Caltech-256 Object Category Dataset

By G. Griffin, Alex Holub, Pietro Perona. 2007

2,926 citations recorded by the source corpus.

How researchers see this paper

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

In Evaluation & Benchmarks

Citations in the corpus

Very Deep Convolutional Networks for Large-Scale Image Recognition (2014, methodology): “On Caltech-256 we also generatd 3 splits, each of which contains 60 training images per class (and the rest is used for testing).”
ImageNet Large Scale Visual Recognition Challenge (2014, background): “Caltech 256 (Griffin et al., 2007) increased the number of object classes to 256 and added images with greater scale and background variability.”
Microsoft COCO: Common Objects in Context (2014, background): “enging directions. The creation of ground truth stereo and optical ﬂow datasets [20], [21] helped stimulate a ﬂood of interest in these areas. The early evolution of object recognition datasets [22], [23], [24] facilitated the direct comparison of hundreds of image recognition algorithms while simul”
SUN database: Large-scale scene recognition from abbey to zoo (2010, background): “Whereas the fields of computer vision and cognitive science have developed several databases to organize knowledge about object categories [10, 28], a comprehensive database of real world scenes does not currently exist (the largest available dataset of scene categories contains only 15 classes).”
The Kinetics Human Action Video Dataset (2017, background): “Caltech 256 [10], does not perform well when tested on another, e.”
Return of the Devil in the Details: Delving Deep into Convolutional Nets (2014, methodology): “Finally, we also evaluate over the Caltech-101 and Caltech-256 image classiﬁcation benchmarks [21], [22].”
YouTube-8M: A Large-Scale Video Classification Benchmark (2016, neutral): “ORK Image benchmarks have played a signiﬁcant role in advancing computer vision algorithms for image understanding. Starting from a number of well labeled small-scale datasets such as Caltech 101/256 [8,10], MSRC [32], PASCAL [7], image understanding research has rapidly advanced to utilizing larger”
Learning Deep Features for Discriminative Localization (2015, background): “3.2 (i.e., thresholding) to first identify bird bounding boxes in both the train and test sets.”
Learning Transferable Features with Deep Adaptation Networks (2015, methodology): “This dataset consists of the 10 common categories shared by the Office31 and Caltech-256 (C) (Griffin et al., 2007) datasets and is widely adopted in transfer learning methods (Long et al.”
Genetic CNN (2017, methodology): “Finally, we evaluate the transfer ability of the GeNets on the Caltech256 dataset [12].”
Domain Adaptation with Conditional Transferable Components (2016, methodology): “, 2010) and the Caltech256 (Griffin et al., 2007) dataset.”
Towards Explainable Deep Neural Networks (xDNN) (2019, methodology): “Caletch-256 has 30,607 images divided into 257 object categories (one of which is the background) [16].”
Interpreting Deep Visual Representations via Network Dissection (2017, neutral): “We include indoor67 [53], sun397 [54] and caltech256 [55].”
Deep Meta-Learning: Learning to Learn in the Concept Space (2018, methodology): “elines in DEML process two different formats of data. For concept discrimination tasks, we perform experiments on a subset of ImageNet (Deng et al.,2009). Imagenet (Vinyals et al.,2016), Caltech-256 (Grifﬁn et al., 2007), CIFAR-100 (Krizhevsky,2009), and CUB-200 (Wah et al.,2011). 4.1.1. DATASETS FO”