Search Results for author:
Found 41 papers, 29 papers with code
Sparse patches adversarial attacks via extrapolating point-wise information
Our approach enables simultaneous optimization of multiple sparse patches' locations and perturbations for any given number and shape.
Hysteresis Activation Function for Efficient Inference
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 constantly remain at zero, as highlighted by Lu et al.
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context Learning (ICL) adapts the model to a new task by simply including examples in the input without any training.
Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
Message Passing Graph Neural Networks (MPGNNs) have emerged as the preferred method for modeling complex interactions across diverse graph entities.
TEAM PILOT -- Learned Feasible Extendable Set of Dynamic MRI Acquisition Trajectories
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.
Robot Instance Segmentation with Few Annotations for Grasping
The ability of robots to manipulate objects relies heavily on their aptitude for visual perception.
Ranked #1 on
Instance Segmentation
on ARMBench
Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters
Obtaining accurate labels for instance segmentation is particularly challenging due to the complex nature of the task.
Ranked #1 on
Instance Segmentation
on COCO-N Medium
Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency
The code for our experiments is available at https://github. com/clearProject/CLEAR/tree/main
DEPTH: Discourse Education through Pre-Training Hierarchically
Language Models (LMs) often 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.
Leveraging Latents for Efficient Thermography Classification and Segmentation
In this work, we present a novel algorithm for both breast cancer classification and segmentation.
Active propulsion noise shaping for multi-rotor aircraft localization
Multi-rotor aerial autonomous vehicles (MAVs) primarily rely on vision for navigation purposes.
Leveraging Temporal Graph Networks Using Module Decoupling
Modern approaches for learning on dynamic graphs have adopted the use of batches instead of applying updates one by one.
Single Image Test-Time Adaptation for Segmentation
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.
Semi-Supervised Semantic Segmentation via Marginal Contextual Information
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation.
Enhanced Meta Label Correction for Coping with Label Corruption
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.
Class-Conditioned Transformation for Enhanced Robust Image Classification
Robust classification methods predominantly concentrate on algorithms that address a specific threat model, resulting in ineffective defenses against other threat models.
Physical Passive Patch Adversarial Attacks on Visual Odometry Systems
While such perturbations are usually discussed as tailored to a specific input, a universal perturbation can be constructed to alter the model's output on a set of inputs.
GoToNet: Fast Monocular Scene Exposure and Exploration
In this work, we present a novel method for real-time environment exploration, whose only requirements are a visually similar dataset for pre-training, enough lighting in the scene, and an on-board forward-looking RGB camera for environmental sensing.
Strategic Classification with Graph Neural Networks
Strategic classification studies learning in settings where users can modify their features to obtain favorable predictions.
AMED: Automatic Mixed-Precision Quantization for Edge Devices
Challenging this assumption, we argue that the optimal minimum changes as the precision changes, and thus, it is better to look at quantization as a random process, placing the foundation for a different approach to quantize neural networks, which, during the training procedure, quantizes the model to a different precision, looks at the bit allocation as a Markov Decision Process, and then, finds an optimal bitwidth allocation for measuring specified behaviors on a specific device via direct signals from the particular hardware architecture.
Bimodal Distributed Binarized Neural Networks
The proposed method consists of a training scheme that we call Weight Distribution Mimicking (WDM), which efficiently imitates the full-precision network weight distribution to their binary counterpart.
A Simple and Universal Rotation Equivariant Point-cloud Network
Equivariance to permutations and rigid motions is an important inductive bias for various 3D learning problems.
Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings
Two popular alternatives that offer a good trade-off between expressive power and computational efficiency are combinatorial (i. e., obtained via the Weisfeiler-Leman (WL) test) and spectral invariants.
Graph Representation Learning via Aggregation Enhancement
Graph neural networks (GNNs) have become a powerful tool for processing graph-structured data but still face challenges in effectively aggregating and propagating information between layers, which limits their performance.
End-to-End Referring Video Object Segmentation with Multimodal Transformers
Due to the complex nature of this multimodal task, which combines text reasoning, video understanding, instance segmentation and tracking, existing approaches typically rely on sophisticated pipelines in order to tackle it.
Ranked #5 on
Referring Expression Segmentation
on J-HMDB
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
In this paper, we identify a "warm-up obstacle": the inability of standard warm-up stages to train high quality feature extractors and avert memorization of noisy labels.
Ranked #1 on
Image Classification
on CIFAR-10 (with noisy labels)
Weakly Supervised Recovery of Semantic Attributes
We consider the problem of the extraction of semantic attributes, supervised only with classification labels.
Single-Node Attacks for Fooling Graph Neural Networks
Graph neural networks (GNNs) have shown broad applicability in a variety of domains.
Self-Supervised Learning for Large-Scale Unsupervised Image Clustering
Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data.
Ranked #1 on
Unsupervised Image Classification
on ObjectNet
HCM: Hardware-Aware Complexity Metric for Neural Network Architectures
Convolutional Neural Networks (CNNs) have become common in many fields including computer vision, speech recognition, and natural language processing.
Colored Noise Injection for Training Adversarially Robust Neural Networks
Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that lead to significant performance degradation.
Loss Aware Post-training Quantization
We show that with more aggressive quantization, the loss landscape becomes highly non-separable with steep curvature, making the selection of quantization parameters more challenging.
Smoothed Inference for Adversarially-Trained Models
In this work, we study the application of randomized smoothing as a way to improve performance on unperturbed data as well as to increase robustness to adversarial attacks.
CAT: Compression-Aware Training for bandwidth reduction
Our method trains the model to achieve low-entropy feature maps, which enables efficient compression at inference time using classical transform coding methods.
Feature Map Transform Coding for Energy-Efficient CNN Inference
We analyze the performance of our approach on a variety of CNN architectures and demonstrate that FPGA implementation of ResNet-18 with our approach results in a reduction of around 40% in the memory energy footprint, compared to quantized network, with negligible impact on accuracy.
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks
While mainstream deep learning methods train the neural networks weights while keeping the network architecture fixed, the emerging neural architecture search (NAS) techniques make the latter also amenable to training.
Beholder-GAN: Generation and Beautification of Facial Images with Conditioning on Their Beauty Level
Beauty is in the eye of the beholder.
Efficient non-uniform quantizer for quantized neural network targeting reconfigurable hardware
While most works use uniform quantizers for both parameters and activations, it is not always the optimal one, and a non-uniform quantizer need to be considered.
NICE: Noise Injection and Clamping Estimation for Neural Network Quantization
Convolutional Neural Networks (CNN) are very popular in many fields including computer vision, speech recognition, natural language processing, to name a few.
UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks
We present a novel method for neural network quantization that emulates a non-uniform $k$-quantile quantizer, which adapts to the distribution of the quantized parameters.
Streaming Architecture for Large-Scale Quantized Neural Networks on an FPGA-Based Dataflow Platform
Using quantized values enables the use of FPGAs to run NNs, since FPGAs are well fitted to these primitives; e. g., FPGAs provide efficient support for bitwise operations and can work with arbitrary-precision representation of numbers.
