ananth ranga - Academia.edu (original) (raw)

ananth ranga

Related Authors

Marcella Astrid

IJERA Journal

IJERA Journal

International Journal of Engineering Research and Applications (IJERA)

Engr.Lubna Aziz

yuelou fang

Uploads

Papers by ananth ranga

Research paper thumbnail of DSSD : Deconvolutional Single Shot Detector

ArXiv, 2017

The main contribution of this paper is an approach for introducing additional context into state-... more The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101[14]) with a fast detection framework (SSD[18]). We then augment SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects, calling our resulting system DSSD for deconvolutional single shot detector. While these two contributions are easily described at a high-level, a naive implementation does not succeed. Instead we show that carefully adding additional stages of learned transformations, specifically a module for feed-forward connections in deconvolution and a new output module, enables this new approach and forms a potential way forward for further detection research. Results are shown on both PASCAL VOC and COCO detection. Our DSSD with 513times513513 \times 513513times513 input achieves 81.5% ...

Research paper thumbnail of DSSD : Deconvolutional Single Shot Detector

ArXiv, 2017

The main contribution of this paper is an approach for introducing additional context into state-... more The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101[14]) with a fast detection framework (SSD[18]). We then augment SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects, calling our resulting system DSSD for deconvolutional single shot detector. While these two contributions are easily described at a high-level, a naive implementation does not succeed. Instead we show that carefully adding additional stages of learned transformations, specifically a module for feed-forward connections in deconvolution and a new output module, enables this new approach and forms a potential way forward for further detection research. Results are shown on both PASCAL VOC and COCO detection. Our DSSD with 513times513513 \times 513513times513 input achieves 81.5% ...

Log In