Using goal-driven deep learning models to understand sensory cortex

DLK Yamins, JJ DiCarlo - Nature neuroscience, 2016 - nature.com
Fueled by innovation in the computer vision and artificial intelligence communities, recent
developments in computational neuroscience have used goal-driven hierarchical …

Detect what you can: Detecting and representing objects using holistic models and body parts

X Chen, R Mottaghi, X Liu, S Fidler… - Proceedings of the …, 2014 - openaccess.thecvf.com
Detecting objects becomes difficult when we need to deal with large shape deformation,
occlusion and low resolution. We propose a novel approach to i) handle large deformations …

Object as hotspots: An anchor-free 3d object detection approach via firing of hotspots

Q Chen, L Sun, Z Wang, K Jia, A Yuille - Computer Vision–ECCV 2020 …, 2020 - Springer
Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of
data sparsity and irregularities. Existing methods strive to organize the points regularly, eg …

A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs

D George, W Lehrach, K Kansky, M Lázaro-Gredilla… - Science, 2017 - science.org
INTRODUCTION Compositionality, generalization, and learning from a few examples are
among the hallmarks of human intelligence. CAPTCHAs (Completely Automated Public …

Robust object detection under occlusion with context-aware compositionalnets

A Wang, Y Sun, A Kortylewski… - Proceedings of the …, 2020 - openaccess.thecvf.com
Detecting partially occluded objects is a difficult task. Our experimental results show that
deep learning approaches, such as Faster R-CNN, are not robust at object detection under …

A probabilistic model for component-based shape synthesis

E Kalogerakis, S Chaudhuri, D Koller… - Acm Transactions on …, 2012 - dl.acm.org
We present an approach to synthesizing shapes from complex domains, by identifying new
plausible combinations of components from existing shapes. Our primary contribution is a …

Automatic generation of software behavioral models

D Lorenzoli, L Mariani, M Pezzè - … of the 30th international conference on …, 2008 - dl.acm.org
Dynamic analysis of software systems produces behavioral models that are useful for
analysis, verification and testing. The main techniques for extracting models of functional …

Compositional convolutional neural networks: A robust and interpretable model for object recognition under occlusion

A Kortylewski, Q Liu, A Wang, Y Sun… - International Journal of …, 2021 - Springer
Computer vision systems in real-world applications need to be robust to partial occlusion
while also being explainable. In this work, we show that black-box deep convolutional …

Compositional convolutional neural networks: A deep architecture with innate robustness to partial occlusion

A Kortylewski, J He, Q Liu… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Recent work has shown that deep convolutional neural networks (DCNNs) do not
generalize well under partial occlusion. Inspired by the success of compositional models at …

Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos

A Gupta, P Srinivasan, J Shi… - 2009 IEEE Conference …, 2009 - ieeexplore.ieee.org
Analyzing videos of human activities involves not only recognizing actions (typically based
on their appearances), but also determining the story/plot of the video. The storyline of a …