20 citations · 57 across the 21 of their papers we have counts for
24 papers
Diagnosing Capability Gaps in Fine-Tuning Data
Saeid Asgari Taghanaki, Rakshanda Agarwal, Bruce Sun +10
Fine-tuning large language models (LLMs) for domain-specific tasks requires training datasets that comprehensively cover the target capabilities a practitioner needs. Yet identifyi…
Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy
Saeid Asgari Taghanaki, Joao Monteiro
Large language models (LLMs) have demonstrated remarkable proficiency in generating detailed and coherent explanations of complex concepts. However, the extent to which these model…
Disentangled PET Lesion Segmentation
Tanya Gatsak, Kumar Abhishek, Hanene Ben Yedder +2
PET imaging is an invaluable tool in clinical settings as it captures the functional activity of both healthy anatomy and cancerous lesions. Developing automatic lesion segmentatio…
MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs
Saeid Asgari Taghanaki, Aliasgahr Khani, Amir Khasahmadi
Existing benchmarks for large language models (LLMs) increasingly struggle to differentiate between top-performing models, underscoring the need for more challenging evaluation fra…
How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?
Saeid Asgari Taghanaki, Joseph Lambourne, Alana Mongkhounsavath
Large foundation models have revolutionized the field, yet challenges remain in optimizing multi-modal models for specialized visual tasks. We propose a novel, generalizable method…
SMITE: Segment Me In TimE
Amirhossein Alimohammadi, Sauradip Nag, Saeid Asgari Taghanaki +3
Segmenting an object in a video presents significant challenges. Each pixel must be accurately labelled, and these labels must remain consistent across frames. The difficulty incre…
Detecting Generative Parroting through Overfitting Masked Autoencoders
Saeid Asgari Taghanaki, Joseph Lambourne
The advent of generative AI models has revolutionized digital content creation, yet it introduces challenges in maintaining copyright integrity due to generative parroting, where m…
TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models
Saeid Asgari Taghanaki, Aliasghar Khani, Ali Saheb Pasand +4
Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that levera…
Sketch-A-Shape: Zero-Shot Sketch-to-3D Shape Generation
Aditya Sanghi, Pradeep Kumar Jayaraman, Arianna Rampini +4
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. This motivates…
MaskTune: Mitigating Spurious Correlations by Forcing to Explore
Saeid Asgari Taghanaki, Aliasghar Khani, Fereshte Khani +4
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…
Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness
Saeid Asgari Taghanaki, Ali Gholami, Fereshte Khani +4
Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy. However, we demonstrate that BN co…
Group-disentangled Representation Learning with Weakly-Supervised Regularization
Linh Tran, Amir Hosein Khasahmadi, Aditya Sanghi +1
Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate…
Robust Representation Learning via Perceptual Similarity Metrics
Saeid Asgari Taghanaki, Kristy Choi, Amir Khasahmadi +1
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious inpu…
RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers
Saeid Asgari Taghanaki, Jieliang Luo, Ran Zhang +3
The 3D deep learning community has seen significant strides in pointcloud processing over the last few years. However, the datasets on which deep models have been trained have larg…
PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
Saeid Asgari Taghanaki, Kaveh Hassani, Pradeep Kumar Jayaraman +2
Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, o…
Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders
Saeid Asgari Taghanaki, Mohammad Havaei, Alex Lamb +3
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. There is a growing…
Signed Input Regularization
Saeid Asgari Taghanaki, Kumar Abhishek, Ghassan Hamarneh
Over-parameterized deep models usually over-fit to a given training distribution, which makes them sensitive to small changes and out-of-distribution samples at inference time, lea…
Deep Semantic Segmentation of Natural and Medical Images: A Review
Saeid Asgari Taghanaki, Kumar Abhishek, Joseph Paul Cohen +2
The semantic image segmentation task consists of classifying each pixel of an image into an instance, where each instance corresponds to a class. This task is a part of the concept…
Improved Inference via Deep Input Transfer
Saied Asgari Taghanaki, Kumar Abhishek, Ghassan Hamarneh
Although numerous improvements have been made in the field of image segmentation using convolutional neural networks, the majority of these improvements rely on training with large…
InfoMask: Masked Variational Latent Representation to Localize Chest Disease
Saeid Asgari Taghanaki, Mohammad Havaei, Tess Berthier +4
The scarcity of richly annotated medical images is limiting supervised deep learning based solutions to medical image analysis tasks, such as localizing discriminatory radiomic dis…
A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations
Saeid Asgari Taghanaki, Kumar Abhishek, Shekoofeh Azizi +1
The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations. To tackle this problem, we propose a non-linea…
Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
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. However, there is not yet…
Select, Attend, and Transfer: Light, Learnable Skip Connections
Saeid Asgari Taghanaki, Aicha Bentaieb, Anmol Sharma +8
Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risk…
Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation
Saeid Asgari Taghanaki, Yefeng Zheng, S. Kevin Zhou +5
Simultaneous segmentation of multiple organs from different medical imaging modalities is a crucial task as it can be utilized for computer-aided diagnosis, computer-assisted surge…