Related papers: Preconditioned Sharpness-Aware Minimization: Unify…

In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of…

Federated learning (FL) enables collaborative model training with privacy preservation. Data heterogeneity across edge devices (clients) can cause models to converge to sharp minima, negatively impacting generalization and robustness.…

Sparse modeling for signal processing and machine learning has been at the focus of scientific research for over two decades. Among others, supervised sparsity-aware learning comprises two major paths paved by: a) discriminative methods and…

Sparsifying neural networks often suffers from seemingly inevitable performance degradation, and it remains challenging to restore the original performance despite much recent progress. Motivated by recent studies in robust optimization, we…

Medical Image Foundation Models have proven to be powerful tools for mask prediction across various datasets. However, accurately assessing the uncertainty of their predictions remains a significant challenge. To address this, we propose a…

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…

Dataset condensation aims to synthesize datasets with a few representative samples that can effectively represent the original datasets. This enables efficient training and produces models with performance close to those trained on the…

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…

Deep neural networks (DNNs) have demonstrated promising results in various complex tasks. However, current DNNs encounter challenges with over-parameterization, especially when there is limited training data available. To enhance the…

Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, exploiting the differences in sensitivity to quantization…

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact…

We analyze the landscape and training dynamics of diagonal linear networks in a linear regression task, with the network parameters being perturbed by small isotropic normal noise. The addition of such noise may be interpreted as a…

Few-shot segmentation has garnered significant attention. Many recent approaches attempt to introduce the Segment Anything Model (SAM) to handle this task. With the strong generalization ability and rich object-specific extraction ability…

Transformer-based language models significantly advanced the state-of-the-art in many linguistic tasks. As this revolution continues, the ability to explain model predictions has become a major area of interest for the NLP community. In…

Remarkable gains in deep learning usually rely on tremendous supervised data. Ensuring the modality diversity for one object in training set is critical for the generalization of cutting-edge deep models, but it burdens human with heavy…

The growing use of information hiding in network streaming media for covert communication poses a significant security threat, necessitating the development of robust detection technologies. However, existing steganalysis methods for…

The Segment Anything Model (SAM), a foundation model pretrained on millions of images and segmentation masks, has significantly advanced semantic segmentation, a fundamental task in computer vision. Despite its strengths, SAM encounters two…

Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to security and privacy…

Object-level Simultaneous Localization and Mapping (SLAM), which incorporates semantic information for high-level scene understanding, faces challenges of under-constrained optimization due to sparse observations. Prior work has introduced…

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…