# Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks Source: [Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:41:08.783Z Authors: Santiago Estrada, Sailesh Conjeti, Muneer Ahmad, Nassir Navab, Martin Reuter Published: 2018-07-20T12:06:06.000Z ## Abstract Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense Fully Convolutional Networks (CDFNet) by introducing competitive maxout activations in place of naive feature concatenation for inducing competition amongst layers. Within CDFNet, we propose two architectural contributions, namely competitive dense block (CDB) and competitive unpooling block (CUB) to induce competition at local and global scales for short and long-range skip connections respectively. This extension is demonstrated to boost learning of specialized sub-networks targeted at segmenting specific anatomies, which in turn eases the training of complex tasks. We present the proof-of-concept on the challenging task of whole body segmentation in the publicly available VISCERAL benchmark and demonstrate improved performance over multiple learning and registration based state-of-the-art methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()