论文检索

Xin Zhang, Yu Liu, Yuming Lin, Qingmin Liao, Yong Li

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.

Bo Lin, Shoshanna Saxe, Timothy C. Y. Chan

Cycling stress assessment, which quantifies cyclists' perceived stress imposed by the built environment and motor traffics, increasingly informs cycling infrastructure planning and cycling route recommendation. However, currently calculating cycling stress is slow and data-intensive, which hinders its broader application. In this paper, We propose a deep learning framework to support accurate, fast, and large-scale cycling stress assessments for urban road networks based on street-view images. Our framework features i) a contrastive learning approach that leverages the ordinal relationship among cycling stress labels, and ii) a post-processing technique that enforces spatial smoothness into our predictions. On a dataset of 39,153 road segments collected in Toronto, Canada, our results demonstrate the effectiveness of our deep learning framework and the value of using image data for cycling stress assessment in the absence of high-quality road geometry and motor traffic data.

Yansheng Li, Bo Dang, Wanchun Li, Yongjun Zhang

Global surface water detection in very-high-resolution (VHR) satellite imagery can directly serve major applications such as refined flood mapping and water resource assessment. Although achievements have been made in detecting surface water in small-size satellite images corresponding to local geographic scales, datasets and methods suitable for mapping and analyzing global surface water have yet to be explored. To encourage the development of this task and facilitate the implementation of relevant applications, we propose the GLH-water dataset that consists of 250 satellite images and 40.96 billion pixels labeled surface water annotations that are distributed globally and contain water bodies exhibiting a wide variety of types (e.g. , rivers, lakes, and ponds in forests, irrigated fields, bare areas, and urban areas). Each image is of the size 12,800 × 12,800 pixels at 0.3 meter spatial resolution. To build a benchmark for GLH-water, we perform extensive experiments employing representative surface water detection models, popular semantic segmentation models, and ultra-high resolution segmentation models. Furthermore, we also design a strong baseline with the novel pyramid consistency loss (PCL) to initially explore this challenge, increasing IoU by 2.4% over the next best baseline. Finally, we implement the cross-dataset generalization and pilot area application experiments, and the superior performance illustrates the strong generalization and practical application value of GLH-water dataset. Project page: https://jack-bo1220.github.io/project/GLH-water.html

Erhu He, Yiqun Xie, Alexander Sun, Jacob Zwart, Jie Yang, Zhenong Jin, Yang Wang, Hassan Karimi, Xiaowei Jia

Accurate prediction of water quality and quantity is crucial for sustainable development and human well-being. However, existing data-driven methods often suffer from spatial biases in model performance due to heterogeneous data, limited observations, and noisy sensor data. To overcome these challenges, we propose Fair-Graph, a novel graph-based recurrent neural network that leverages interrelated knowledge from multiple rivers to predict water flow and temperature within large-scale stream networks. Additionally, we introduce node-specific graph masks for information aggregation and adaptation to enhance prediction over heterogeneous river segments. To reduce performance disparities across river segments, we introduce a centralized coordination strategy that adjusts training priorities for segments. We evaluate the prediction of water temperature within the Delaware River Basin, and the prediction of streamflow using simulated data from U.S. National Water Model in the Houston River network. The results showcase improvements in predictive performance and highlight the proposed model's ability to maintain spatial fairness over different river segments.

Xuan Gong, Shanglin Li, Yuxiang Bao, Barry Yao, Yawen Huang, Ziyan Wu, Baochang Zhang, Yefeng Zheng, David Doermann

Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data. Existing FL methods either iteratively share local model parameters or deploy co-distillation. However, the former is highly susceptible to private data leakage, and the latter design relies on the prerequisites of task-relevant real data. Instead, we propose a data-free FL framework based on local-to-central collaborative distillation with direct input and output space exploitation. Our design eliminates any requirement of recursive local parameter exchange or auxiliary task-relevant data to transfer knowledge, thereby giving direct privacy control to local users. In particular, to cope with the inherent data heterogeneity across locals, our technique learns to distill input on which each local model produces consensual yet unique results to represent each expertise. Our proposed FL framework achieves notable privacy-utility trade-offs with extensive experiments on image classification and segmentation tasks under various real-world heterogeneous federated learning settings on both natural and medical images. Code is available at https://github.com/lsl001006/FedIOD.

