Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
- pp 1-9
TLDR
Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).Abstract:
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.read more
Citations
More filters
Proceedings ArticleDOI
MovieQA: Understanding Stories in Movies through Question-Answering
TL;DR: The MovieQA dataset as discussed by the authors consists of 14,944 questions about 408 movies with high semantic diversity, ranging from simpler "Who" did "What" to "Whom", to "Why" and "How" certain events occurred.
Proceedings Article
Deep Double Descent: Where Bigger Models and More Data Hurt
TL;DR: The notion of model complexity allows us to identify certain regimes where increasing the number of train samples actually hurts test performance, and defines a new complexity measure called the effective model complexity and conjecture a generalized double descent with respect to this measure.
Proceedings ArticleDOI
Multi-level Factorisation Net for Person Re-identification
TL;DR: Multi-Level Factorization Net (MLFN) as discussed by the authors is a novel network architecture that factorises the visual appearance of a person into latent discriminative factors at multiple semantic levels without manual annotation.
Proceedings ArticleDOI
Learning distributed representations of sentences from unlabelled data
TL;DR: In this article, a systematic comparison of models that learn distributed representations of words from unlabeled data is presented, and it is shown that shallow log-linear models work best for building representation spaces that can be decoded with simple spatial distance metrics.
Journal ArticleDOI
Deep Multimodal Learning: A Survey on Recent Advances and Trends
TL;DR: This work first classify deep multimodal learning architectures and then discusses methods to fuse learned multi-modal representations in deep-learning architectures.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.