Discovering Internal Representations from Object-CNNs Using Population Encoding

17 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.

What makes ImageNet good for transfer learning? (2016, background): “Another line of prior work investigated questions such as how distributed are CNN representations [2, 43], what is the the effect of feature transformations such as binarization [2, 14], how do CNN features change with systematic variations in scene factors [3], how invariant are features to differe”
Adversarial Examples for Semantic Segmentation and Object Detection (2017, background): “Currently, one of the most popular object detection pipeline [28][5][17] involves first generating a number of proposals of different scales and positions, classifying each of them, and performing post-processing such as nonmaximal suppression (NMS).”
Deep Nets: What have They Ever Done for Vision? (2018, background): “scales show that clusters of feature responses are often interpretable and correspond to subparts of the objects (Wang et al., 2015).”
Object Recognition with and without Objects (2016, methodology): “In this work, we will use a much simpler way of visualization which is inspired by [Wang et al., 2015a].”
Visualizations of Deep Neural Networks in Computer Vision: A Survey (2017, methodology): “[71] 2015 Architecture assessment Pixel displays Detection CNNs PASCAL3D+”