Vision Transformers (ViTs) have revolutionized medical imaging analysis, showcasing superior efficacy compared to conventional Convolutional Neural Networks (CNNs) in vital tasks such as polyp classification, detection, and segmentation. Leveraging attention mechanisms to focus on specific image regions, ViTs exhibit contextual awareness in processing visual data, culminating in robust and precise predictions, even for intricate medical images. Moreover, the inherent self-attention mechanism in Transformers accommodates varying input sizes and resolutions, granting an unprecedented flexibility absent in traditional CNNs. However, Transformers grapple with challenges like excessive memory usage and limited training parallelism due to self-attention, rendering them impractical for real-time disease detection on resource-constrained devices. In this study, we address these hurdles by investigating the integration of the recently introduced retention mechanism into polyp segmentation, introducing RetSeg, an encoder-decoder network featuring multi-head retention blocks. Drawing inspiration from Retentive Networks (RetNet), RetSeg is designed to bridge the gap between precise polyp segmentation and resource utilization, particularly tailored for colonoscopy images. We train and validate RetSeg for polyp segmentation employing two publicly available datasets: Kvasir-SEG and CVC-ClinicDB. Additionally, we showcase RetSeg's promising performance across diverse public datasets, including CVC-ColonDB, ETIS-LaribPolypDB, CVC-300, and BKAI-IGH NeoPolyp. While our work represents an early-stage exploration, further in-depth studies are imperative to advance these promising findings.
In recent years, funding agencies and journals increasingly advocate for open science practices (e.g. data and method sharing) to improve the transparency, access, and reproducibility of science. However, quantifying these practices at scale has proven difficult. In this work, we leverage a large-scale dataset of 1.1M papers from arXiv that are representative of the fields of physics, math, and computer science to analyze the adoption of data and method link-sharing practices over time and their impact on article reception. To identify links to data and methods, we train a neural text classification model to automatically classify URL types based on contextual mentions in papers. We find evidence that the practice of link-sharing to methods and data is spreading as more papers include such URLs over time. Reproducibility efforts may also be spreading because the same links are being increasingly reused across papers (especially in computer science); and these links are increasingly concentrated within fewer web domains (e.g. Github) over time. Lastly, articles that share data and method links receive increased recognition in terms of citation count, with a stronger effect when the shared links are active (rather than defunct). Together, these findings demonstrate the increased spread and perceived value of data and method sharing practices in open science.
This paper presents a novel semi-supervised deep learning algorithm for retrieving similar 2D and 3D videos based on visual content. The proposed approach combines the power of deep convolutional and recurrent neural networks with dynamic time warping as a similarity measure. The proposed algorithm is designed to handle large video datasets and retrieve the most related videos to a given inquiry video clip based on its graphical frames and contents. We split both the candidate and the inquiry videos into a sequence of clips and convert each clip to a representation vector using an autoencoder-backed deep neural network. We then calculate a similarity measure between the sequences of embedding vectors using a bi-directional dynamic time-warping method. This approach is tested on multiple public datasets, including CC\_WEB\_VIDEO, Youtube-8m, S3DIS, and Synthia, and showed good results compared to state-of-the-art. The algorithm effectively solves video retrieval tasks and outperforms the benchmarked state-of-the-art deep learning model.
Anomaly detection in time series data, to identify points that deviate from normal behaviour, is a common problem in various domains such as manufacturing, medical imaging, and cybersecurity. Recently, Generative Adversarial Networks (GANs) are shown to be effective in detecting anomalies in time series data. The neural network architecture of GANs (i.e. Generator and Discriminator) can significantly improve anomaly detection accuracy. In this paper, we propose a new GAN model, named Adjusted-LSTM GAN (ALGAN), which adjusts the output of an LSTM network for improved anomaly detection in both univariate and multivariate time series data in an unsupervised setting. We evaluate the performance of ALGAN on 46 real-world univariate time series datasets and a large multivariate dataset that spans multiple domains. Our experiments demonstrate that ALGAN outperforms traditional, neural network-based, and other GAN-based methods for anomaly detection in time series data.
Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning, games, and control. Guaranteeing the global optimality of policy gradient methods, however, is highly nontrivial due to nonconcavity of the value functions. In this exposition, we highlight recent progresses in understanding and developing policy gradient methods with global convergence guarantees, putting an emphasis on their finite-time convergence rates with regard to salient problem parameters.
This report introduce our work on Egocentric 3D Hand Pose Estimation workshop. Using AssemblyHands, this challenge focuses on egocentric 3D hand pose estimation from a single-view image. In the competition, we adopt ViT based backbones and a simple regressor for 3D keypoints prediction, which provides strong model baselines. We noticed that Hand-objects occlusions and self-occlusions lead to performance degradation, thus proposed a non-model method to merge multi-view results in the post-process stage. Moreover, We utilized test time augmentation and model ensemble to make further improvement. We also found that public dataset and rational preprocess are beneficial. Our method achieved 12.21mm MPJPE on test dataset, achieve the first place in Egocentric 3D Hand Pose Estimation challenge.
