Universal Correspondence Network

Authors: Christopher B. Choy, JunYoung Gwak, Silvio Savarese, Manmohan Chandraker

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on KITTI, PASCAL, and CUB-2011 datasets demonstrate the significant advantages of our features over prior works that use either hand-constructed or learned features.
Researcher Affiliation Collaboration Christopher B. Choy Stanford University chrischoy@ai.stanford.edu Jun Young Gwak Stanford University jgwak@ai.stanford.edu Silvio Savarese Stanford University ssilvio@stanford.edu Manmohan Chandraker NEC Laboratories America, Inc. manu@nec-labs.com
Pseudocode No The paper describes the system architecture and components but does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not include an unambiguous statement about releasing its source code or a direct link to a code repository for the methodology described.
Open Datasets Yes For geometric correspondence (matching images of same 3D point in different views), we use two optical flow datasets from KITTI 2015 Flow benchmark and MPI Sintel dataset and split their training set into a training and a validation set individually. The exact splits are available on the project website.
Dataset Splits Yes For geometric correspondence (matching images of same 3D point in different views), we use two optical flow datasets from KITTI 2015 Flow benchmark and MPI Sintel dataset and split their training set into a training and a validation set individually. The exact splits are available on the project website.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No We use Caffe [14] package for implementation. Since it does not support the new layers we propose, we implement the correspondence contrastive loss layer and the convolutional spatial transformer layer, the K-NN layer based on [10] and the channel-wise L2 normalization layer.
Experiment Setup Yes For each experiment setup, we train and test three variations of networks. First, the network has hard negative mining and spatial transformer (Ours-HN-ST). Second, the same network without spatial transformer (Ours-HN). Third, the same network without spatial transformer and hard negative mining, providing random negative samples that are at least certain pixels apart from the ground truth correspondence location instead (Ours-RN). We pick random 1000 correspondences in each KITTI or MPI Sintel image during training. We consider a correspondence as a hard negative if the nearest neighbor in the feature space is more than 16 pixels away from the ground truth correspondence.