Related papers: Fighting Fire with Fire: Avoiding DNN Shortcuts th…
The use of pretrained deep neural networks represents an attractive way to achieve strong results with few data available. When specialized in dense problems such as object detection, learning local rather than global information in images…
Deep neural networks have demonstrated high accuracy in image classification tasks. However, they were shown to be weak against adversarial examples: a small perturbation in the image which changes the classification output dramatically. In…
Discriminative localization is essential for fine-grained image classification task, which devotes to recognizing hundreds of subcategories in the same basic-level category. Reflecting on discriminative regions of objects, key differences…
Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…
The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…
Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…
Recently, deep learning-based models have exhibited remarkable performance for image manipulation detection. However, most of them suffer from poor universality of handcrafted or predetermined features. Meanwhile, they only focus on…
Discriminative features play an important role in image and object classification and also in other fields of research such as semi-supervised learning, fine-grained classification, out of distribution detection. Inspired by Linear…
There is an ongoing effort to develop feature selection algorithms to improve interpretability, reduce computational resources, and minimize overfitting in predictive models. Neural networks stand out as architectures on which to build…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using a deep neural network as its function approximator and by learning directly from raw images. A drawback of using raw images is that…
Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…
Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit…
Convolutional neural networks (CNNs) are used in many embedded applications, from industrial robotics and automation systems to biometric identification on mobile devices. State-of-the-art classification is typically achieved by large…
Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images…
A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive capacity is trained. Pruning is an established approach to…
Action recognition has become a rapidly developing research field within the last decade. But with the increasing demand for large scale data, the need of hand annotated data for the training becomes more and more impractical. One way to…
As deep learning gains popularity, edge IoT devices have seen proliferating deployment of pre-trained Deep Neural Network (DNN) models. These DNNs represent valuable intellectual property and face significant confidentiality threats from…
Pretraining is a common technique in deep learning for increasing performance and reducing training time, with promising experimental results in deep reinforcement learning (RL). However, pretraining requires a relevant dataset for…
Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples. Despite their appeal, these…
The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of…