Search Results for author: Saeid Asgari Taghanaki

Found 17 papers, 6 papers with code

Radial Basis Feature Transformation to Arm CNNs Against Adversarial Attacks

no code implementations ICLR 2019 Saeid Asgari Taghanaki, Shekoofeh Azizi, Ghassan Hamarneh

The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations.

Image Classification

SLiMe: Segment Like Me

1 code implementation6 Sep 2023 Aliasghar Khani, Saeid Asgari Taghanaki, Aditya Sanghi, Ali Mahdavi Amiri, Ghassan Hamarneh

Then, using the extracted attention maps, the text embeddings of Stable Diffusion are optimized such that, each of them, learn about a single segmented region from the training image.

3D Shape Generation Segmentation

TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models

no code implementations1 Sep 2023 Saeid Asgari Taghanaki, Aliasghar Khani, Amir Khasahmadi, Aditya Sanghi, Karl D. D. Willis, Ali Mahdavi-Amiri

These sentences are then used to extract the most frequent words, providing a comprehensive understanding of the learned features and patterns within the classifier.

Decision Making

Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generation

no code implementations8 Jul 2023 Aditya Sanghi, Pradeep Kumar Jayaraman, Arianna Rampini, Joseph Lambourne, Hooman Shayani, Evan Atherton, Saeid Asgari Taghanaki

Significant progress has recently been made in creative applications of large pre-trained models for downstream tasks in 3D vision, such as text-to-shape generation.

3D Shape Generation Text-to-Shape Generation

MaskTune: Mitigating Spurious Correlations by Forcing to Explore

1 code implementation30 Sep 2022 Saeid Asgari Taghanaki, Aliasghar Khani, Fereshte Khani, Ali Gholami, Linh Tran, Ali Mahdavi-Amiri, Ghassan Hamarneh

A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features.

Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness

no code implementations4 Jul 2022 Saeid Asgari Taghanaki, Ali Gholami, Fereshte Khani, Kristy Choi, Linh Tran, Ran Zhang, Aliasghar Khani

Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy.

Robust Representation Learning via Perceptual Similarity Metrics

no code implementations11 Jun 2021 Saeid Asgari Taghanaki, Kristy Choi, Amir Khasahmadi, Anirudh Goyal

A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features.

Out-of-Distribution Generalization Representation Learning

PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing

1 code implementation9 Jul 2020 Saeid Asgari Taghanaki, Kaveh Hassani, Pradeep Kumar Jayaraman, Amir Hosein Khasahmadi, Tonya Custis

We show that coupling a PointMask layer with an arbitrary model can discern the points in the input space which contribute the most to the prediction score, thereby leading to interpretability.

3D Point Cloud Classification Robust classification

Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders

no code implementations12 May 2020 Saeid Asgari Taghanaki, Mohammad Havaei, Alex Lamb, Aditya Sanghi, Ara Danielyan, Tonya Custis

The latent variables learned by VAEs have seen considerable interest as an unsupervised way of extracting features, which can then be used for downstream tasks.

Signed Input Regularization

no code implementations16 Nov 2019 Saeid Asgari Taghanaki, Kumar Abhishek, Ghassan Hamarneh

To test the effectiveness of the proposed idea and compare it with other competing methods, we design several test scenarios, such as classification performance, uncertainty, out-of-distribution, and robustness analyses.

Data Augmentation

Deep Semantic Segmentation of Natural and Medical Images: A Review

no code implementations16 Oct 2019 Saeid Asgari Taghanaki, Kumar Abhishek, Joseph Paul Cohen, Julien Cohen-Adad, Ghassan Hamarneh

The semantic image segmentation task consists of classifying each pixel of an image into an instance, where each instance corresponds to a class.

Image Segmentation Medical Image Segmentation +3

InfoMask: Masked Variational Latent Representation to Localize Chest Disease

no code implementations28 Mar 2019 Saeid Asgari Taghanaki, Mohammad Havaei, Tess Berthier, Francis Dutil, Lisa Di Jorio, Ghassan Hamarneh, Yoshua Bengio

The scarcity of richly annotated medical images is limiting supervised deep learning based solutions to medical image analysis tasks, such as localizing discriminatory radiomic disease signatures.

Multiple Instance Learning

Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks

no code implementations9 Jul 2018 Saeid Asgari Taghanaki, Arkadeep Das, Ghassan Hamarneh

Recently, there have been several successful deep learning approaches for automatically classifying chest X-ray images into different disease categories.

Classification General Classification +1

Select, Attend, and Transfer: Light, Learnable Skip Connections

no code implementations14 Apr 2018 Saeid Asgari Taghanaki, Aicha Bentaieb, Anmol Sharma, S. Kevin Zhou, Yefeng Zheng, Bogdan Georgescu, Puneet Sharma, Sasa Grbic, Zhoubing Xu, Dorin Comaniciu, Ghassan Hamarneh

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients.

Segmentation

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