CoSegNet: Image Co-segmentation using a Conditional Siamese Convolutional Network

Authors: Sayan Banerjee, Avik Hati, Subhasis Chaudhuri, Rajbabu Velmurugan

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results reflect an excellent performance of our method compared to stateof-the-art methods on challenging co-segmentation datasets. We evaluate the proposed method on three challenging cosegmentation datasets Pascal-VOC, Internet and MSRC and compare with state-of-the-art methods.
Researcher Affiliation Academia 1Indian Institute of Technology Bombay, India 2Istituto Italiano di Tecnologia,Genova, Italy
Pseudocode No The paper describes the network architecture and training process in text and diagrams, but does not include any explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statement providing concrete access to source code for the methodology described, nor does it include a link to a repository or mention supplementary materials for code.
Open Datasets Yes We evaluate the proposed method on three challenging cosegmentation datasets Pascal-VOC, Internet and MSRC and compare with state-of-the-art methods. referencing [Everingham et al., 2010] for PASCAL-VOC and [Rubinstein et al., 2013] for Internet and MSRC.
Dataset Splits Yes For Pascal-VOC and MSRC datasets, we randomly split the dataset in the ratio of 3:1:1 for training, validation and testing sets.
Hardware Specification No The paper mentions memory constraints influencing batch size ('Due to memory constraint, we use a batch size of 3') but does not provide any specific details about the hardware (e.g., GPU, CPU models, memory size) used for the experiments.
Software Dependencies No The paper does not provide specific details about ancillary software dependencies, such as programming languages, libraries, or frameworks, along with their version numbers.
Experiment Setup Yes We use stochastic gradient descent as our optimizer and fix the learning rate and momentum at 0.00001 and 0.9, respectively for all three datasets. For Pascal-VOC and MSRC datasets, we set the weight decay to 0.0004 and for Internet we set it to 0.0005. Due to memory constraint, we use a batch size of 3. We resize all the input images to 224 224 and set the margin α to 1.