Search Results - "Kalluri, Tarun"

Machine Learning for Accurate Force Calculations in Molecular Dynamics Simulations by Pattnaik, Punyaslok, Raghunathan, Shampa, Kalluri, Tarun, Bhimalapuram, Prabhakar, Jawahar, C. V, Priyakumar, U. Deva

“…The computationally expensive nature of ab initio molecular dynamics simulations severely limits its ability to simulate large system sizes and long time…”
Get full text

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation by Sharma, Astuti, Kalluri, Tarun, Chandraker, Manmohan

“…Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target…”
Get full text

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation by Kalluri, Tarun, Pathak, Deepak, Chandraker, Manmohan, Tran, Du

“…Most modern frame interpolation approaches rely on explicit bidirectional optical flows between adjacent frames, thus are sensitive to the accuracy of…”
Get full text

FLAVR: flow-free architecture for fast video frame interpolation by Kalluri, Tarun, Pathak, Deepak, Chandraker, Manmohan, Tran, Du

“…Many modern frame interpolation approaches rely on explicit bidirectional optical flows between adjacent frames, thus are sensitive to the accuracy of…”
Get full text

GeoNet: Benchmarking Unsupervised Adaptation across Geographies by Kalluri, Tarun, Xu, Wangdong, Chandraker, Manmohan

“…In recent years, several efforts have been aimed at improving the robustness of vision models to domains and environments unseen during training. An important…”
Get full text

Universal Semi-Supervised Semantic Segmentation by Kalluri, Tarun, Varma, Girish, Chandraker, Manmohan, Jawahar, C.V.

“…In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of…”
Get full text

Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels by Kalluri, Tarun, Chandraker, Manmohan

“…Domain adaptation for semantic segmentation across datasets consisting of the same categories has seen several recent successes. However, a more general…”
Get full text

Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels by Kalluri, Tarun, Chandraker, Manmohan

“…Domain adaptation for semantic segmentation across datasets consisting of the same categories has seen several recent successes. However, a more general…”
Get full text

UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework by Kalluri, Tarun, Ravichandran, Sreyas, Chandraker, Manmohan

“…In this work, we take a deeper look into the diverse factors that influence the efficacy of modern unsupervised domain adaptation (UDA) methods using a…”
Get full text

Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos by Kalluri, Tarun, Majumder, Bodhisattwa Prasad, Chandraker, Manmohan

“…We introduce LaGTran, a novel framework that utilizes text supervision to guide robust transfer of discriminative knowledge from labeled source to unlabeled…”
Get full text

GeoNet: Benchmarking Unsupervised Adaptation across Geographies by Kalluri, Tarun, Xu, Wangdong, Chandraker, Manmohan

“…In recent years, several efforts have been aimed at improving the robustness of vision models to domains and environments unseen during training. An important…”
Get full text

MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation by Kalluri, Tarun, Sharma, Astuti, Chandraker, Manmohan

“…Practical real world datasets with plentiful categories introduce new challenges for unsupervised domain adaptation like small inter-class discriminability,…”
Get full text

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation by Sharma, Astuti, Kalluri, Tarun, Chandraker, Manmohan

“…Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target…”
Get full text

Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision by Kalluri, Tarun, Wang, Weiyao, Wang, Heng, Chandraker, Manmohan, Torresani, Lorenzo, Tran, Du

“…Top-down instance segmentation architectures excel with predefined closed-world taxonomies but exhibit biases and performance degradation in open-world…”
Get full text

Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data by Kalluri, Tarun, Lee, Jihyeon, Sohn, Kihyuk, Singla, Sahil, Chandraker, Manmohan, Xu, Joseph, Liu, Jeremiah

“…We present a simple and efficient method to leverage emerging text-to-image generative models in creating large-scale synthetic supervision for the task of…”
Get full text

Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data by Kalluri, Tarun, Lee, Jihyeon, Sohn, Kihyuk, Singla, Sahil, Chandraker, Manmohan, Xu, Joseph, Liu, Jeremiah

“…We present a simple and efficient method to leverage emerging text-to-image generative models in creating large-scale synthetic supervision for the task of…”
Get full text

Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision by Kalluri, Tarun, Wang, Weiyao, Wang, Heng, Chandraker, Manmohan, Torresani, Lorenzo, Tran, Du

“…Many top-down architectures for instance segmentation achieve significant success when trained and tested on pre-defined closed-world taxonomy. However, when…”
Get full text

FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation by Kalluri, Tarun, Pathak, Deepak, Chandraker, Manmohan, Tran, Du

“…A majority of methods for video frame interpolation compute bidirectional optical flow between adjacent frames of a video, followed by a suitable warping…”
Get full text

Regenerative relaying in energy harvesting cognitive radio networks by Kalluri, Tarun, Bohara, Vivek Ashok

“…In this paper a cognitive radio network is considered where a licensed primary user and an energy harvesting secondary (cognitive) user co-exist, and relaying…”
Get full text

Universal Semi-Supervised Semantic Segmentation by Kalluri, Tarun, Varma, Girish, Chandraker, Manmohan, Jawahar, C V

“…In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of…”
Get full text