Kshitiz ., Sonu Shreshtha, Bikash Dutta, Muskan Dosi, Mayank Vatsa, Richa Singh, Saket Anand, Sudeep Sarkar, Sevaram Mali Parihar

Automatic recognition of bird behavior from long-term, un controlled outdoor imagery can contribute to conservation efforts by enabling large-scale monitoring of bird populations. Current techniques in AI-based wildlife monitoring have focused on short-term tracking and monitoring birds individually rather than in species-rich flocks. We present Bird-Collect, a comprehensive benchmark dataset for monitoring dense bird flock attributes. It includes a unique collection of more than 6,000 high-resolution images of Demoiselle Cranes (Anthropoides virgo) feeding and nesting in the vicinity of Khichan region of Rajasthan. Particularly, each image contains an average of 190 individual birds, illustrating the complex dynamics of densely populated bird flocks on a scale that has not previously been studied. In addition, a total of 433 distinct pictures captured at Keoladeo National Park, Bharatpur provide a comprehensive representation of 34 distinct bird species belonging to various taxonomic groups. These images offer details into the diversity and the behaviour of birds in vital natural ecosystem along the migratory flyways. Additionally, we provide a set of 2,500 point-annotated samples which serve as ground truth for benchmarking various computer vision tasks like crowd counting, density estimation, segmentation, and species classification. The benchmark performance for these tasks highlight the need for tailored approaches for specific wildlife applications, which include varied conditions including views, illumination, and resolutions. With around 46.2 GBs in size encompassing data collected from two distinct nesting ground sets, it is the largest birds dataset containing detailed annotations, showcasing a substantial leap in bird research possibilities. We intend to publicly release the dataset to the research community. The database is available at: https://iab-rubric.org/resources/wildlife-dataset/birdcollect

Yuanpeng Tu, Yuxi Li, Boshen Zhang, Liang Liu, Jiangning Zhang, Yabiao Wang, Cairong Zhao

Robust autonomous driving requires agents to accurately identify unexpected areas (anomalies) in urban scenes. To this end, some critical issues remain open: how to design advisable metric to measure anomalies, and how to properly generate training samples of anomaly data? Classical effort in anomaly detection usually resorts to pixel-wise uncertainty or sample synthesis, which ignores the contextual information and sometimes requires auxiliary data with fine-grained annotations. On the contrary, in this paper, we exploit the strong context-dependent nature of segmentation task and design an energy-guided self-supervised frameworks for anomaly segmentation, which optimizes an anomaly head by maximizing likelihood of self-generated anomaly pixels. For this purpose, we design two estimators to model anomaly likelihood, one is a task-agnostic binary estimator and the other depicts the likelihood as residual of task-oriented joint energy. Based on proposed estimators, we devise an adaptive self-supervised training framework, which exploits the contextual reliance and estimated likelihood to refine mask annotations in anomaly areas. We conduct extensive experiments on challenging Fishyscapes and Road Anomaly benchmarks, demonstrating that without any auxiliary data or synthetic models, our method can still achieves comparable performance to supervised competitors. Code is available at https://github.com/yuanpengtu/SLEEG.

Minsu Kim, Seong-Hyeon Hwang, Steven Euijong Whang

Continuous machine learning pipelines are common in industrial settings where models are periodically trained on data streams. Unfortunately, concept drifts may occur in data streams where the joint distribution of the data X and label y, P(X, y), changes over time and possibly degrade model accuracy. Existing concept drift adaptation approaches mostly focus on updating the model to the new data possibly using ensemble techniques of previous models and tend to discard the drifted historical data. However, we contend that explicitly utilizing the drifted data together leads to much better model accuracy and propose Quilt, a data-centric framework for identifying and selecting data segments that maximize model accuracy. To address the potential downside of efficiency, Quilt extends existing data subset selection techniques, which can be used to reduce the training data without compromising model accuracy. These techniques cannot be used as is because they only assume virtual drifts where the posterior probabilities P(y|X) are assumed not to change. In contrast, a key challenge in our setup is to also discard undesirable data segments with concept drifts. Quilt thus discards drifted data segments and selects data segment subsets holistically for accurate and efficient model training. The two operations use gradient-based scores, which have little computation overhead. In our experiments, we show that Quilt outperforms state-of-the-art drift adaptation and data selection baselines on synthetic and real datasets.

