Chaim Baskin
YOU?
Author Swipe
View article: Robustness of Visual-Based Aerial Navigation to Real-World Adversarial Attacks
Robustness of Visual-Based Aerial Navigation to Real-World Adversarial Attacks Open
Imaging technologies are pivotal in the emerging aerial navigation ecosystem. However, these technologies are vulnerable to adversarial attacks. Current methods for enhancing the adversarial robustness of learned models are primarily based…
View article: Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking Open
Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval, where joint-encoder rerankers are standard, comparable vision--language rerankers a…
View article: WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP
WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP Open
We introduce WAVECLIP, a single unified model for adaptive resolution inference in CLIP, enabled by wavelet-based tokenization. WAVECLIP replaces standard patch embeddings with a multi-level wavelet decomposition, enabling the model to pro…
View article: Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling
Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling Open
Generalization in medical segmentation models is challenging due to limited annotated datasets and imaging variability. To address this, we propose Retinal Layout-Aware Diffusion (RLAD), a novel diffusion-based framework for generating con…
View article: T1-PILOT: Optimized Trajectories for T1 Mapping Acceleration
T1-PILOT: Optimized Trajectories for T1 Mapping Acceleration Open
Cardiac T1 mapping provides critical quantitative insights into myocardial tissue composition, enabling the assessment of pathologies such as fibrosis, inflammation, and edema. However, the inherently dynamic nature of the heart imposes st…
View article: Adversarial Robustness in Parameter-Space Classifiers
Adversarial Robustness in Parameter-Space Classifiers Open
Implicit Neural Representations (INRs) have been recently garnering increasing interest in various research fields, mainly due to their ability to represent large, complex data in a compact and continuous manner. Past work further showed t…
View article: On Adversarial Attacks In Acoustic Drone Localization
On Adversarial Attacks In Acoustic Drone Localization Open
Multi-rotor aerial autonomous vehicles (MAVs, more widely known as "drones") have been generating increased interest in recent years due to their growing applicability in a vast and diverse range of fields (e.g., agriculture, commercial de…
View article: Jailbreak Attack Initializations as Extractors of Compliance Directions
Jailbreak Attack Initializations as Extractors of Compliance Directions Open
Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space. Recent works show that initializing attacks via self-transfer from other prompts significa…
View article: Sparse patches adversarial attacks via extrapolating point-wise information
Sparse patches adversarial attacks via extrapolating point-wise information Open
Sparse and patch adversarial attacks were previously shown to be applicable in realistic settings and are considered a security risk to autonomous systems. Sparse adversarial perturbations constitute a setting in which the adversarial pert…
View article: Hysteresis Activation Function for Efficient Inference
Hysteresis Activation Function for Efficient Inference Open
The widely used ReLU is favored for its hardware efficiency, {as the implementation at inference is a one bit sign case,} yet suffers from issues such as the ``dying ReLU'' problem, where during training, neurons fail to activate and const…
View article: Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods Open
Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context L…
View article: Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks Open
Message Passing Graph Neural Networks (MPGNNs) have emerged as the preferred method for modeling complex interactions across diverse graph entities. While the theory of such models is well understood, their aggregation module has not recei…
View article: TEAM PILOT -- Learned Feasible Extendable Set of Dynamic MRI Acquisition Trajectories
TEAM PILOT -- Learned Feasible Extendable Set of Dynamic MRI Acquisition Trajectories Open
Dynamic Magnetic Resonance Imaging (MRI) is a crucial non-invasive method used to capture the movement of internal organs and tissues, making it a key tool for medical diagnosis. However, dynamic MRI faces a major challenge: long acquisiti…
View article: Robot Instance Segmentation with Few Annotations for Grasping
Robot Instance Segmentation with Few Annotations for Grasping Open
The ability of robots to manipulate objects relies heavily on their aptitude for visual perception. In domains characterized by cluttered scenes and high object variability, most methods call for vast labeled datasets, laboriously hand-ann…
View article: Noisy Annotations in Semantic Segmentation
Noisy Annotations in Semantic Segmentation Open
Obtaining accurate labels for instance segmentation is particularly challenging due to the complex nature of the task. Each image necessitates multiple annotations, encompassing not only the object class but also its precise spatial bounda…
View article: Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency
Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency Open
Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offe…
View article: AMED: Automatic Mixed-Precision Quantization for Edge Devices
AMED: Automatic Mixed-Precision Quantization for Edge Devices Open
Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. This makes them highly appropriate for systems with limited resources and low power capacity.…
View article: DEPTH: Discourse Education through Pre-Training Hierarchically
DEPTH: Discourse Education through Pre-Training Hierarchically Open
Language Models (LMs) struggle with linguistic understanding at the discourse level, even though discourse patterns such as coherence, cohesion, and narrative flow are prevalent in their pre-training data. To improve the discourse capabili…
View article: Leveraging Latents for Efficient Thermography Classification and Segmentation
Leveraging Latents for Efficient Thermography Classification and Segmentation Open
Breast cancer is a prominent health concern worldwide, currently being the secondmost common and second-deadliest type of cancer in women. While current breast cancer diagnosis mainly relies on mammography imaging, in recent years the use …
View article: Leveraging Temporal Graph Networks Using Module Decoupling
Leveraging Temporal Graph Networks Using Module Decoupling Open
Modern approaches for learning on dynamic graphs have adopted the use of batches instead of applying updates one by one. The use of batches allows these techniques to become helpful in streaming scenarios where updates to graphs are receiv…
View article: Single Image Test-Time Adaptation for Segmentation
Single Image Test-Time Adaptation for Segmentation Open
Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation. This work explores adapting segmentation models to a single unlabelled im…
View article: Semi-Supervised Semantic Segmentation via Marginal Contextual Information
Semi-Supervised Semantic Segmentation via Marginal Contextual Information Open
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the spa…
View article: Enhanced Meta Label Correction for Coping with Label Corruption
Enhanced Meta Label Correction for Coping with Label Corruption Open
Traditional methods for learning with the presence of noisy labels have successfully handled datasets with artificially injected noise but still fall short of adequately handling real-world noise. With the increasing use of meta-learning i…
View article: Class-Conditioned Transformation for Enhanced Robust Image Classification
Class-Conditioned Transformation for Enhanced Robust Image Classification Open
Robust classification methods predominantly concentrate on algorithms that address a specific threat model, resulting in ineffective defenses against other threat models. Real-world applications are exposed to this vulnerability, as malici…
View article: Bimodal-Distributed Binarized Neural Networks
Bimodal-Distributed Binarized Neural Networks Open
Binary neural networks (BNNs) are an extremely promising method for reducing deep neural networks’ complexity and power consumption significantly. Binarization techniques, however, suffer from ineligible performance degradation compared to…
View article: Physical Passive Patch Adversarial Attacks on Visual Odometry Systems
Physical Passive Patch Adversarial Attacks on Visual Odometry Systems Open
Deep neural networks are known to be susceptible to adversarial perturbations -- small perturbations that alter the output of the network and exist under strict norm limitations. While such perturbations are usually discussed as tailored t…
View article: GoToNet: Fast Monocular Scene Exposure and Exploration
GoToNet: Fast Monocular Scene Exposure and Exploration Open
Autonomous scene exposure and exploration, especially in localization or communication-denied areas, useful for finding targets in unknown scenes, remains a challenging problem in computer navigation. In this work, we present a novel metho…
View article: Strategic Classification with Graph Neural Networks
Strategic Classification with Graph Neural Networks Open
Strategic classification studies learning in settings where users can modify their features to obtain favorable predictions. Most current works focus on simple classifiers that trigger independent user responses. Here we examine the implic…