Joint Learning of Set Cardinality and State Distribution

Authors: S. Hamid Rezatofighi, Anton Milan, Qinfeng Shi, Anthony Dick, Ian Reid

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the validity of our method on the task of multi-label image classification and achieve a new state of the art on the PASCAL VOC and MS COCO datasets.
Researcher Affiliation Collaboration S. Hamid Rezatofighi,1 Anton Milan,2 Qinfeng Shi,1 Anthony Dick,1 Ian Reid1 1School of Computer Science, The University of Adelaide, Australia 2Amazon Development Center, Germany firstname.lastname@adelaide.edu.au
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described in this paper.
Open Datasets Yes To make our work directly comparable to (Rezatofighi et al. 2017), we use the same two standard and popular benchmarks, the PASCAL VOC 2007 dataset (Everingham et al. 2007) and the Microsoft Common Objects in Context (MS COCO) dataset (Lin et al. 2014).
Dataset Splits Yes We then fine-tune the entire network using the training set of these datasets with the same train/test split as in existing literature (Rezatofighi et al. 2017; Gong et al. 2013a; Wang et al. 2016).
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions building the model on the '16-layers VGG network' but does not specify any software dependencies like programming languages, libraries, or frameworks with version numbers (e.g., Python, PyTorch, TensorFlow, CUDA).
Experiment Setup Yes To train our network, which we call JDS in the following, we use stochastic gradient descent and set the weight decay to γ = 5 10 4, with a momentum of 0.9 and a dropout rate of 0.5. The learning rate is adjusted to gradually decrease after each epoch, starting from 0.001. The network is trained for 60 epochs for both datasets and the epoch with the lowest validation objective value is chosen for evaluation on the test set. The hyper-parameter U is set to be 2.36, adjusted on the validation set.