Hamed Pirsiavash
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hamed Pirsiavash has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Soheil Kolouri
Department of Computer Science Vanderbilt University
4 shared publications - Soroush Abbasi Koohpayegani
University of California Davis
3 shared publications - Ali Abbasi
Department of Computer Science Vanderbilt University TN USA
2 shared publications - Soroush Abbasi Koohpayegani
University of Maryland Baltimore County
2 shared publications Ajinkya Tejankar
1 shared publication- Ajinkya Tejankar
University of California Davis
1 shared publication
Latest Publications
- 23 November 2024
- Published by Springer Nature
- p. 330-349
CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization
- 23 November 2024
- Published by Springer Nature
- p. 330-349
CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization
- Open Access
SimA: Simple Softmax-free Attention for Vision Transformers
Recently, vision transformers have become very popular. However, deploying them in many applications is computationally expensive partly due to the Softmax layer in the attention block. We introduce a simple but effective, Softmax-free attention block, SimA, which normalizes query and key matrices with simple $\ell_1$-norm instead of using Softmax layer. Then, the attention block in SimA is a simple multiplication of three matrices, so SimA can dynamically change the ordering of the computation at the test time to achieve linear computation on the number of tokens or the number of channels. We empirically show that SimA applied to three SOTA variations of transformers, DeiT, XCiT, and CvT, results in on-par accuracy compared to the SOTA models, without any need for Softmax layer. Interestingly, changing SimA from multi-head to single-head has only a small effect on the accuracy, which simplifies the attention block further. The code is available here: https://github.com/UCDvision/sima
Open AccessSimA: Simple Softmax-free Attention for Vision Transformers
Recently, vision transformers have become very popular. However, deploying them in many applications is computationally expensive partly due to the Softmax layer in the attention block. We introduce a simple but effective, Softmax-free attention block, SimA, which normalizes query and key matrices with simple $\ell_1$-norm instead of using Softmax layer. Then, the attention block in SimA is a simple multiplication of three matrices, so SimA can dynamically change the ordering of the computation at the test time to achieve linear computation on the number of tokens or the number of channels. We empirically show that SimA applied to three SOTA variations of transformers, DeiT, XCiT, and CvT, results in on-par accuracy compared to the SOTA models, without any need for Softmax layer. Interestingly, changing SimA from multi-head to single-head has only a small effect on the accuracy, which simplifies the attention block further. The code is available here: https://github.com/UCDvision/sima
- Open Access
One Category One Prompt: Dataset Distillation using Diffusion Models
The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive datasets into a much smaller yet representative set of synthetic samples. However, traditional dataset distillation approaches often struggle to scale effectively with high-resolution images and more complex architectures due to the limitations in bi-level optimization. Recently, several works have proposed exploiting knowledge distillation with decoupled optimization schemes to scale up dataset distillation. Although these methods effectively address the scalability issue, they rely on extensive image augmentations requiring the storage of soft labels for augmented images. In this paper, we introduce Dataset Distillation using Diffusion Models (D3M) as a novel paradigm for dataset distillation, leveraging recent advancements in generative text-to-image foundation models. Our approach utilizes textual inversion, a technique for fine-tuning text-to-image generative models, to create concise and informative representations for large datasets. By employing these learned text prompts, we can efficiently store and infer new samples for introducing data variability within a fixed memory budget. We show the effectiveness of our method through extensive experiments across various computer vision benchmark datasets with different memory budgets.
Open AccessOne Category One Prompt: Dataset Distillation using Diffusion Models
The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive datasets into a much smaller yet representative set of synthetic samples. However, traditional dataset distillation approaches often struggle to scale effectively with high-resolution images and more complex architectures due to the limitations in bi-level optimization. Recently, several works have proposed exploiting knowledge distillation with decoupled optimization schemes to scale up dataset distillation. Although these methods effectively address the scalability issue, they rely on extensive image augmentations requiring the storage of soft labels for augmented images. In this paper, we introduce Dataset Distillation using Diffusion Models (D3M) as a novel paradigm for dataset distillation, leveraging recent advancements in generative text-to-image foundation models. Our approach utilizes textual inversion, a technique for fine-tuning text-to-image generative models, to create concise and informative representations for large datasets. By employing these learned text prompts, we can efficiently store and infer new samples for introducing data variability within a fixed memory budget. We show the effectiveness of our method through extensive experiments across various computer vision benchmark datasets with different memory budgets.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 1812-1816
Multi-Agent Lifelong Implicit Neural Learning
Implicit neural representations (INRs) have emerged as powerful tools for the continuous representation of signals, finding applications in imaging, computer graphics, and signal compression. Additionally, decentralized multi-agent systems are crucial in various applications, frequently leading to enhanced reliability and efficiencies in computation and communication. In this paper, we explore using multi-agent Lifelong Learning (LL) systems for learning INRs. We propose a rigorous problem setup and evaluation plan to investigate the efficacy of such systems compared to single-agent and multi-task learning baselines. Our research, conducted across varied dimensions, demonstrates promising results, thereby contributing a novel perspective to the realm of continual learning.
