Related papers: Hard Mixtures of Experts for Large Scale Weakly Su…
Federated learning (FL) has emerged as the predominant approach for collaborative training of neural network models across multiple users, without the need to gather the data at a central location. One of the important challenges in this…
Developing scalable solutions for training Graph Neural Networks (GNNs) for link prediction tasks is challenging due to the high data dependencies which entail high computational cost and huge memory footprint. We propose a new method for…
Mixture-of-Experts (MoE) models achieve a favorable trade-off between performance and inference efficiency by activating only a subset of experts. However, the memory overhead of storing all experts remains a major limitation, especially in…
Deep learning models for vision tasks are trained on large datasets under the assumption that there exists a universal representation that can be used to make predictions for all samples. Whereas high complexity models are proven to be…
Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples…
Systems for training massive deep learning models (billions of parameters) today assume and require specialized "hyper-clusters": hundreds or thousands of GPUs wired with specialized high-bandwidth interconnects such as NV-Link and…
The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the…
Contrastive Language-Image Pre-training (CLIP) has attracted a surge of attention for its superior zero-shot performance and excellent transferability to downstream tasks. However, training such large-scale models usually requires…
Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is…
Medical image segmentation using deep neural networks has been highly successful. However, the effectiveness of these networks is often limited by inadequate dense prediction and inability to extract robust features. To achieve refined…
The Sparsely-Activated Mixture-of-Experts (MoE) has gained increasing popularity for scaling up large language models (LLMs) without exploding computational costs. Despite its success, the current design faces a challenge where all experts…
Modern deep learning applications urge to push the model inference taking place at the edge devices for multiple reasons such as achieving shorter latency, relieving the burden of the network connecting to the cloud, and protecting user…
Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data. We propose two methods for selecting the most relevant data with weak…
Monocular depth estimation is a challenging task in complex compositions depicting multiple objects of diverse scales. Albeit the recent great progress thanks to the deep convolutional neural networks (CNNs), the state-of-the-art monocular…
Purpose: The aim of this work is to demonstrate that convolutional neural networks (CNN) can be applied to extremely sparse image libraries by subdivision of the original image datasets. Methods: Image datasets from a conventional digital…
Network binarization is a promising hardware-aware direction for creating efficient deep models. Despite its memory and computational advantages, reducing the accuracy gap between binary models and their real-valued counterparts remains an…
Deep networks can learn to accurately recognize objects of a category by training on a large number of annotated images. However, a meta-learning challenge known as a low-shot image recognition task comes when only a few images with…
Deepfakes are synthetically generated images, videos or audios, which fraudsters use to manipulate legitimate information. Current deepfake detection systems struggle against unseen data. To address this, we employ three different deep…
Retinal image matching plays a crucial role in monitoring disease progression and treatment response. However, datasets with matched keypoints between temporally separated pairs of images are not available in abundance to train…
Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. Enforcing…