23 citations · 75 across the 11 of their papers we have counts for
11 papers
Segmentation-Free Guidance for Text-to-Image Diffusion Models
Kambiz Azarian, Debasmit Das, Qiqi Hou +1
We introduce segmentation-free guidance, a novel method designed for text-to-image diffusion models like Stable Diffusion. Our method does not require retraining of the diffusion m…
TransAdapt: A Transformative Framework for Online Test Time Adaptive Semantic Segmentation
Debasmit Das, Shubhankar Borse, Hyojin Park +4
Test-time adaptive (TTA) semantic segmentation adapts a source pre-trained image semantic segmentation model to unlabeled batches of target domain test images, different from real-…
Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation
Kambiz Azarian, Debasmit Das, Hyojin Park +1
We consider the problem of improving the human instance segmentation mask quality for a given test image using keypoints estimation. We compare two alternative approaches. The firs…
Unsupervised Information Obfuscation for Split Inference of Neural Networks
Mohammad Samragh, Hossein Hosseini, Aleksei Triastcyn +3
Splitting network computations between the edge device and a server enables low edge-compute inference of neural networks but might expose sensitive information about the test quer…
Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning
Kambiz Azarian, Fatih Porikli
We report, for the first time, on the cascade weight shedding phenomenon in deep neural networks where in response to pruning a small percentage of a network's weights, a large per…
Learned Threshold Pruning
Kambiz Azarian, Yash Bhalgat, Jinwon Lee +1
This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds vi…