Related papers: Self Identity Mapping
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into $L$ simplices of $V$ dimensions each using a softmax operation. This procedure conditions the…
In today's heavily overparameterized models, the value of the training loss provides few guarantees on model generalization ability. Indeed, optimizing only the training loss value, as is commonly done, can easily lead to suboptimal model…
Representing visual signals by implicit representation (e.g., a coordinate based deep network) has prevailed among many vision tasks. This work explores a new intriguing direction: training a stylized implicit representation, using a…
In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…
Structured illumination microscopy (SIM) is an important super-resolution based microscopy technique that breaks the diffraction limit and enhances optical microscopy systems. With the development of biology and medical engineering, there…
We introduce a general framework for analyzing learning algorithms based on the notion of self-regularization, which captures implicit complexity control without requiring explicit regularization. This is motivated by previous observations…
Image harmonization is a crucial technique in image composition that aims to seamlessly match the background by adjusting the foreground of composite images. Current methods adopt either global-level or pixel-level feature matching.…
Implicit Neural Representations (INRs) provide a powerful continuous framework for modeling complex visual and geometric signals, but spectral bias remains a fundamental challenge, limiting their ability to capture high-frequency details.…
Sharpness-Aware Minimization (SAM) is a recent optimization framework aiming to improve the deep neural network generalization, through obtaining flatter (i.e. less sharp) solutions. As SAM has been numerically successful, recent papers…
In this paper, we investigate the empirical impact of orthogonality regularization (OR) in deep learning, either solo or collaboratively. Recent works on OR showed some promising results on the accuracy. In our ablation study, however, we…
Simultaneous localization and mapping (SLAM) is the process of constructing a global model of an environment from local observations of it; this is a foundational capability for mobile robots, supporting such core functions as planning,…
Traditional AI-planning methods for task planning in robotics require a symbolically encoded domain description. While powerful in well-defined scenarios, as well as human-interpretable, setting this up requires substantial effort.…
Regularization is a powerful technique for extracting useful information from noisy data. Typically, it is implemented by adding some sort of norm constraint to an objective function and then exactly optimizing the modified objective…
We propose SING (StabIlized and Normalized Gradient), a plug-and-play technique that improves the stability and generalization of the Adam(W) optimizer. SING is straightforward to implement and has minimal computational overhead, requiring…
Structured illumination microscopy (SIM) is a pivotal technique for dynamic subcellular imaging in live cells. Conventional SIM reconstruction algorithms depend on accurately estimating the illumination pattern and can introduce artefacts…
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms. In…
This paper addresses the problem of matching pedestrians across multiple camera views, known as person re-identification. Variations in lighting conditions, environment and pose changes across camera views make re-identification a…
Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the…
Overfitting is one of the most critical challenges in deep neural networks, and there are various types of regularization methods to improve generalization performance. Injecting noises to hidden units during training, e.g., dropout, is…
Simultaneous Localization and Mapping (SLAM) algorithms perform visual-inertial estimation via filtering or batch optimization methods. Empirical evidence suggests that filtering algorithms are computationally faster, while optimization…