37 citations · 106 across the 17 of their papers we have counts for
17 papers
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
Lin Li, Haoyan Guan, Jianing Qiu +1
Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the ad…
The Importance of Anti-Aliasing in Tiny Object Detection
Jinlai Ning, Michael Spratling
Tiny object detection has gained considerable attention in the research community owing to the frequent occurrence of tiny objects in numerous critical real-world scenarios. Howeve…
OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift
Lin Li, Yifei Wang, Chawin Sitawarin +1
Existing works have made great progress in improving adversarial robustness, but typically test their method only on data from the same distribution as the training data, i.e. in-d…
A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifiers
Michael W. Spratling
Reliable and robust evaluation methods are a necessary first step towards developing machine learning models that are themselves robust and reliable. Unfortunately, current evaluat…
When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review
Maxime Fontana, Michael Spratling, Miaojing Shi
Multi-Task Learning (MTL) aims to learn multiple tasks simultaneously while exploiting their mutual relationships. By using shared resources to simultaneously calculate multiple ou…
AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentation
Lin Li, Jianing Qiu, Michael Spratling
Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting whi…
Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing
Lin Li, Michael Spratling
Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So f…
Rethinking the backbone architecture for tiny object detection
Jinlai Ning, Haoyan Guan, Michael Spratling
Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios. However, existing tiny object det…
Data Augmentation Alone Can Improve Adversarial Training
Lin Li, Michael Spratling
Adversarial training suffers from the issue of robust overfitting, which seriously impairs its generalization performance. Data augmentation, which is effective at preventing overf…
Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization
Lin Li, Michael Spratling
Adversarial training is widely used to improve the robustness of deep neural networks to adversarial attack. However, adversarial training is prone to overfitting, and the cause is…
CobNet: Cross Attention on Object and Background for Few-Shot Segmentation
Haoyan Guan, Michael Spratling
Few-shot segmentation aims to segment images containing objects from previously unseen classes using only a few annotated samples. Most current methods focus on using object inform…
On the biological plausibility of orthogonal initialisation for solving gradient instability in deep neural networks
Nikolay Manchev, Michael Spratling
Initialising the synaptic weights of artificial neural networks (ANNs) with orthogonal matrices is known to alleviate vanishing and exploding gradient problems. A major objection a…
Query Semantic Reconstruction for Background in Few-Shot Segmentation
Haoyan Guan, Michael Spratling
Few-shot segmentation (FSS) aims to segment unseen classes using a few annotated samples. Typically, a prototype representing the foreground class is extracted from annotated suppo…
Registration based Few-Shot Anomaly Detection
Chaoqin Huang, Haoyan Guan, Aofan Jiang +3
This paper considers few-shot anomaly detection (FSAD), a practical yet under-studied setting for anomaly detection (AD), where only a limited number of normal images are provided…
Robust Template Matching via Hierarchical Convolutional Features from a Shape Biased CNN
Bo Gao, M. W. Spratling
Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a deep feature-space, produce…
Explaining Away Results in Accurate and Tolerant Template Matching
M. W. Spratling
Recognising and locating image patches or sets of image features is an important task underlying much work in computer vision. Traditionally this has been accomplished using templa…
A three-dimensional approach to Visual Speech Recognition using Discrete Cosine Transforms
Toni Heidenreich, Michael W. Spratling
Visual speech recognition aims to identify the sequence of phonemes from continuous speech. Unlike the traditional approach of using 2D image feature extraction methods to derive f…