Search Results for author: Thomas Serre

Found 26 papers, 4 papers with code

The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks

no code implementations30 Sep 2021 Girik Malik, Drew Linsley, Thomas Serre, Ennio Mingolla

Here, we introduce $\textit{PathTracker}$, a visual challenge inspired by cognitive psychology, which tests the ability of observers to learn to track objects solely by their motion.

Object Recognition Object Tracking

Understanding the computational demands underlying visual reasoning

no code implementations8 Aug 2021 Mohit Vaishnav, Remi Cadene, Andrea Alamia, Drew Linsley, Rufin VanRullen, Thomas Serre

Our analysis leads to a novel taxonomy of visual reasoning tasks, which can be primarily explained by both the type of relations (same-different vs. spatial-relation judgments) and the number of relations used to compose the underlying rules.

Visual Reasoning

Tracking Without Re-recognition in Humans and Machines

no code implementations NeurIPS 2021 Drew Linsley, Girik Malik, Junkyung Kim, Lakshmi N Govindarajan, Ennio Mingolla, Thomas Serre

For this, we introduce PathTracker, a synthetic visual challenge that asks human observers and machines to track a target object in the midst of identical-looking "distractor" objects.

Decision Making Object Tracking +1

KuraNet: Systems of Coupled Oscillators that Learn to Synchronize

1 code implementation6 May 2021 Matthew Ricci, Minju Jung, Yuwei Zhang, Mathieu Chalvidal, Aneri Soni, Thomas Serre

Here, we present a single approach to both of these problems in the form of "KuraNet", a deep-learning-based system of coupled oscillators that can learn to synchronize across a distribution of disordered network conditions.

Iterative VAE as a predictive brain model for out-of-distribution generalization

no code implementations NeurIPS Workshop SVRHM 2020 Victor Boutin, Aimen Zerroug, Minju Jung, Thomas Serre

Our ability to generalize beyond training data to novel, out-of-distribution, image degradations is a hallmark of primate vision.

Recurrent neural circuits for contour detection

no code implementations ICLR 2020 Drew Linsley, Junkyung Kim, Alekh Ashok, Thomas Serre

We introduce a deep recurrent neural network architecture that approximates visual cortical circuits.

Contour Detection

How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networks

no code implementations7 Sep 2020 Thomas Fel, David Vigouroux, Rémi Cadène, Thomas Serre

A plethora of methods have been proposed to explain how deep neural networks reach their decisions but comparatively, little effort has been made to ensure that the explanations produced by these methods are objectively relevant.

Image Classification

Go with the Flow: Adaptive Control for Neural ODEs

no code implementations ICLR 2021 Mathieu Chalvidal, Matthew Ricci, Rufin VanRullen, Thomas Serre

Despite their elegant formulation and lightweight memory cost, neural ordinary differential equations (NODEs) suffer from known representational limitations.

Image Reconstruction Representation Learning

Stable and expressive recurrent vision models

1 code implementation NeurIPS 2020 Drew Linsley, Alekh Karkada Ashok, Lakshmi Narasimhan Govindarajan, Rex Liu, Thomas Serre

We posit that the effectiveness of recurrent vision models is bottlenecked by the standard algorithm used for training them, "back-propagation through time" (BPTT), which has O(N) memory-complexity for training an N step model.

Panoptic Segmentation

Disentangling neural mechanisms for perceptual grouping

no code implementations ICLR 2020 Junkyung Kim, Drew Linsley, Kalpit Thakkar, Thomas Serre

Forming perceptual groups and individuating objects in visual scenes is an essential step towards visual intelligence.

Learning what and where to attend with humans in the loop

no code implementations ICLR 2019 Drew Linsley, Dan Shiebler, Sven Eberhardt, Thomas Serre

Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs).

Image Categorization Object Recognition

Robust pose tracking with a joint model of appearance and shape

no code implementations28 Jun 2018 Yuliang Guo, Lakshmi Narasimhan Govindarajan, Benjamin Kimia, Thomas Serre

We present a novel approach for estimating the 2D pose of an articulated object with an application to automated video analysis of small laboratory animals.

Pose Tracking

Learning what and where to attend

no code implementations22 May 2018 Drew Linsley, Dan Shiebler, Sven Eberhardt, Thomas Serre

Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs).

Image Categorization Object Recognition

Learning long-range spatial dependencies with horizontal gated-recurrent units

1 code implementation NeurIPS 2018 Drew Linsley, Junkyung Kim, Vijay Veerabadran, Thomas Serre

As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -- and sometimes even surpassing -- human accuracy on a variety of visual recognition tasks.

Contour Detection

Same-different problems strain convolutional neural networks

no code implementations9 Feb 2018 Matthew Ricci, Junkyung Kim, Thomas Serre

The robust and efficient recognition of visual relations in images is a hallmark of biological vision.

Visual Reasoning

What are the visual features underlying human versus machine vision?

no code implementations10 Jan 2017 Drew Linsley, Sven Eberhardt, Tarun Sharma, Pankaj Gupta, Thomas Serre

Our study demonstrates that the narrowing gap between the object recognition accuracy of human observers and DCNs obscures distinct visual strategies used by each to achieve this performance.

Object Recognition

How Deep is the Feature Analysis underlying Rapid Visual Categorization?

no code implementations NeurIPS 2016 Sven Eberhardt, Jonah Cader, Thomas Serre

We found that recognition accuracy increases with higher stages of visual processing (higher level stages indeed outperforming human participants on the same task) but that human decisions agree best with predictions from intermediate stages.

Object Recognition

Cooking in the kitchen: Recognizing and Segmenting Human Activities in Videos

no code implementations25 Aug 2015 Hilde Kuehne, Juergen Gall, Thomas Serre

Through extensive system evaluations, we demonstrate that combining compact video representations based on Fisher Vectors with HMM-based modeling yields very significant gains in accuracy and when properly trained with sufficient training samples, structured temporal models outperform unstructured bag-of-word types of models by a large margin on the tested performance metric.

Action Recognition

Neuronal Synchrony in Complex-Valued Deep Networks

no code implementations20 Dec 2013 David P. Reichert, Thomas Serre

Here, we show how aspects of spike timing, long hypothesized to play a crucial role in cortical information processing, could be incorporated into deep networks to build richer, versatile representations.

Neural representation of action sequences: how far can a simple snippet-matching model take us?

no code implementations NeurIPS 2013 Cheston Tan, Jedediah M. Singer, Thomas Serre, David Sheinberg, Tomaso Poggio

The macaque Superior Temporal Sulcus (STS) is a brain area that receives and integrates inputs from both the ventral and dorsal visual processing streams (thought to specialize in form and motion processing respectively).

Cannot find the paper you are looking for? You can Submit a new open access paper.