Thomas Serre

Thomas Serre

Auto-generated profile, based on publicly available information

Thomas Serre

Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge, MA 02139, USA

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

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

Representative Publications

View All Publications
22 January 2007 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
TSThomas Serre
Thomas Serre
LWLior Wolf
Lior Wolf
SBStanley Bileschi
Stanley Bileschi
MRMaximilian Riesenhuber
Maximilian Riesenhuber
TPTomaso Poggio
Tomaso Poggio
We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex

10 April 2007 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Closed access
TSThomas Serre
Thomas Serre
AOAude Oliva
Aude Oliva
TPTomaso Poggio
Tomaso Poggio
Primates are remarkably good at recognizing objects. The level of performance of their visual system and its robustness to image degradations still surpasses the best computer vision systems despite decades of engineering effort. In particular, the high accuracy of primates in ultra rapid object categorization and rapid serial visual presentation tasks is remarkable. Given the number of processing stages involved and typical neural latencies, such rapid visual processing is likely to be mostly feedforward. Here we show that a specific implementation of a class of feedforward theories of object recognition (that extend the Hubel and Wiesel simple-to-complex cell hierarchy and account for many anatomical and physiological constraints) can predict the level and the pattern of performance achieved by humans on a rapid masked animal vs. non-animal categorization task.

1 January 2007
Verified
Conference Paper
Closed access
HJH. Jhuang
H. Jhuang
TST. Serre
T. Serre
LWL. Wolf
L. Wolf
TPT. Poggio
T. Poggio
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feedforward architectures [25, 16, 20] and extends a neurobiological model of motion processing in the visual cortex [10]. The system consists of a hierarchy of spatio-temporal feature detectors of increasing complexity: an input sequence is first analyzed by an array of motion- direction sensitive units which, through a hierarchy of processing stages, lead to position-invariant spatio-temporal feature detectors. We experiment with different types of motion-direction sensitive units as well as different system architectures. As in [16], we find that sparse features in intermediate stages outperform dense ones and that using a simple feature selection approach leads to an efficient system that performs better with far fewer features. We test the approach on different publicly available action datasets, in all cases achieving the highest results reported to date.

1 January 2007
Verified
Book Chapter
Closed access
TSThomas Serre
Thomas Serre
GKGabriel Kreiman
Gabriel Kreiman
MKMinjoon Kouh
Minjoon Kouh
CCCharles Cadieu
Charles Cadieu
UKUlf Knoblich
Ulf Knoblich
TPTomaso Poggio
Tomaso Poggio

1 January 2006
Verified
Report
Closed access
PDF file
TSThomas Serre
Thomas Serre
MRMaximilian Riesenhuber
Maximilian Riesenhuber
JLJennifer Louie
Jennifer Louie
TPTomaso Poggio
Tomaso Poggio
Models of object recognition in cortex have so far been mostly applied to tasks involving the recognition of isolated objects presented on blank backgrounds. However, ultimately models of the visual system have to prove themselves in real world object recognition tasks. Here we took a first step in this direction: We investigated the performance of the HMAX model of object recognition in cortex recently presented by Riesenhuber & Poggio on the task of face detection using natural images. We found that the standard version of HMAX performs rather poorly on this task, due to the low specificity of the hardwired feature set of C2 units in the model (corresponding to neurons in intermediate visual area V4) that do not show any particular tuning for faces vs. background. We show how visual features of intermediate complexity can be learned in HMAX using a simple learning rule. Using this rule, HMAX outperforms a classical machine vision face detection system presented in the literature. This suggests an important role for the set of features in intermediate visual areas in object recognition.

26 December 2007
Verified
Report
Closed access
PDF file
TMTimothee Masquelier
Timothee Masquelier
TSThomas Serre
Thomas Serre
STSimon Thorpe
Simon Thorpe
TPTomaso Poggio
Tomaso Poggio
Digital breast tomosynthesis (DBT) strives to overcome the obstacles presented in conventional 2D mammography by taking multiple projections over a fixed angle and reconstructing volumetric data isolates overlying anatomy from in-plane structures and amplify the conspicuity of lesions. Temporal subtraction automates the process of comparative analysis by using two images taken sequentially and subtracting them in order to find temporal discrepancies. The purpose of this project is to determine the feasibility of using temporal subtraction on DBT phantom images to allow for easier and earlier detection of breast cancer than with either technique alone. The investigator acquired initial tomosynthesis images with the compressible and deformable breast phantom using materials to simulate the breast parenchyma. This was a first step to see if the physical breast phantom originally conceived in theory would work in practice. Unfortunately, the materials used for the breast tissues did not provide a realistic enough breast simulation. Further work must be done to find different materials to use for the physical breast phantom so that realistic images can be used for the observer study. The investigator found that a 3D computer simulated breast phantom needs to provide a realistic and accurate representation of the breast parenchyma in order to offer a compelling argument for the technique. This can be accomplished through either mathematical methods using geometrical primitives or voxelizations of real patient data. The investigator has decided to use an approach combining empirical breast CT data with subdivision surfaces (SD)and non-uniform rational b-splines (NURBS) in the future for the computer breast simulation.