Image background features can constitute background bias (spurious correlations) and impact deep classifiers decisions, causing shortcut learning (Clever Hans effect) and reducing the generalization skill on real-world data. The concept of optimizing Layer-wise Relevance Propagation (LRP) heatmaps, to improve classifier behavior, was recently introduced by a neural network architecture named ISNet. It minimizes background relevance in LRP maps, to mitigate the influence of image background features on deep classifiers decisions, hindering shortcut learning and improving generalization. For each training image, the original ISNet produces one heatmap per possible class in the classification task, hence, its training time scales linearly with the number of classes. Here, we introduce reformulated architectures that allow the training time to become independent from this number, rendering the optimization process much faster. We challenged the enhanced models utilizing the MNIST dataset with synthetic background bias, and COVID-19 detection in chest X-rays, an application that is prone to shortcut learning due to background bias. The trained models minimized background attention and hindered shortcut learning, while retaining high accuracy. Considering external (out-of-distribution) test datasets, they consistently proved more accurate than multiple state-of-the-art deep neural network architectures, including a dedicated image semantic segmenter followed by a classifier. The architectures presented here represent a potentially massive improvement in training speed over the original ISNet, thus introducing LRP optimization into a gamut of applications that could not be feasibly handled by the original model.
Urban villages, defined as informal residential areas in or around urban centers, are characterized by inadequate infrastructures and poor living conditions, closely related to the Sustainable Development Goals (SDGs) on poverty, adequate housing, and sustainable cities. Traditionally, governments heavily depend on field survey methods to monitor the urban villages, which however are time-consuming, labor-intensive, and possibly delayed. Thanks to widely available and timely updated satellite images, recent studies develop computer vision techniques to detect urban villages efficiently. However, existing studies either focus on simple urban village image classification or fail to provide accurate boundary information. To accurately identify urban village boundaries from satellite images, we harness the power of the vision foundation model and adapt the Segment Anything Model (SAM) to urban village segmentation, named UV-SAM. Specifically, UV-SAM first leverages a small-sized semantic segmentation model to produce mixed prompts for urban villages, including mask, bounding box, and image representations, which are then fed into SAM for fine-grained boundary identification. Extensive experimental results on two datasets in China demonstrate that UV-SAM outperforms existing baselines, and identification results over multiple years show that both the number and area of urban villages are decreasing over time, providing deeper insights into the development trends of urban villages and sheds light on the vision foundation models for sustainable cities. The dataset and codes of this study are available at https://github.com/tsinghua-fib-lab/UV-SAM.
Wearable devices like smart glasses are approaching the compute capability to seamlessly generate real-time closed captions for live conversations. We build on our recently introduced directional Automatic Speech Recognition (ASR) for smart glasses that have microphone arrays, which fuses multi-channel ASR with serialized output training, for wearer/conversation-partner disambiguation as well as suppression of cross-talk speech from non-target directions and noise. When ASR work is part of a broader system-development process, one may be faced with changes to microphone geometries as system development progresses. This paper aims to make multi-channel ASR insensitive to limited variations of microphone-array geometry. We show that a model trained on multiple similar geometries is largely agnostic and generalizes well to new geometries, as long as they are not too different. Furthermore, training the model this way improves accuracy for seen geometries by 15 to 28\% relative. Lastly, we refine the beamforming by a novel Non-Linearly Constrained Minimum Variance criterion.
In this paper, we formulate the multi-agent graph bandit problem as a multi-agent extension of the graph bandit problem introduced by Zhang, Johansson, and Li [CISS 57, 1-6 (2023)]. In our formulation, $N$ cooperative agents travel on a connected graph $G$ with $K$ nodes. Upon arrival at each node, agents observe a random reward drawn from a node-dependent probability distribution. The reward of the system is modeled as a weighted sum of the rewards the agents observe, where the weights capture the decreasing marginal reward associated with multiple agents sampling the same node at the same time. We propose an Upper Confidence Bound (UCB)-based learning algorithm, Multi-G-UCB, and prove that its expected regret over $T$ steps is bounded by $O(N\log(T)[\sqrt{KT} + DK])$, where $D$ is the diameter of graph $G$. Lastly, we numerically test our algorithm by comparing it to alternative methods.
Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial energy consumption and computational resources. Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources. In this paper, we explore this attack surface about availability of VLMs and aim to induce high energy-latency cost during inference of VLMs. We find that high energy-latency cost during inference of VLMs can be manipulated by maximizing the length of generated sequences. To this end, we propose verbose images, with the goal of crafting an imperceptible perturbation to induce VLMs to generate long sentences during inference. Concretely, we design three loss objectives. First, a loss is proposed to delay the occurrence of end-of-sequence (EOS) token, where EOS token is a signal for VLMs to stop generating further tokens. Moreover, an uncertainty loss and a token diversity loss are proposed to increase the uncertainty over each generated token and the diversity among all tokens of the whole generated sequence, respectively, which can break output dependency at token-level and sequence-level. Furthermore, a temporal weight adjustment algorithm is proposed, which can effectively balance these losses. Extensive experiments demonstrate that our verbose images can increase the length of generated sequences by 7.87 times and 8.56 times compared to original images on MS-COCO and ImageNet datasets, which presents potential challenges for various applications. Our code is available at https://github.com/KuofengGao/Verbose_Images.
