Learning about Canonical Views from Internet Image Collections

29 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.

Webly Supervised Learning of Convolutional Networks (2015, methodology): “After seventh layer, another fully connected layer is used to predict class labels.”
Why do deep convolutional networks generalize so poorly to small image transformations? (2018, neutral): “Consistent with previous results on "dataset bias" [37, 33, 2, 44, 45, 32] we find that the ImageNet dataset is not invariant to translations and rescalings.”
On the "steerability" of generative adversarial networks (2019, background): “Dataset biases partly comes from human preferences in taking photos: we typically capture images in specific “canonical” views that are not fully representative of the entire visual world [19, 12].”
Learning visual biases from human imagination (2014, methodology): “We extend ideas [24] to use computer vision to analyze these biases.”
Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes (2017, background): “Internet image collections of particular objects were shown to mirror canonical viewpoint preferences by people [24].”
Concept Generalization in Visual Representation Learning (2020, unknown): “We need these datasets to have diverse object-level images [2] and to be as less biased as possible, e.g., towards canonical views [39].”
Learning Everything about Anything: Webly-Supervised Visual Concept Learning (2014, background): “While the results are not perfect, the top ranked images for most queries tend to be very relevant [32].”