Small Data Image Classification
57 papers with code • 12 benchmarks • 9 datasets
Supervised image classification with tens to hundreds of labeled training examples.
Benchmarks
These leaderboards are used to track progress in Small Data Image Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
CIFAR-10
CIFAR-100
CUB-200-2011
UCF-Crime
TMED
Ecoli
DEIC Benchmark
WikiChurches
Latest papers
Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response
Multimedia content in social media platforms provides significant information during disaster events.
Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data
ieee8023/covid-chestxray-dataset
•
•
The possibility to use widespread and simple chest X-ray (CXR) imaging for early screening of COVID-19 patients is attracting much interest from both the clinical and the AI community.
Finding Covid-19 from Chest X-rays using Deep Learning on a Small Dataset
On a test set of 20 unseen COVID-19 cases all were correctly classified and more than 95% of 4171 other pneumonia examples were correctly classified.
Generative Latent Implicit Conditional Optimization when Learning from Small Sample
IdanAzuri/glico-learning-small-sample
•
•
GLICO learns a mapping from the training examples to a latent space and a generator that generates images from vectors in the latent space.
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location
oskyhn/CNNs-Without-Borders
•
•
CVPR 2020
In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant.
Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
zhang64-llnl/Mix-n-Match-Calibration
•
•
We show that none of the existing methods satisfy all three requirements, and demonstrate how Mix-n-Match calibration strategies (i. e., ensemble and composition) can help achieve remarkably better data-efficiency and expressive power while provably maintaining the classification accuracy of the original classifier.
Unbiased Mean Teacher for Cross-domain Object Detection
We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies.
Rigid-Soft Interactive Learning for Robust Grasping
bionicdl-sustech/DeepClawBenchmark
•
•
We use soft, stuffed toys for training, instead of everyday objects, to reduce the integration complexity and computational burden and exploit such rigid-soft interaction by changing the gripper fingers to the soft ones when dealing with rigid, daily-life items such as the Yale-CMU-Berkeley (YCB) objects.
Data Structures & Algorithms for Exact Inference in Hierarchical Clustering
In contrast to existing methods, we present novel dynamic-programming algorithms for \emph{exact} inference in hierarchical clustering based on a novel trellis data structure, and we prove that we can exactly compute the partition function, maximum likelihood hierarchy, and marginal probabilities of sub-hierarchies and clusters.
Performance Analysis of Semi-supervised Learning in the Small-data Regime using VAEs
varunmannam/Papers_with_Code
•
•
Extracting large amounts of data from biological samples is not feasible due to radiation issues, and image processing in the small-data regime is one of the critical challenges when working with a limited amount of data.
