Related papers: Saliency Suppressed, Semantics Surfaced: Visual Tr…

Subjective image quality measures based on deep neural networks are very related to models of visual neuroscience. This connection benefits engineering but, more interestingly, the freedom to optimize deep networks in different ways, make…

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

The high cost of pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source usually does not contain enough information to train a well-performing model. To…

While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual neurons. We present a technique called as Linguistic…

Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connections between the two tasks, which is not the most efficient…

Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing studies visually analyze the mechanisms of convolutional…

The availability of large amounts of data and compelling computation power have made deep learning models much popular for text classification and sentiment analysis. Deep neural networks have achieved competitive performance on the above…

Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain. By focusing on the benefits of joint auditory and visual information, most VSP methods are capable of…

The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks. This prospect, however, has…

Biological visual systems learn from limited experience, unlike deep learning models that rely on millions of training images. What learning principles make this possible? We tested whether efficient coding, the idea that neural…

Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the input data, the…

Deep learning techniques have proven highly effective in image classification, but their deployment in resourceconstrained environments remains challenging due to high computational demands. Furthermore, their interpretability is of high…

Shortcut learning is common but harmful to deep learning models, leading to degenerated feature representations and consequently jeopardizing the model's generalizability and interpretability. However, shortcut learning in the widely used…

With their increase in performance, neural network architectures also become more complex, necessitating explainability. Therefore, many new and improved methods are currently emerging, which often generate so-called saliency maps in order…

We introduce SaltiNet, a deep neural network for scanpath prediction trained on 360-degree images. The model is based on a temporal-aware novel representation of saliency information named the saliency volume. The first part of the network…

Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions. Saliency map is a common form of explanation illustrating the heatmap of feature attributions, but it suffers from noise in…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…

Deep learning has revolutionized many computer vision fields in the last few years, including learning-based image compression. In this paper, we propose a deep semantic segmentation-based layered image compression (DSSLIC) framework in…

In recent years, the demand of image compression models for machine vision has increased dramatically. However, the training frameworks of image compression still focus on the vision of human, maintaining the excessive perceptual details,…