- 30 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 1812-1816
Multi-Agent Lifelong Implicit Neural Learning
Implicit neural representations (INRs) have emerged as powerful tools for the continuous representation of signals, finding applications in imaging, computer graphics, and signal compression. Additionally, decentralized multi-agent systems are crucial in various applications, frequently leading to enhanced reliability and efficiencies in computation and communication. In this paper, we explore using multi-agent Lifelong Learning (LL) systems for learning INRs. We propose a rigorous problem setup and evaluation plan to investigate the efficacy of such systems compared to single-agent and multi-task learning baselines. Our research, conducted across varied dimensions, demonstrates promising results, thereby contributing a novel perspective to the realm of continual learning.
- Open Access
Surveying Nutrient Assessment with Photographs of Meals (SNAPMe): A Benchmark Dataset of Food Photos for Dietary Assessment
Photo-based dietary assessment is becoming more feasible as artificial intelligence methods improve. However, advancement of these methods for dietary assessment in research settings has been hindered by the lack of an appropriate dataset against which to benchmark algorithm performance. We conducted the Surveying Nutrient Assessment with Photographs of Meals (SNAPMe) study (ClinicalTrials ID: NCT05008653) to pair meal photographs with traditional food records. Participants were recruited nationally, and 110 enrollment meetings were completed via web-based video conferencing. Participants uploaded and annotated their meal photos using a mobile phone app called Bitesnap and completed food records using the Automated Self-Administered 24-h Dietary Assessment Tool (ASA24®) version 2020. Participants included photos before and after eating non-packaged and multi-serving packaged meals, as well as photos of the front and ingredient labels for single-serving packaged foods. The SNAPMe Database (DB) contains 3311 unique food photos linked with 275 ASA24 food records from 95 participants who photographed all foods consumed and recorded food records in parallel for up to 3 study days each. The use of the SNAPMe DB to evaluate ingredient prediction demonstrated that the publicly available algorithms FB Inverse Cooking and Im2Recipe performed poorly, especially for single-ingredient foods and beverages. Correlations between nutrient estimates common to the Bitesnap and ASA24 dietary assessment tools indicated a range in predictive capacity across nutrients (cholesterol, adjusted R2 = 0.85, p < 0.0001; food folate, adjusted R2 = 0.21, p < 0.05). SNAPMe DB is a publicly available benchmark for photo-based dietary assessment in nutrition research. Its demonstrated utility suggested areas of needed improvement, especially the prediction of single-ingredient foods and beverages.
Open AccessSurveying Nutrient Assessment with Photographs of Meals (SNAPMe): A Benchmark Dataset of Food Photos for Dietary Assessment
Photo-based dietary assessment is becoming more feasible as artificial intelligence methods improve. However, advancement of these methods for dietary assessment in research settings has been hindered by the lack of an appropriate dataset against which to benchmark algorithm performance. We conducted the Surveying Nutrient Assessment with Photographs of Meals (SNAPMe) study (ClinicalTrials ID: NCT05008653) to pair meal photographs with traditional food records. Participants were recruited nationally, and 110 enrollment meetings were completed via web-based video conferencing. Participants uploaded and annotated their meal photos using a mobile phone app called Bitesnap and completed food records using the Automated Self-Administered 24-h Dietary Assessment Tool (ASA24®) version 2020. Participants included photos before and after eating non-packaged and multi-serving packaged meals, as well as photos of the front and ingredient labels for single-serving packaged foods. The SNAPMe Database (DB) contains 3311 unique food photos linked with 275 ASA24 food records from 95 participants who photographed all foods consumed and recorded food records in parallel for up to 3 study days each. The use of the SNAPMe DB to evaluate ingredient prediction demonstrated that the publicly available algorithms FB Inverse Cooking and Im2Recipe performed poorly, especially for single-ingredient foods and beverages. Correlations between nutrient estimates common to the Bitesnap and ASA24 dietary assessment tools indicated a range in predictive capacity across nutrients (cholesterol, adjusted R2 = 0.85, p < 0.0001; food folate, adjusted R2 = 0.21, p < 0.05). SNAPMe DB is a publicly available benchmark for photo-based dietary assessment in nutrition research. Its demonstrated utility suggested areas of needed improvement, especially the prediction of single-ingredient foods and beverages.
