208 citations · 208 across the 5 of their papers we have counts for
7 papers
Does Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination
Mohammad Khalooei, Mohammad Sabokrou
Large audio-language models (LALMs) frequently exhibit object hallucination, affirming absent sounds. The dominant mitigation, Audio-Aware Decoding (AAD), contrasts logits under re…
Enhancing Anomaly Detection Generalization through Knowledge Exposure: The Dual Effects of Augmentation
Mohammad Akhavan Anvari, Rojina Kashefi, Vahid Reza Khazaie +2
Anomaly detection involves identifying instances within a dataset that deviate from the norm and occur infrequently. Current benchmarks tend to favor methods biased towards low div…
Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework
Mohammad Khalooei, Mohammad Mehdi Homayounpour, Maryam Amirmazlaghani
Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular import…
Diverse Knowledge Distillation (DKD): A Solution for Improving The Robustness of Ensemble Models Against Adversarial Attacks
Ali Mirzaeian, Jana Kosecka, Houman Homayoun +2
This paper proposes an ensemble learning model that is resistant to adversarial attacks. To build resilience, we introduced a training process where each member learns a radically…
End-to-End CNN+LSTM Deep Learning Approach for Bearing Fault Diagnosis
Amin Khorram, Mohammad Khalooei, Mansoor Rezghi
Fault diagnostics and prognostics are important topics both in practice and research. There is an intense pressure on industrial plants to continue reducing unscheduled downtime, p…
Self-Supervised Representation Learning via Neighborhood-Relational Encoding
Mohammad Sabokrou, Mohammad Khalooei, Ehsan Adeli
In this paper, we propose a novel self-supervised representation learning by taking advantage of a neighborhood-relational encoding (NRE) among the training data. Conventional unsu…
Adversarially Learned One-Class Classifier for Novelty Detection
Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy +1
Novelty detection is the process of identifying the observation(s) that differ in some respect from the training observations (the target class). In reality, the novelty class is o…