Open Access. Powered by Scholars. Published by Universities.®

Artificial Intelligence and Robotics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Computer Vision Faculty Publications

Articles 91 - 98 of 98

Full-Text Articles in Artificial Intelligence and Robotics

Deep Gaussian Processes For Few-Shot Segmentation, Joakim Johnander, Johan Edstedt, Martin Danelljan, Michael Felsberg, Fahad Shahbaz Khan Mar 2021

Deep Gaussian Processes For Few-Shot Segmentation, Joakim Johnander, Johan Edstedt, Martin Danelljan, Michael Felsberg, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A common approach is to model each class with a single prototype. While conceptually simple, these methods suffer when the target appearance distribution is multi-modal or not linearly separable in feature space. To tackle this issue, we propose a few-shot learner formulation based on Gaussian process (GP) regression. Through the expressivity of the GP, our approach is capable of modeling complex appearance distributions in the deep feature space. The GP provides a principled way …

Go to article

On Generating Transferable Targeted Perturbations, Muzammal Naseer, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Fatih Porikli Mar 2021

On Generating Transferable Targeted Perturbations, Muzammal Naseer, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Fatih Porikli

Computer Vision Faculty Publications

While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific 'targeted' class remains a challenging feat. In this paper, we propose a new generative approach for highly transferable targeted perturbations (TTP). We note that the existing methods are less suitable for this task due to their reliance on class-boundary information that changes from one model to another, thus reducing transferability. In contrast, our approach matches the perturbed image 'distribution' with that of the target class, leading to high targeted transferability rates. To this end, we propose a new objective …

Go to article

Orthogonal Projection Loss, Kanchana Ranasinghe, Muzammal Naseer, Munawar Hayat, Salman Khan, Fahad Shahbaz Khan Mar 2021

Orthogonal Projection Loss, Kanchana Ranasinghe, Muzammal Naseer, Munawar Hayat, Salman Khan, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Deep neural networks have achieved remarkable performance on a range of classification tasks, with softmax cross-entropy (CE) loss emerging as the de-facto objective function. The CE loss encourages features of a class to have a higher projection score on the true class-vector compared to the negative classes. However, this is a relative constraint and does not explicitly force different class features to be well-separated. Motivated by the observation that ground-truth class representations in CE loss are orthogonal (one-hot encoded vectors), we develop a novel loss function termed 'Orthogonal Projection Loss' (OPL) which imposes orthogonality in the feature space. OPL augments …

Go to article

Efficient Cnn Building Blocks For Encrypted Data, Nayna Jain, Karthik Nandakumar, Nalini K. Ratha, Sharath U. Pankanti, Uttam Kumar Jan 2021

Efficient Cnn Building Blocks For Encrypted Data, Nayna Jain, Karthik Nandakumar, Nalini K. Ratha, Sharath U. Pankanti, Uttam Kumar

Computer Vision Faculty Publications

Machine learning on encrypted data can address the concerns related to privacy and legality of sharing sensitive data with untrustworthy service providers, while leveraging their resources to facilitate extraction of valuable insights from otherwise non-shareable data. Fully Homomorphic Encryption (FHE) is a promising technique to enable machine learning and inferencing while providing strict guarantees against information leakage. Since deep convolutional neural networks (CNNs) have become the machine learning tool of choice in several applications, several attempts have been made to harness CNNs to extract insights from encrypted data. However, existing works focus only on ensuring data security and ignore security …

Go to article

Generative Multi-Label Zero-Shot Learning, Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Joost Van De Weijer Jan 2021

Generative Multi-Label Zero-Shot Learning, Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Joost Van De Weijer

Computer Vision Faculty Publications

Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of …

Go to article

Low Light Image Enhancement Via Global And Local Context Modeling, Aditya Arora, Muhammad Haris, Syed Waqas Zamir, Munawar Hayat, Fahad Shahbaz Khan, Ling Shao, Ming-Hsuan Yang Jan 2021

Low Light Image Enhancement Via Global And Local Context Modeling, Aditya Arora, Muhammad Haris, Syed Waqas Zamir, Munawar Hayat, Fahad Shahbaz Khan, Ling Shao, Ming-Hsuan Yang

Computer Vision Faculty Publications

Images captured under low-light conditions manifest poor visibility, lack contrast and color vividness. Compared to conventional approaches, deep convolutional neural networks (CNNs) perform well in enhancing images. However, being solely reliant on confined fixed primitives to model dependencies, existing data-driven deep models do not exploit the contexts at various spatial scales to address low-light image enhancement. These contexts can be crucial towards inferring several image enhancement tasks, e.g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent. To this end, we introduce a context-aware deep network for low-light image enhancement. First, …

Go to article

Trainable Structure Tensors For Autonomous Baggage Threat Detection Under Extreme Occlusion, Taimur Hassan, Samet Akçay, Mohammed Bennamoun, Salman Khan, Naoufel Werghi Sep 2020

Trainable Structure Tensors For Autonomous Baggage Threat Detection Under Extreme Occlusion, Taimur Hassan, Samet Akçay, Mohammed Bennamoun, Salman Khan, Naoufel Werghi

Computer Vision Faculty Publications

Detecting baggage threats is one of the most difficult tasks, even for expert officers. Many researchers have developed computer-aided screening systems to recognize these threats from the baggage X-ray scans. However, all of these frameworks are limited in identifying the contraband items under extreme occlusion. This paper presents a novel instance segmentation framework that utilizes trainable structure tensors to highlight the contours of the occluded and cluttered contraband items (by scanning multiple predominant orientations), while simultaneously suppressing the irrelevant baggage content. The proposed framework has been extensively tested on four publicly available X-ray datasets where it outperforms the state-of-the-art frameworks …

Go to article

Any-Shot Object Detection, Shafin Rahman, Salman Khan, Nick Barnes, Fahad Shahbaz Khan Mar 2020

Any-Shot Object Detection, Shafin Rahman, Salman Khan, Nick Barnes, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Previous work on novel object detection considers zero or few-shot settings where none or few examples of each category are available for training. In real world scenarios, it is less practical to expect that ‘all’ the novel classes are either unseen or have few-examples. Here, we propose a more realistic setting termed ‘Any-shot detection’, where totally unseen and few-shot categories can simultaneously co-occur during inference. Any-shot detection offers unique challenges compared to conventional novel object detection such as, a high imbalance between unseen, few-shot and seen object classes, susceptibility to forget base-training while learning novel classes and distinguishing novel classes …

Go to article

First Prev