Related papers: Task Specific Visual Saliency Prediction with Memo…

Recently, a unified model for image-to-image translation tasks within adversarial learning framework has aroused widespread research interests in computer vision practitioners. Their reported empirical success however lacks solid…

The in-context learning capabilities of modern language models have motivated a deeper mathematical understanding of sequence models. A line of recent work has shown that linear attention models can emulate projected gradient descent…

Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency,…

Most existing saliency models use low-level features or task descriptions when generating attention predictions. However, the link between observer characteristics and gaze patterns is rarely investigated. We present a novel saliency…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Vision transformer networks have shown superiority in many computer vision tasks. In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for…

Feature maps in deep neural network generally contain different semantics. Existing methods often omit their characteristics that may lead to sub-optimal results. In this paper, we propose a novel end-to-end deep saliency network which…

Automatically generating the descriptions of an image, i.e., image captioning, is an important and fundamental topic in artificial intelligence, which bridges the gap between computer vision and natural language processing. Based on the…

Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve robustness. Extending purely data-driven generative models, recent specialized models satisfy additional…

Being able to generate constrained samples is one of the most appealing applications of the deep generators. Conditional generators are one of the successful implementations of such models wherein the created samples are constrained to a…

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning…

This work addresses the problems of semantic segmentation and image super-resolution by jointly considering the performance of both in training a Generative Adversarial Network (GAN). We propose a novel architecture and domain-specific…

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…

Image completion has achieved significant progress due to advances in generative adversarial networks (GANs). Albeit natural-looking, the synthesized contents still lack details, especially for scenes with complex structures or images with…

Recently, generative adversarial networks (GAN) have gathered a lot of interest. Their efficiency in generating unseen samples of high quality, especially images, has improved over the years. In the field of Natural Language Generation…

Conditioning image generation on specific features of the desired output is a key ingredient of modern generative models. However, existing approaches lack a general and unified way of representing structural and semantic conditioning at…

Action prediction aims to infer the forthcoming human action with partially-observed videos, which is a challenging task due to the limited information underlying early observations. Existing methods mainly adopt a reconstruction strategy…

Deep neural networks have shown their profound impact on achieving human level performance in visual saliency prediction. However, it is still unclear how they learn the task and what it means in terms of understanding human visual system.…

In this paper, we address the task of semantic-guided scene generation. One open challenge in scene generation is the difficulty of the generation of small objects and detailed local texture, which has been widely observed in global…

Many machine learning methods have been recently developed to circumvent the high computational cost of the gradient-based topology optimization. These methods typically require extensive and costly datasets for training, have a difficult…