Background: Wide-field calcium imaging (WFCI) with genetically encoded calcium indicators allows for spatiotemporal recordings of neuronal activity in mice. When applied to the study of sleep, WFCI data are manually scored into the sleep states of wakefulness, non-REM (NREM) and REM by use of adjunct EEG and EMG recordings. However, this process is time-consuming, invasive and often suffers from low inter- and intra-rater reliability. Therefore, an automated sleep state classification method that operates on spatiotemporal WFCI data is desired. New Method: A hybrid network architecture consisting of a convolutional neural network (CNN) to extract spatial features of image frames and a bidirectional long short-term memory network (BiLSTM) with attention mechanism to identify temporal dependencies among different time points was proposed to classify WFCI data into states of wakefulness, NREM and REM sleep. Results: Sleep states were classified with an accuracy of 84% and Cohen's kappa of 0.64. Gradient-weighted class activation maps revealed that the frontal region of the cortex carries more importance when classifying WFCI data into NREM sleep while posterior area contributes most to the identification of wakefulness. The attention scores indicated that the proposed network focuses on short- and long-range temporal dependency in a state-specific manner. Comparison with Existing Method: On a 3-hour WFCI recording, the CNN-BiLSTM achieved a kappa of 0.67, comparable to a kappa of 0.65 corresponding to the human EEG/EMG-based scoring. Conclusions: The CNN-BiLSTM effectively classifies sleep states from spatiotemporal WFCI data and will enable broader application of WFCI in sleep.
Human beings possess the capability to multiply a melange of multisensory cues while actively exploring and interacting with the 3D world. Current multi-modal large language models, however, passively absorb sensory data as inputs, lacking the capacity to actively interact with the objects in the 3D environment and dynamically collect their multisensory information. To usher in the study of this area, we propose MultiPLY, a multisensory embodied large language model that could incorporate multisensory interactive data, including visual, audio, tactile, and thermal information into large language models, thereby establishing the correlation among words, actions, and percepts. To this end, we first collect Multisensory Universe, a large-scale multisensory interaction dataset comprising 500k data by deploying an LLM-powered embodied agent to engage with the 3D environment. To perform instruction tuning with pre-trained LLM on such generated data, we first encode the 3D scene as abstracted object-centric representations and then introduce action tokens denoting that the embodied agent takes certain actions within the environment, as well as state tokens that represent the multisensory state observations of the agent at each time step. In the inference time, MultiPLY could generate action tokens, instructing the agent to take the action in the environment and obtain the next multisensory state observation. The observation is then appended back to the LLM via state tokens to generate subsequent text or action tokens. We demonstrate that MultiPLY outperforms baselines by a large margin through a diverse set of embodied tasks involving object retrieval, tool use, multisensory captioning, and task decomposition.
We study the problem of deciding whether a given language is directed. A language $L$ is \emph{directed} if every pair of words in $L$ have a common (scattered) superword in $L$. Deciding directedness is a fundamental problem in connection with ideal decompositions of downward closed sets. Another motivation is that deciding whether two \emph{directed} context-free languages have the same downward closures can be decided in polynomial time, whereas for general context-free languages, this problem is known to be coNEXP-complete. We show that the directedness problem for regular languages, given as NFAs, belongs to $AC^1$, and thus polynomial time. Moreover, it is NL-complete for fixed alphabet sizes. Furthermore, we show that for context-free languages, the directedness problem is PSPACE-complete.
In this paper, we consider an unmanned aerial vehicle (UAV)-enabled emergency communication system, which establishes temporary communication link with users equipment (UEs) in a typical disaster environment with mountainous forest and obstacles. Towards this end, a joint deployment, power allocation, and user association optimization problem is formulated to maximize the total transmission rate, while considering the demand of each UE and the disaster environment characteristics. Then, an alternating optimization algorithm is proposed by integrating coalition game and virtual force approach which captures the impact of the demand priority of UEs and the obstacles to the flight path and consumed power. Simulation results demonstrate that the computation time consumed by our proposed algorithm is only $5.6\%$ of the traditional heuristic algorithms, which validates its effectiveness in disaster scenarios.
Transformer models have demonstrated high accuracy in numerous applications but have high complexity and lack sequential processing capability making them ill-suited for many streaming applications at the edge where devices are heavily resource-constrained. Thus motivated, many researchers have proposed reformulating the transformer models as RNN modules which modify the self-attention computation with explicit states. However, these approaches often incur significant performance degradation. The ultimate goal is to develop a model that has the following properties: parallel training, streaming and low-cost inference, and SOTA performance. In this paper, we propose a new direction to achieve this goal. We show how architectural modifications to a recurrent model can help push its performance toward Transformer models while retaining its sequential processing capability. Specifically, inspired by the recent success of Legendre Memory Units (LMU) in sequence learning tasks, we propose LMUFormer, which augments the LMU with convolutional patch embedding and convolutional channel mixer. Moreover, we present a spiking version of this architecture, which introduces the benefit of states within the patch embedding and channel mixer modules while simultaneously reducing the computing complexity. We evaluated our architectures on multiple sequence datasets. In comparison to SOTA transformer-based models within the ANN domain on the SCv2 dataset, our LMUFormer demonstrates comparable performance while necessitating a remarkable 53 times reduction in parameters and a substantial 65 times decrement in FLOPs. Additionally, owing to our model's proficiency in real-time data processing, we can achieve a 32.03% reduction in sequence length, all while incurring an inconsequential decline in performance. Our code is publicly available at https://github.com/zeyuliu1037/LMUFormer.git.