2024-04-18-arya24a.md

title	software	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification	https://github.com/Shivvrat/Advanced-Inference-Schemes-for-DDNs	We present a unified framework called deep dependency networks (DDNs) that combines dependency networks and deep learning architectures for multi-label classification, with a particular emphasis on image and video data. The primary advantage of dependency networks is their ease of training, in contrast to other probabilistic graphical models like Markov networks. In particular, when combined with deep learning architectures, they provide an intuitive, easy-to-use loss function for multi-label classification. A drawback of DDNs compared to Markov networks is their lack of advanced inference schemes, necessitating the use of Gibbs sampling. To address this challenge, we propose novel inference schemes based on local search and integer linear programming for computing the most likely assignment to the labels given observations. We evaluate our novel methods on three video datasets (Charades, TACoS, Wetlab) and three image datasets (MS-COCO, PASCAL VOC, NUS-WIDE), comparing their performance with (a) basic neural architectures and (b) neural architectures combined with Markov networks equipped with advanced inference and learning techniques. Our results demonstrate the superiority of our new DDN methods over the two competing approaches.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	arya24a	0	Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification	2818	2826	2818-2826	2818	false	Arya, Shivvrat and Xiang, Yu and Gogate, Vibhav	given family Shivvrat Arya given family Yu Xiang given family Vibhav Gogate	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/arya24a/arya24a.pdf