Stefano Soatto

Stefano Soatto


Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 January 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
AAAlessandro Achille
Alessandro Achille
SSStefano Soatto
Stefano Soatto
The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization term, which is related to injecting multiplicative noise in the activations of a Deep Neural Network, a special case of which is the common practice of dropout. We show that our regularized loss function can be efficiently minimized using Information Dropout, a generalization of dropout rooted in information-theoretic principles that automatically adapts to the data and can better exploit architectures of limited capacity. When the task is the reconstruction of the input, our loss function yields a Variational Autoencoder as a special case, thus providing a link between representation learning, information theory and variational inference. Finally, we prove that we can promote the creation of disentangled representations simply by enforcing a factorized prior, a fact that has been observed empirically in recent work. Our experiments validate the theoretical intuitions behind our method, and we find that information dropout achieves a comparable or better generalization performance than dropout, especially on smaller models, since it adapts to both the architecture and the test samples.

15 March 2023 in Nature
Verified
Journal Article
Open access
PDF file
MHMingqi Han
Mingqi Han
EBEric A. Bushong
Eric A. Bushong
MSMayuko Segawa
Mayuko Segawa
ATAlexandre Tiard
Alexandre Tiard
AWAlex Wong
Alex Wong
DSDavid B. Shackelford
David B. Shackelford
Mitochondria are critical to the governance of metabolism and bioenergetics in cancer cells1. The mitochondria form highly organized networks, in which their outer and inner membrane structures define their bioenergetic capacity2,3. However, in vivo studies delineating the relationship between the structural organization of mitochondrial networks and their bioenergetic activity have been limited. Here we present an in vivo structural and functional analysis of mitochondrial networks and bioenergetic phenotypes in non-small cell lung cancer (NSCLC) using an integrated platform consisting of positron emission tomography imaging, respirometry and three-dimensional scanning block-face electron microscopy. The diverse bioenergetic phenotypes and metabolic dependencies we identified in NSCLC tumours align with distinct structural organization of mitochondrial networks present. Further, we discovered that mitochondrial networks are organized into distinct compartments within tumour cells. In tumours with high rates of oxidative phosphorylation (OXPHOSHI) and fatty acid oxidation, we identified peri-droplet mitochondrial networks wherein mitochondria contact and surround lipid droplets. By contrast, we discovered that in tumours with low rates of OXPHOS (OXPHOSLO), high glucose flux regulated perinuclear localization of mitochondria, structural remodelling of cristae and mitochondrial respiratory capacity. Our findings suggest that in NSCLC, mitochondrial networks are compartmentalized into distinct subpopulations that govern the bioenergetic capacity of tumours.

1 April 2005 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
HJHailin Jin
Hailin Jin
SSStefano Soatto
Stefano Soatto
AYAnthony J. Yezzi
Anthony J. Yezzi

1 January 2007
Verified
Conference Paper
Closed access
HLHaibin Ling
Haibin Ling
SSStefano Soatto
Stefano Soatto
NRNarayanan Ramanathan
Narayanan Ramanathan
DJDavid W. Jacobs
David W. Jacobs
In this paper we study face recognition across ages within a real passport photo verification task. First, we propose using the gradient orientation pyramid for this task. Discarding the gradient magnitude and utilizing hierarchical techniques, we found that the new descriptor yields a robust and discriminative representation. With the proposed descriptor, we model face verification as a two-class problem and use a support vector machine as a classifier. The approach is applied to two passport data sets containing more than 1,800 image pairs from each person with large age differences. Although simple, our approach outperforms previously tested Bayesian technique and other descriptors, including the intensity difference and gradient with magnitude. In addition, it works as well as two commercial systems. Second, for the first time, we empirically study how age differences affect recognition performance. Our experiments show that, although the aging process adds difficulty to the recognition task, it does not surpass illumination or expression as a confounding factor.

29 October 2022
Verified
Book Chapter
Closed access
PDF file
ZCZhaowei Cai
Zhaowei Cai
GKGukyeong Kwon
Gukyeong Kwon
ARAvinash Ravichandran
Avinash Ravichandran
EBErhan Bas
Erhan Bas
ZTZhuowen Tu
Zhuowen Tu
SSStefano Soatto
Stefano Soatto

1 June 2007
Verified
Conference Paper
Closed access
ABAlessandro Bissacco
Alessandro Bissacco
MYMing Yang
Ming Yang
SSStefano Soatto
Stefano Soatto
We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our algorithm can be viewed as a fast initialization step for human body trackers, or as a tracker itself. We extend gradient boosting techniques to learn a multi-dimensional map from (rotated and scaled) Haar features to the entire set of joint angles representing the full body pose. We test our approach by learning a map from image patches to body joint angles from synchronized video and motion capture walking data. We show how our technique enables learning an efficient real-time pose estimator, validated on publicly available datasets.