- Open Access
BrainWash: A Poisoning Attack to Forget in Continual Learning
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its susceptibility to adversarial attacks, especially with the aim of inducing forgetting. In this paper, we introduce "BrainWash," a novel data poisoning method tailored to impose forgetting on a continual learner. By adding the BrainWash noise to a variety of baselines, we demonstrate how a trained continual learner can be induced to forget its previously learned tasks catastrophically, even when using these continual learning baselines. An important feature of our approach is that the attacker requires no access to previous tasks' data and is armed merely with the model's current parameters and the data belonging to the most recent task. Our extensive experiments highlight the efficacy of BrainWash, showcasing degradation in performance across various regularization-based continual learning methods.
Open AccessBrainWash: A Poisoning Attack to Forget in Continual Learning
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its susceptibility to adversarial attacks, especially with the aim of inducing forgetting. In this paper, we introduce "BrainWash," a novel data poisoning method tailored to impose forgetting on a continual learner. By adding the BrainWash noise to a variety of baselines, we demonstrate how a trained continual learner can be induced to forget its previously learned tasks catastrophically, even when using these continual learning baselines. An important feature of our approach is that the attacker requires no access to previous tasks' data and is armed merely with the model's current parameters and the data belonging to the most recent task. Our extensive experiments highlight the efficacy of BrainWash, showcasing degradation in performance across various regularization-based continual learning methods.
- Open Access
Is Multi-Task Learning an Upper Bound for Continual Learning?
Continual and multi-task learning are common machine learning approaches to learning from multiple tasks. The existing works in the literature often assume multi-task learning as a sensible performance upper bound for various continual learning algorithms. While this assumption is empirically verified for different continual learning benchmarks, it is not rigorously justified. Moreover, it is imaginable that when learning from multiple tasks, a small subset of these tasks could behave as adversarial tasks reducing the overall learning performance in a multi-task setting. In contrast, continual learning approaches can avoid the performance drop caused by such adversarial tasks to preserve their performance on the rest of the tasks, leading to better performance than a multi-task learner. This paper proposes a novel continual self-supervised learning setting, where each task corresponds to learning an invariant representation for a specific class of data augmentations. In this setting, we show that continual learning often beats multi-task learning on various benchmark datasets, including MNIST, CIFAR-10, and CIFAR-100.
Open AccessIs Multi-Task Learning an Upper Bound for Continual Learning?
Continual and multi-task learning are common machine learning approaches to learning from multiple tasks. The existing works in the literature often assume multi-task learning as a sensible performance upper bound for various continual learning algorithms. While this assumption is empirically verified for different continual learning benchmarks, it is not rigorously justified. Moreover, it is imaginable that when learning from multiple tasks, a small subset of these tasks could behave as adversarial tasks reducing the overall learning performance in a multi-task setting. In contrast, continual learning approaches can avoid the performance drop caused by such adversarial tasks to preserve their performance on the rest of the tasks, leading to better performance than a multi-task learner. This paper proposes a novel continual self-supervised learning setting, where each task corresponds to learning an invariant representation for a specific class of data augmentations. In this setting, we show that continual learning often beats multi-task learning on various benchmark datasets, including MNIST, CIFAR-10, and CIFAR-100.
- Open Access
Backdoor Attacks on Self-Supervised Learning
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks - where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images. The model performance is good on clean test images, but the attacker can manipulate the decision of the model by showing the trigger at test time. Backdoor attacks have been studied extensively in supervised learning and to the best of our knowledge, we are the first to study them for self-supervised learning. Backdoor attacks are more practical in self-supervised learning, since the use of large unlabeled data makes data inspection to remove poisons prohibitive. We show that in our targeted attack, the attacker can produce many false positives for the target category by using the trigger at test time. We also propose a defense method based on knowledge distillation that succeeds in neutralizing the attack. Our code is available here: https://github.com/UMBCvision/SSL-Backdoor .
