Weakly-supervised Discovery of Visual Pattern Configurations

Authors: Hyun Oh Song, Yong Jae Lee, Stefanie Jegelka, Trevor Darrell

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In our experiments on the challenging PASCAL VOC dataset, we find the inclusion of our discriminative, automatically detected configurations to outperform all existing state-of-the-art methods.
Researcher Affiliation Academia University of California, Berkeley *University of California, Davis
Pseudocode No The paper describes algorithms in paragraph form, such as the greedy algorithm, but does not provide structured pseudocode or algorithm blocks with formal labeling.
Open Source Code No The paper does not include any explicit statements about releasing source code or provide links to a code repository for the described methodology.
Open Datasets Yes In our experiments on the challenging PASCAL VOC dataset, we find the inclusion of our discriminative, automatically detected configurations to outperform all existing state-of-the-art methods.
Dataset Splits No The paper mentions using the PASCAL test set but does not specify a separate validation set or describe how data was split for validation purposes.
Hardware Specification No The paper does not provide specific details about the hardware used for experiments, such as CPU or GPU models, memory, or cloud instance types.
Software Dependencies No The paper mentions using 'fc7 features from the CNN model [6]' and a 'region based detection framework [13, 29]', but it does not specify version numbers for any software dependencies or libraries.
Experiment Setup Yes For discriminative patch discovery, we use K = |P|/2, θ = K/20. For correspondence detection, we discretize the 4D transform space of {x: relative horizontal shift, y: relative vertical shift, s: relative scale, p: relative aspect ratio} with x = 30 px, y = 30 px, s = 1 px/px, p = 1 px/px.