Search Results for author:
Found 19 papers, 10 papers with code
Neural Architecture Search in a Proxy Validation Loss Landscape
This paper searches for the optimal neural architecture by minimizing a proxy of validation loss.
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
To alleviate this issue, we redesign the diffusion framework from generating high-quality images to predicting distinguishable image labels.
VSSD: Vision Mamba with Non-Causal State Space Duality
Recently, State Space Duality (SSD), an improved variant of SSMs, was introduced in Mamba2 to enhance model performance and efficiency.
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
To improve the performance of SSMs in vision tasks, a multi-scan strategy is widely adopted, which leads to significant redundancy of SSMs.
Random Entangled Tokens for Adversarially Robust Vision Transformer
Recognizing the challenge posed by the structural disparities between ViTs and CNNs we introduce a novel module input-independent random entangled self-attention (II-ReSA).
Imitation Learning from Purified Demonstrations
In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise.
Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks
Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations.
Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization
Moreover, to ameliorate the phenomenon of sub-optimization with one fixed style, we propose to discover the optimal style given a target through style optimization in a continuous relaxation manner.
A Benchmark Study on Calibration
As far as we are aware, our research represents the first large-scale investigation into calibration properties and the premier study of calibration issues within NAS.
Neural Architecture Retrieval
With the increasing number of new neural architecture designs and substantial existing neural architectures, it becomes difficult for the researchers to situate their contributions compared with existing neural architectures or establish the connections between their designs and other relevant ones.
Dual Focal Loss for Calibration
While different variants of focal loss have been explored, it is difficult to find a balance between over-confidence and under-confidence.
Calibrating a Deep Neural Network with Its Predecessors
However, early stopping, as a well-known technique to mitigate overfitting, fails to calibrate networks.
Adversarial Robustness via Random Projection Filters
Deep Neural Networks show superior performance in various tasks but are vulnerable to adversarial attacks.
Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations
In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space.
Spatial-Channel Token Distillation for Vision MLPs
Recently, neural architectures with all Multi-layer Perceptrons (MLPs) have attracted great research interest from the computer vision community.
Ranked #500 on
Image Classification
on ImageNet
An Empirical Study of Adder Neural Networks for Object Detection
Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications.
Towards Stable and Robust AdderNets
Adder neural network (AdderNet) replaces the original convolutions with massive multiplications by cheap additions while achieving comparable performance thus yields a series of energy-efficient neural networks.
Handling Long-tailed Feature Distribution in AdderNets
Adder neural networks (ANNs) are designed for low energy cost which replace expensive multiplications in convolutional neural networks (CNNs) with cheaper additions to yield energy-efficient neural networks and hardware accelerations.
Adversarially Robust Neural Architectures
We explore the relationship among adversarial robustness, Lipschitz constant, and architecture parameters and show that an appropriate constraint on architecture parameters could reduce the Lipschitz constant to further improve the robustness.
