Search Results for author: Saeed Khorram

Found 10 papers, 4 papers with code

Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions

1 code implementation26 Feb 2024 Saeed Khorram, Mingqi Jiang, Mohamad Shahbazi, Mohamad H. Danesh, Li Fuxin

In the presence of imbalanced multi-class training data, GANs tend to favor classes with more samples, leading to the generation of low-quality and less diverse samples in tail classes.

Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods

no code implementations13 Dec 2022 Mingqi Jiang, Saeed Khorram, Li Fuxin

In order to learn better about how different visual recognition backbones make decisions, we propose a methodology that systematically applies deep explanation algorithms on a dataset-wide basis, and compares the statistics generated from the amount and nature of the explanations to gain insights about the decision-making of different models.

Decision Making

Cycle-Consistent Counterfactuals by Latent Transformations

no code implementations CVPR 2022 Saeed Khorram, Li Fuxin

CounterFactual (CF) visual explanations try to find images similar to the query image that change the decision of a vision system to a specified outcome.

counterfactual

From Heatmaps to Structural Explanations of Image Classifiers

no code implementations13 Sep 2021 Li Fuxin, Zhongang Qi, Saeed Khorram, Vivswan Shitole, Prasad Tadepalli, Minsuk Kahng, Alan Fern

This paper summarizes our endeavors in the past few years in terms of explaining image classifiers, with the aim of including negative results and insights we have gained.

Stochastic Block-ADMM for Training Deep Networks

no code implementations1 May 2021 Saeed Khorram, Xiao Fu, Mohamad H. Danesh, Zhongang Qi, Li Fuxin

We prove the convergence of our proposed method and justify its capabilities through experiments in supervised and weakly-supervised settings.

iGOS++: Integrated Gradient Optimized Saliency by Bilateral Perturbations

2 code implementations31 Dec 2020 Saeed Khorram, Tyler Lawson, Fuxin Li

In this paper, we present iGOS++, a framework to generate saliency maps that are optimized for altering the output of the black-box system by either removing or preserving only a small fraction of the input.

Re-understanding Finite-State Representations of Recurrent Policy Networks

1 code implementation6 Jun 2020 Mohamad H. Danesh, Anurag Koul, Alan Fern, Saeed Khorram

We introduce an approach for understanding control policies represented as recurrent neural networks.

Atari Games

Sleep Stage Scoring Using Joint Frequency-Temporal and Unsupervised Features

no code implementations10 Apr 2020 Mohamadreza Jafaryani, Saeed Khorram, Vahid Pourahmadi, Minoo Shahbazi

Detection of such sleep disorders is usually possible by analyzing a number of vital signals that have been collected from the patients.

Visualizing Deep Networks by Optimizing with Integrated Gradients

1 code implementation2 May 2019 Zhongang Qi, Saeed Khorram, Li Fuxin

Understanding and interpreting the decisions made by deep learning models is valuable in many domains.

Embedding Deep Networks into Visual Explanations

no code implementations15 Sep 2017 Zhongang Qi, Saeed Khorram, Fuxin Li

The XNN works by learning a nonlinear embedding of a high-dimensional activation vector of a deep network layer into a low-dimensional explanation space while retaining faithfulness i. e., the original deep learning predictions can be constructed from the few concepts extracted by our explanation network.

Image Classification

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