasets of Large Images
This generalization capability allows GSP to avoid both patchwise cancellation and overfitting by training on small patches and inference on full-resolution images as a whole.
Semantic Binary Segmentation using Convolutional Networks without Decoders
In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation.
Bridgeout: stochastic bridge regularization for deep neural networks
Stochastic methods such as Dropout and Shakeout, in expectation, are equivalent to imposing a ridge and elastic-net penalty on the model parameters, respectively.
Improving Object Counting with Heatmap Regulation
Adding HR to a simple VGG front-end improves performance on all these benchmarks compared to a simple one-look baseline model and results in state-of-the-art performance for car counting.
DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning
In this paper, we investigate estimating emergence and biomass traits from color images and elevation maps of wheat field plots.
Leaf Counting with Deep Convolutional and Deconvolutional Networks
In this paper, we investigate the problem of counting rosette leaves from an RGB image, an important task in plant phenotyping.
Prediction of Muscle Activations for Reaching Movements using Deep Neural Networks
In this work, we investigate deep autoencoders for the prediction of muscle activation trajectories for point-to-point reaching movements.