Open AccessBackdoor Attacks on Self-Supervised Learning
Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use an inductive bias that random augmentations (e.g., random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks - where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images. The model performance is good on clean test images, but the attacker can manipulate the decision of the model by showing the trigger at test time. Backdoor attacks have been studied extensively in supervised learning and to the best of our knowledge, we are the first to study them for self-supervised learning. Backdoor attacks are more practical in self-supervised learning, since the use of large unlabeled data makes data inspection to remove poisons prohibitive. We show that in our targeted attack, the attacker can produce many false positives for the target category by using the trigger at test time. We also propose a defense method based on knowledge distillation that succeeds in neutralizing the attack. Our code is available here: https://github.com/UMBCvision/SSL-Backdoor .
- Open Access
Consistent Explanations by Contrastive Learning
Post-hoc explanation methods, e.g., Grad-CAM, enable humans to inspect the spatial regions responsible for a particular network decision. However, it is shown that such explanations are not always consistent with human priors, such as consistency across image transformations. Given an interpretation algorithm, e.g., Grad-CAM, we introduce a novel training method to train the model to produce more consistent explanations. Since obtaining the ground truth for a desired model interpretation is not a well-defined task, we adopt ideas from contrastive self-supervised learning, and apply them to the interpretations of the model rather than its embeddings. We show that our method, Contrastive Grad-CAM Consistency (CGC), results in Grad-CAM interpretation heatmaps that are more consistent with human annotations while still achieving comparable classification accuracy. Moreover, our method acts as a regularizer and improves the accuracy on limited-data, fine-grained classification settings. In addition, because our method does not rely on annotations, it allows for the incorporation of unlabeled data into training, which enables better generalization of the model. Our code is available here: https://github.com/UCDvision/CGC
Open AccessConsistent Explanations by Contrastive Learning
Post-hoc explanation methods, e.g., Grad-CAM, enable humans to inspect the spatial regions responsible for a particular network decision. However, it is shown that such explanations are not always consistent with human priors, such as consistency across image transformations. Given an interpretation algorithm, e.g., Grad-CAM, we introduce a novel training method to train the model to produce more consistent explanations. Since obtaining the ground truth for a desired model interpretation is not a well-defined task, we adopt ideas from contrastive self-supervised learning, and apply them to the interpretations of the model rather than its embeddings. We show that our method, Contrastive Grad-CAM Consistency (CGC), results in Grad-CAM interpretation heatmaps that are more consistent with human annotations while still achieving comparable classification accuracy. Moreover, our method acts as a regularizer and improves the accuracy on limited-data, fine-grained classification settings. In addition, because our method does not rely on annotations, it allows for the incorporation of unlabeled data into training, which enables better generalization of the model. Our code is available here: https://github.com/UCDvision/CGC
- Open Access
A Simple Baseline for Low-Budget Active Learning
Active learning focuses on choosing a subset of unlabeled data to be labeled. However, most such methods assume that a large subset of the data can be annotated. We are interested in low-budget active learning where only a small subset (e.g., 0.2% of ImageNet) can be annotated. Instead of proposing a new query strategy to iteratively sample batches of unlabeled data given an initial pool, we learn rich features by an off-the-shelf self-supervised learning method only once, and then study the effectiveness of different sampling strategies given a low labeling budget on a variety of datasets including ImageNet. We show that although the state-of-the-art active learning methods work well given a large labeling budget, a simple K-means clustering algorithm can outperform them on low budgets. We believe this method can be used as a simple baseline for low-budget active learning on image classification. Code is available at: https://github.com/UCDvision/low-budget-al
Open AccessA Simple Baseline for Low-Budget Active Learning
Active learning focuses on choosing a subset of unlabeled data to be labeled. However, most such methods assume that a large subset of the data can be annotated. We are interested in low-budget active learning where only a small subset (e.g., 0.2% of ImageNet) can be annotated. Instead of proposing a new query strategy to iteratively sample batches of unlabeled data given an initial pool, we learn rich features by an off-the-shelf self-supervised learning method only once, and then study the effectiveness of different sampling strategies given a low labeling budget on a variety of datasets including ImageNet. We show that although the state-of-the-art active learning methods work well given a large labeling budget, a simple K-means clustering algorithm can outperform them on low budgets. We believe this method can be used as a simple baseline for low-budget active learning on image classification. Code is available at: https://github.com/UCDvision/low-budget-al