Related papers: Learning Distortion Invariant Representation for I…

Accurate prediction of local distortion visibility thresholds is critical in many image and video processing applications. Existing methods require an accurate modeling of the human visual system, and are derived through pshycophysical…

This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of…

In recent years, discriminative self-supervised methods have made significant strides in advancing various visual tasks. The central idea of learning a data encoder that is robust to data distortions/augmentations is straightforward yet…

Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training. Due to different semantic distributions between synthetic and real-world captured datasets, there exists semantic mismatch between…

Out-of-distribution generalization is a common problem that expects the model to perform well in the different distributions even far from the train data. A popular approach to addressing this issue is invariant learning (IL), in which the…

Deep reinforcement learning (DRL) requires the collection of interventional data, which is sometimes expensive and even unethical in the real world, such as in the autonomous driving and the medical field. Offline reinforcement learning…

Domain incremental learning (DIL) has been discussed in previous studies on deep neural network models for classification. In DIL, we assume that samples on new domains are observed over time. The models must classify inputs on all domains.…

We introduce Consistent Assignment for Representation Learning (CARL), an unsupervised learning method to learn visual representations by combining ideas from self-supervised contrastive learning and deep clustering. By viewing contrastive…

Replicating In-Context Learning (ICL) in computer vision remains challenging due to task heterogeneity. We propose \textbf{VIRAL}, a framework that elicits visual reasoning from a pre-trained image editing model by formulating ICL as…

Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…

Non-uniform blind deblurring for general dynamic scenes is a challenging computer vision problem as blurs arise not only from multiple object motions but also from camera shake, scene depth variation. To remove these complicated motion…

With the widespread applications of deep convolutional neural networks (DCNNs), it becomes increasingly important for DCNNs not only to make accurate predictions but also to explain how they make their decisions. In this work, we propose a…

Medical imaging is nowadays a pillar in diagnostics and therapeutic follow-up. Current research tries to integrate established - but ionizing - tomographic techniques with technologies offering reduced radiation exposure. Diffuse Optical…

Deep learning has shown great promise for CT image reconstruction, in particular to enable low dose imaging and integrated diagnostics. These merits, however, stand at great odds with the low availability of diverse image data which are…

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance…

Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain…

We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely on complex…

In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one…

Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials.…

In recent years, deep learning methods have been extensively developed for inverse imaging problems (IIPs), encompassing supervised, self-supervised, and generative approaches. Most of these methods require large amounts of labeled or…