@conference {cSalvadord, title = {Recurrent Neural Networks for Semantic Instance Segmentation}, booktitle = {ECCV 2018 Women in Computer Vision (WiCV) Workshop}, year = {2018}, month = {12/2017}, abstract = {

We present a recurrent model for semantic instance segmentation that sequentially generates pairs of masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end, does not require post-processing steps on its output and is conceptually simpler than current methods relying on object proposals. We observe that our model learns to follow a consistent pattern to generate object sequences, which correlates with the activations learned in the encoder part of our network. We achieve competitive results on three different instance segmentation benchmarks (Pascal VOC 2012, Cityscapes and CVPPP Plant Leaf Segmentation).

Recurrent Neural Networks for Semantic Instance Segmentation from Universitat Polit{\`e}cnica de Catalunya
}, url = {https://imatge-upc.github.io/rsis/}, author = {Amaia Salvador and M{\'\i}riam Bellver and Baradad, Manel and V{\'\i}ctor Campos and Marqu{\'e}s, F. and Jordi Torres and Xavier Gir{\'o}-i-Nieto} } @conference {cSalvadore, title = {Recurrent Neural Networks for Semantic Instance Segmentation}, booktitle = {CVPR 2018 DeepVision Workshop}, year = {2018}, month = {06/2018}, abstract = {

We present a recurrent model for semantic instance segmentation that sequentially generates binary masks and their associated class probabilities for every object in an image. Our proposed system is trainable end-to-end from an input image to a sequence of labeled masks and, compared to methods relying on object proposals, does not require post-processing steps on its output. We study the suitability of our recurrent model on three different instance segmentation benchmarks, namely Pascal VOC 2012, CVPPP Plant Leaf Segmentation and Cityscapes. Further, we analyze the object sorting patterns generated by our model and observe that it learns to follow a consistent pattern, which correlates with the activations learned in the encoder part of our network.

}, author = {Amaia Salvador and M{\'\i}riam Bellver and Baradad, Manel and V{\'\i}ctor Campos and Marqu{\'e}s, F. and Jordi Torres and Xavier Gir{\'o}-i-Nieto} } @conference {xSalvadora, title = {Recurrent Semantic Instance Segmentation}, booktitle = {NIPS 2017 Women in Machine Learning Workshop (WiML)}, year = {2017}, month = {12/2017}, publisher = {NIPS 2017 Women in Machine Learning Workshop}, organization = {NIPS 2017 Women in Machine Learning Workshop}, address = {Long Beach, CA, USA}, abstract = {

We present a recurrent model for end-to-end instance-aware semantic segmentation that is able to sequentially generate pairs of masks and class predictions. Our proposed system is trainable end-to-end for instance segmentation, does not require further post-processing steps on its output and is conceptually simpler than current methods relying on object proposals. While recent works have proposed recurrent architectures for instance segmentation, these are trained and evaluated for a single category.

Our model is composed of a series of Convolutional LSTMs that are applied in chain with upsampling layers in between to predict a sequence of binary masks and associated class probabilities. Skip connections are incorporated in our model by concatenating the output of the corresponding convolutional layer in the base model with the upsampled output of the ConvLSTM. Binary masks are finally obtained with a 1x1 convolution with sigmoid activation. We concatenate the side outputs of all ConvLSTM layers and apply a per-channel max-pooling operation followed by a single fully-connected layer with softmax activation to obtain the category for each predicted mask.

We train and evaluate our models with the Pascal VOC 2012 dataset. Future work will aim at analyzing and understanding the behavior of the network on other datasets, comparing the system with state of the art solutions and study the relationship of the learned object discovery patterns of our model with those of humans.

}, author = {Amaia Salvador and Baradad, Manel and Xavier Gir{\'o}-i-Nieto and Marqu{\'e}s, F.} }