Electromagnetic (EM) body models predict the impact of human presence and motions on the Radio-Frequency (RF) stray radiation received by wireless devices nearby. These wireless devices may be co-located members of a Wireless Local Area Network (WLAN) or even cellular devices connected with a Wide Area Network (WAN). Despite their accuracy, EM models are time-consuming methods which prevent their adoption in strict real-time computational imaging problems and Bayesian estimation, such as passive localization, RF tomography, and holography. Physics-informed Generative Neural Network (GNN) models have recently attracted a lot of attention thanks to their potential to reproduce a process by incorporating relevant physical laws and constraints. Thus, GNNs can be used to simulate/reconstruct missing samples, or learn physics-informed data distributions. The paper discusses a Variational Auto-Encoder (VAE) technique and its adaptations to incorporate a relevant EM body diffraction method with applications to passive RF sensing and localization/tracking. The proposed EM-informed generative model is verified against classical diffraction-based EM body tools and validated on real RF measurements. Applications are also introduced and discussed.
Large language models (LLMs) have played a pivotal role in revolutionizing various facets of our daily existence. Solving attention regression is a fundamental task in optimizing LLMs. In this work, we focus on giving a provable guarantee for the one-layer attention network objective function $L(X,Y) = \sum_{j_0 = 1}^n \sum_{i_0 = 1}^d ( \langle \langle \exp( \mathsf{A}_{j_0} x ) , {\bf 1}_n \rangle^{-1} \exp( \mathsf{A}_{j_0} x ), A_{3} Y_{*,i_0} \rangle - b_{j_0,i_0} )^2$. Here $\mathsf{A} \in \mathbb{R}^{n^2 \times d^2}$ is Kronecker product between $A_1 \in \mathbb{R}^{n \times d}$ and $A_2 \in \mathbb{R}^{n \times d}$. $A_3$ is a matrix in $\mathbb{R}^{n \times d}$, $\mathsf{A}_{j_0} \in \mathbb{R}^{n \times d^2}$ is the $j_0$-th block of $\mathsf{A}$. The $X, Y \in \mathbb{R}^{d \times d}$ are variables we want to learn. $B \in \mathbb{R}^{n \times d}$ and $b_{j_0,i_0} \in \mathbb{R}$ is one entry at $j_0$-th row and $i_0$-th column of $B$, $Y_{*,i_0} \in \mathbb{R}^d$ is the $i_0$-column vector of $Y$, and $x \in \mathbb{R}^{d^2}$ is the vectorization of $X$. In a multi-layer LLM network, the matrix $B \in \mathbb{R}^{n \times d}$ can be viewed as the output of a layer, and $A_1= A_2 = A_3 \in \mathbb{R}^{n \times d}$ can be viewed as the input of a layer. The matrix version of $x$ can be viewed as $QK^\top$ and $Y$ can be viewed as $V$. We provide an iterative greedy algorithm to train loss function $L(X,Y)$ up $\epsilon$ that runs in $\widetilde{O}( ({\cal T}_{\mathrm{mat}}(n,n,d) + {\cal T}_{\mathrm{mat}}(n,d,d) + d^{2\omega}) \log(1/\epsilon) )$ time. Here ${\cal T}_{\mathrm{mat}}(a,b,c)$ denotes the time of multiplying $a \times b$ matrix another $b \times c$ matrix, and $\omega\approx 2.37$ denotes the exponent of matrix multiplication.
We present a lifelong audio-video masked autoencoder that continually learns the multimodal representations from a video stream containing audio-video pairs, while its distribution continually shifts over time. Specifically, we propose two novel ideas to tackle the problem: (1) Localized Alignment: We introduce a small trainable multimodal encoder that predicts the audio and video tokens that are well-aligned with each other. This allows the model to learn only the highly correlated audiovisual patches with accurate multimodal relationships. (2) Forget-robust multimodal patch selection: We compare the relative importance of each audio-video patch between the current and past data pair to mitigate unintended drift of the previously learned audio-video representations. Our proposed method, FLAVA (Forget-robust Localized Audio-Video Alignment), therefore, captures the complex relationships between the audio and video modalities during training on a sequence of pre-training tasks while alleviating the forgetting of learned audiovisual correlations. Our experiments validate that FLAVA outperforms the state-of-the-art continual learning methods on several benchmark datasets under continual audio-video representation learning scenarios.
Recent advances in machine learning (ML) have shown promise in aiding and accelerating classical combinatorial optimization algorithms. ML-based speed ups that aim to learn in an end to end manner (i.e., directly output the solution) tend to trade off run time with solution quality. Therefore, solutions that are able to accelerate existing solvers while maintaining their performance guarantees, are of great interest. We consider an APX-hard problem, where an adversary aims to attack shortest paths in a graph by removing the minimum number of edges. We propose the GRASP algorithm: Graph Attention Accelerated Shortest Path Attack, an ML aided optimization algorithm that achieves run times up to 10x faster, while maintaining the quality of solution generated. GRASP uses a graph attention network to identify a smaller subgraph containing the combinatorial solution, thus effectively reducing the input problem size. Additionally, we demonstrate how careful representation of the input graph, including node features that correlate well with the optimization task, can highlight important structure in the optimization solution.