Search Results for author: Ali Hassani

Found 12 papers, 8 papers with code

OneFormer: One Transformer to Rule Universal Image Segmentation

1 code implementation10 Nov 2022 Jitesh Jain, Jiachen Li, MangTik Chiu, Ali Hassani, Nikita Orlov, Humphrey Shi

However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance.

Instance Segmentation Panoptic Segmentation +1

StyleNAT: Giving Each Head a New Perspective

2 code implementations10 Nov 2022 Steven Walton, Ali Hassani, Xingqian Xu, Zhangyang Wang, Humphrey Shi

Image generation has been a long sought-after but challenging task, and performing the generation task in an efficient manner is similarly difficult.

Face Generation

Dilated Neighborhood Attention Transformer

3 code implementations29 Sep 2022 Ali Hassani, Humphrey Shi

These models typically employ localized attention mechanisms, such as the sliding-window Neighborhood Attention (NA) or Swin Transformer's Shifted Window Self Attention.

Image Classification Instance Segmentation +2

AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition

no code implementations27 Sep 2022 Yulin Wang, Yang Yue, Xinhong Xu, Ali Hassani, Victor Kulikov, Nikita Orlov, Shiji Song, Humphrey Shi, Gao Huang

Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e. g., allocating the majority of computation to a task-relevant subset of frames or the most valuable image regions of each frame.

Video Recognition

DiSparse: Disentangled Sparsification for Multitask Model Compression

1 code implementation CVPR 2022 Xinglong Sun, Ali Hassani, Zhangyang Wang, Gao Huang, Humphrey Shi

We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse network architecture identified by each task even before the training starts.

Model Compression

Neighborhood Attention Transformer

5 code implementations14 Apr 2022 Ali Hassani, Steven Walton, Jiachen Li, Shen Li, Humphrey Shi

We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision.

Image Classification Object Detection +1

Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey

no code implementations22 Feb 2022 Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Imran Razzak, Kevin Lee, Chetan Arora, Ali Hassani, Arkady Zaslavsky

Indeed, Adversarial Artificial Intelligence (AI) which refers to a set of techniques that attempt to fool machine learning models with deceptive data, is a growing threat in the AI and machine learning research community, in particular for machine-critical applications.

Adversarial Attack BIG-bench Machine Learning +3

ConvMLP: Hierarchical Convolutional MLPs for Vision

4 code implementations9 Sep 2021 Jiachen Li, Ali Hassani, Steven Walton, Humphrey Shi

MLP-based architectures, which consist of a sequence of consecutive multi-layer perceptron blocks, have recently been found to reach comparable results to convolutional and transformer-based methods.

Ranked #7 on Image Classification on Flowers-102 (using extra training data)

Image Classification Instance Segmentation +3

Escaping the Big Data Paradigm with Compact Transformers

5 code implementations12 Apr 2021 Ali Hassani, Steven Walton, Nikhil Shah, Abulikemu Abuduweili, Jiachen Li, Humphrey Shi

Our models are flexible in terms of model size, and can have as little as 0. 28M parameters while achieving competitive results.

 Ranked #1 on Image Classification on Flowers-102 (using extra training data)

Fine-Grained Image Classification Superpixel Image Classification

DISCERN: Diversity-based Selection of Centroids for k-Estimation and Rapid Non-stochastic Clustering

1 code implementation IJMLC 2020 Ali Hassani, Amir Iranmanesh, Mahdi Eftekhari, Abbas Salemi

One of the applications of center-based clustering algorithms such as K-Means is partitioning data points into K clusters.

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