Good Practice in Large-Scale Learning for Image Classification

By Zeynep Akata, Florent Perronnin, Zaïd Harchaoui, Cordelia Schmid. 2014

121 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bernt Schiele
2. Luc Van Gool
3. Armand Joulin
4. Trevor Darrell
5. Juergen Gall
6. Matthias Hein
7. Abhinav Kumar Gupta
8. Quoc V. Le

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Bernt Schiele
3. Dacheng Tao
4. Trevor Darrell
5. Xiaogang Wang
6. Andrew Zisserman
7. Ming-Hsuan Yang
8. Jitendra Malik

Citations in the corpus

• Learning Visual Features from Large Weakly Supervised Data (2015, background): “Third, it is essential to sample data uniformly per class to learn good visual features [2].”
• Loss Functions for Top-k Error: Analysis and Insights (2015, methodology): “The multiclass hinge loss has also been shown to be competitive in large-scale image classification [2].”
• Incremental Learning of Random Forests for Large-Scale Image Classification (2016, methodology): “they are now outperformed on large-scale datasets both in accuracy and in training time by nearest neighbor or multiclass approaches [4], [5], [6], [7].”
• Incremental Learning Using Conditional Adversarial Networks (2019, methodology): “Among various classifiers, SVM [2] is the most popular and has been widely applied to large scale image classification [1].”
• Disease Diagnosis in Smart Healthcare: Innovation, Technologies and Applications (2017, background): “Some of the difficulties are: large dimensionality of feature vectors [50], bias/variance dilemma [51], input and output noise [52], large-scale training data [53], data heterogeneity [54], data redundancy [55] and non-linearity among features [56].”
• Incremental Learning of NCM Forests for Large-Scale Image Classification (2014, methodology): “For comparison, we used nearest class mean classifier (NCM), NCM with metric learning [14] (MET+NCM), structured-output multi-class SVM [1] (MC SVM), k-nearest neighbors (KNN), and Random Forests with axis-aligned splitting functions [5] (RF), which performed better than RF with random linear…”
• Binary Stochastic Representations for Large Multi-class Classification (2017, background): “Note that one versus all techniques are, up to now, among the strongest contender in terms of classification performances for large number of classes [3].”
• From categories to subcategories: Large-scale image classification with partial class label refinement (2015, methodology): “18 accuracy and outperforms multiclass SVM [3] (71.”