OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very competitive results for the detection and classifications tasks. In post-competition work, we establish a new state of the art for the detection task. Finally, we release a feature extractor from our best model called OverFeat.
Keywords for this software
References in zbMATH (referenced in 12 articles )
Showing results 1 to 12 of 12.
- Arridge, Simon; Maass, Peter; Öktem, Ozan; Schönlieb, Carola-Bibiane: Solving inverse problems using data-driven models (2019)
- Jeong, Chiyoon; Yang, Hyun S.; Moon, KyeongDeok: A novel approach for detecting the horizon using a convolutional neural network and multi-scale edge detection (2019)
- Mäkinen, Ymir; Kanniainen, Juho; Gabbouj, Moncef; Iosifidis, Alexandros: Forecasting jump arrivals in stock prices: new attention-based network architecture using limit order book data (2019)
- Liu, Yu; Chen, Xun; Cheng, Juan; Peng, Hu; Wang, Zengfu: Infrared and visible image fusion with convolutional neural networks (2018)
- Sultana, Nazneen N.; Puhan, N. B.: Recent deep learning methods for melanoma detection: a review (2018)
- Fehri, Amin; Velasco-Forero, Santiago; Meyer, Fernand: Prior-based hierarchical segmentation highlighting structures of interest (2017)
- Anselmi, Fabio; Rosasco, Lorenzo; Poggio, Tomaso: On invariance and selectivity in representation learning (2016)
- Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, Bernt Schiele: The Cityscapes Dataset for Semantic Urban Scene Understanding (2016) arXiv
- Zhou, Peicheng; Cheng, Gong; Liu, Zhenbao; Bu, Shuhui; Hu, Xintao: Weakly supervised target detection in remote sensing images based on transferred deep features and negative bootstrapping (2016)
- Arriaga, Rosa I.; Rutter, David; Cakmak, Maya; Vempala, Santosh S.: Visual categorization with random projection (2015)
- Fernandes, Tomas; von der Malsburg, Christoph: Self-organization of control circuits for invariant fiber projections (2015)
- Schmidhuber, Jürgen: Deep learning in neural networks: an overview (2015) ioport