Search Results for author: Saksham Suri

Found 9 papers, 3 papers with code

LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors

no code implementations21 Mar 2024 Saksham Suri, Matthew Walmer, Kamal Gupta, Abhinav Shrivastava

We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks.

Object Discovery

Gen2Det: Generate to Detect

no code implementations7 Dec 2023 Saksham Suri, Fanyi Xiao, Animesh Sinha, Sean Chang Culatana, Raghuraman Krishnamoorthi, Chenchen Zhu, Abhinav Shrivastava

In the long-tailed detection setting on LVIS, Gen2Det improves the performance on rare categories by a large margin while also significantly improving the performance on other categories, e. g. we see an improvement of 2. 13 Box AP and 1. 84 Mask AP over just training on real data on LVIS with Mask R-CNN.

Image Generation Object +2

Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization

1 code implementation18 Aug 2023 Soumik Mukhopadhyay, Saksham Suri, Ravi Teja Gadde, Abhinav Shrivastava

We show results on both reconstruction (same audio-video inputs) as well as cross (different audio-video inputs) settings on Voxceleb2 and LRW datasets.

Teaching Matters: Investigating the Role of Supervision in Vision Transformers

1 code implementation CVPR 2023 Matthew Walmer, Saksham Suri, Kamal Gupta, Abhinav Shrivastava

We compare ViTs trained through different methods of supervision, and show that they learn a diverse range of behaviors in terms of their attention, representations, and downstream performance.

Towards Discovery and Attribution of Open-world GAN Generated Images

1 code implementation ICCV 2021 Sharath Girish, Saksham Suri, Saketh Rambhatla, Abhinav Shrivastava

Through extensive experiments, we show that our algorithm discovers unseen GANs with high accuracy and also generalizes to GANs trained on unseen real datasets.

Attribute Clustering +1

Learned Spatial Representations for Few-shot Talking-Head Synthesis

no code implementations ICCV 2021 Moustafa Meshry, Saksham Suri, Larry S. Davis, Abhinav Shrivastava

In contrast, we propose to factorize the representation of a subject into its spatial and style components.

On Matching Faces with Alterations due to Plastic Surgery and Disguise

no code implementations18 Nov 2018 Saksham Suri, Anush Sankaran, Mayank Vatsa, Richa Singh

In this paper, a novel framework is proposed which transfers fundamental visual features learnt from a generic image dataset to supplement a supervised face recognition model.

Face Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.