Search Results for author:
Found 13 papers, 8 papers with code
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
This work studies the adversarial robustness of VLMs from the novel perspective of the text prompt instead of the extensively studied model weights (frozen in this work).
The Importance of Anti-Aliasing in Tiny Object Detection
Additionally, we also propose a bottom-heavy version of the backbone, which further improves the performance of tiny object detection while also reducing the required number of parameters by almost half.
OODRobustBench: benchmarking and analyzing adversarial robustness under distribution shift
Based on this, we are able to predict the upper limit of OOD robustness for existing robust training schemes.
When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review
Second, it presents the different challenges arising from such a multi-objective optimisation scheme.
AROID: Improving Adversarial Robustness through Online Instance-wise Data Augmentation
This allows our method to efficiently explore a large search space for a more effective DA policy and evolve the policy as training progresses.
Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing
We find that during training an overall reduction of adversarial loss is achieved by sacrificing a considerable proportion of training samples to be more vulnerable to adversarial attack, which results in an uneven distribution of adversarial vulnerability among data.
Rethinking the backbone architecture for tiny object detection
Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios.
Data Augmentation Alone Can Improve Adversarial Training
Data augmentation, which is effective at preventing overfitting in standard training, has been observed by many previous works to be ineffective in mitigating overfitting in adversarial training.
Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization
Adversarial training is widely used to improve the robustness of deep neural networks to adversarial attack.
On the biological plausibility of orthogonal initialisation for solving gradient instability in deep neural networks
Initialising the synaptic weights of artificial neural networks (ANNs) with orthogonal matrices is known to alleviate vanishing and exploding gradient problems.
CobNet: Cross Attention on Object and Background for Few-Shot Segmentation
To overcome this issue, we propose CobNet which utilises information about the background that is extracted from the query images without annotations of those images.
Query Semantic Reconstruction for Background in Few-Shot Segmentation
To successfully associate prototypes with class labels and extract a background prototype that is capable of predicting a mask for the background regions of the image, the machinery for extracting and using foreground prototypes is induced to become more discriminative between different classes.
Registration based Few-Shot Anomaly Detection
Inspired by how humans detect anomalies, i. e., comparing an image in question to normal images, we here leverage registration, an image alignment task that is inherently generalizable across categories, as the proxy task, to train a category-agnostic anomaly detection model.
Ranked #72 on
Anomaly Detection
on MVTec AD
