arXiv subjects

Pradeep Shenoy

Publications and source records attributed to Pradeep Shenoy.

22 records · Page 2Linked to original sources

arXiv2022

FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing

Multi-object multi-part scene parsing is a challenging task which requires detecting multiple object classes in a scene and segmenting the semantic parts within each object. In this paper, we propose FLOAT, a factorized label space framework for scalable multi-object multi-part parsing. Our framework involves independent dense prediction of object category and part attributes which increases scalability and reduces task complexity compared to the monolithic label space counterpart. In addition, we propose an inference-time 'zoom' refinement technique which significantly improves segmentation quality, especially for smaller objects/parts. Compared to state of the art, FLOAT obtains an absolute improvement of 2.0% for mean IOU (mIOU) and 4.8% for segmentation quality IOU (sqIOU) on the Pascal-Part-58 dataset. For the larger Pascal-Part-108 dataset, the improvements are 2.1% for mIOU and 3.9% for sqIOU. We incorporate previously excluded part attributes and other minor parts of the Pascal-Part dataset to create the most comprehensive and challenging version which we dub Pascal-Part-201. FLOAT obtains improvements of 8.6% for mIOU and 7.5% for sqIOU on the new dataset, demonstrating its parsing effectiveness across a challenging diversity of objects and parts. The code and datasets are available at floatseg.github.io.

cs.CV↗

arXiv2021

End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks

Neural models and symbolic algorithms have recently been combined for tasks requiring both perception and reasoning. Neural models ground perceptual input into a conceptual vocabulary, on which a classical reasoning algorithm is applied to generate output. A key limitation is that such neural-to-symbolic models can only be trained end-to-end for tasks where the output space is symbolic. In this paper, we study neural-symbolic-neural models for reasoning tasks that require a conversion from an image input (e.g., a partially filled sudoku) to an image output (e.g., the image of the completed sudoku). While designing such a three-step hybrid architecture may be straightforward, the key technical challenge is end-to-end training -- how to backpropagate without intermediate supervision through the symbolic component. We propose NSNnet, an architecture that combines an image reconstruction loss with a novel output encoder to generate a supervisory signal, develops update algorithms that leverage policy gradient methods for supervision, and optimizes loss using a novel subsampling heuristic. We experiment on problem settings where symbolic algorithms are easily specified: a visual maze solving task and a visual Sudoku solver where the supervision is in image form. Experiments show high accuracy with significantly less data compared to purely neural approaches.

cs.AI↗

arXiv2021

Model-agnostic Fits for Understanding Information Seeking Patterns in Humans

In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task. Here, we reexamine data from previous carefully designed experiments, collected at scale, that measured and catalogued these biases in aggregate form. We design deep learning models that replicate these biases in aggregate, while also capturing individual variation in behavior. A key finding of our work is that paucity of data collected from each individual subject can be overcome by sampling large numbers of subjects from the population, while still capturing individual differences. In addition, we can predict human behavior with high accuracy without making any assumptions about task goals, reward structure, or individual biases, thus providing a model-agnostic fit to human behavior in the task. Such an approach can sidestep potential limitations in modeler-specified inductive biases, and has implications for computational modeling of human cognitive function in general, and of human-AI interfaces in particular.

cs.AI↗

arXiv2000

Don't Trash your Intermediate Results, Cache 'em

In data warehouse and data mart systems, queries often take a long time to execute due to their complex nature. Query response times can be greatly improved by caching final/intermediate results of previous queries, and using them to answer later queries. In this paper we describe a caching system called Exchequer which incorporates several novel features including optimization aware cache maintenance and the use of a cache aware optimizer. In contrast, in existing work, the module that makes cost-benefit decisions is part of the cache manager and works independent of the optimizer which essentially reconsiders these decisions while finding the best plan for a query. In our work, the optimizer takes the decisions for the cache manager. Furthermore, existing approaches are either restricted to cube (slice/point) queries, or cache just the query results. On the other hand, our work is extens ible and in fact presents a data-model independent framework and algorithm. Our experimental results attest to the efficacy of our cache management techniques and show that over a wide range of parameters (a) Exchequer's query response times are lower by more than 30% compared to the best performing competitor, and (b) Exchequer can deliver the same response time as its competitor with just one tenth of the cache size.

cs.DB↗