Yu Zhang, Yunyi Zhang, Yanzhen Shen, Yu Deng, Lucian Popa, Larisa Shwartz, ChengXiang Zhai, Jiawei Han

Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such data in highly specialized science and engineering domains (e.g., software engineering and security) can be time-consuming and costly, without mentioning the domain gaps between training and inference data if the model needs to be applied to confidential datasets. In this paper, we study the task of seed-guided fine-grained entity typing in science and engineering domains, which takes the name and a few seed entities for each entity type as the only supervision and aims to classify new entity mentions into both seen and unseen types (i.e., those without seed entities). To solve this problem, we propose SEType which first enriches the weak supervision by finding more entities for each seen type from an unlabeled corpus using the contextualized representations of pre-trained language models. It then matches the enriched entities to unlabeled text to get pseudo-labeled samples and trains a textual entailment model that can make inferences for both seen and unseen types. Extensive experiments on two datasets covering four domains demonstrate the effectiveness of SEType in comparison with various baselines. Code and data are available at: https://github.com/yuzhimanhua/SEType.

Jinshan Zeng, Xianchao Tong, Xianglong Yu, Wenyan Xiao, Qing Huang

The hybrid automatic readability assessment (ARA) models that combine deep and linguistic features have recently received rising attention due to their impressive performance. However, the utilization of linguistic features is not fully realized, as ARA models frequently concentrate excessively on numerical values of these features, neglecting valuable structural information embedded within them. This leads to limited contribution of linguistic features in these hybrid ARA models, and in some cases, it may even result in counterproductive outcomes. In this paper, we propose a novel hybrid ARA model named InterpretARA through introducing a linguistic interpreter to better comprehend the structural information contained in linguistic features, and leveraging the contrastive learning that enables the model to understand relative difficulty relationships among texts and thus enhances deep representations. Both document-level and segment-level deep representations are extracted and used for the readability assessment. A series of experiments are conducted over four English corpora and one Chinese corpus to demonstrate the effectiveness of the proposed model. Experimental results show that InterpretARA outperforms state-of-the-art models in most corpora, and the introduced linguistic interpreter can provide more useful information than existing ways for ARA.

Jin Huang, Danfeng Yan, Yuanqiang Cai

The prompt-based method has been proven effective in improving the performance of pre-trained language models (PLMs) on sentence-level few-shot tasks. However, when applying prompting to token-level tasks such as Named Entity Recognition (NER), specific templates need to be designed, and all possible segments of the input text need to be enumerated. These methods have high computational complexity in both training and inference processes, making them difficult to apply in real-world scenarios. To address these issues, we redefine the NER task as a Machine Reading Comprehension (MRC) task and incorporate prompting into the MRC framework. Specifically, we sequentially insert boundary markers for various entity types into the templates and use these markers as anchors during the inference process to differentiate entity types. In contrast to the traditional multi-turn question-answering extraction in the MRC framework, our method can extract all spans of entity types in one round. Furthermore, we propose word-based template and example-based template that enhance the MRC framework's perception of entity start and end positions while significantly reducing the manual effort required for template design. It is worth noting that in cross-domain scenarios, PMRC does not require redesigning the model architecture and can continue training by simply replacing the templates to recognize entity types in the target domain. Experimental results demonstrate that our approach outperforms state-of-the-art models in low-resource settings, achieving an average performance improvement of +5.2% in settings where access to source domain data is limited. Particularly, on the ATIS dataset with a large number of entity types and 10-shot setting, PMRC achieves a performance improvement of +15.7%. Moreover, our method achieves a decoding speed 40.56 times faster than the template-based cloze-style approach.

Xinjie Chen, Kai Fan, Wei Luo, Linlin Zhang, Libo Zhao, Xinggao Liu, Zhongqiang Huang

To achieve high-quality translation with low latency, a Simultaneous Speech Translation (SimulST) system relies on a policy module to decide whether to translate immediately or wait for additional streaming input, along with a translation model capable of effectively handling partial speech input. Prior research has tackled these components separately, either using ``wait-k'' policies based on fixed-length segments or detected word boundaries, or dynamic policies based on different strategies (e.g., meaningful units), while employing offline models for prefix-to-prefix translation. In this paper, we propose Divergence-Guided Simultaneous Speech Translation (DiG-SST), a tightly integrated approach focusing on both translation quality and latency for streaming input. Specifically, we introduce a simple yet effective prefix-based strategy for training translation models with partial speech input, and develop an adaptive policy that makes read/write decisions for the translation model based on the expected divergence in translation distributions resulting from future input. Our experiments on multiple translation directions of the MuST-C benchmark demonstrate that our approach achieves a better trade-off between translation quality and latency compared to existing methods.

Aydar Bulatov, Yuri Kuratov, Yermek Kapushev, Mikhail Burtsev

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer models to extend input context length while linearly scaling compute. Our approach demonstrates the capability to store information in memory for sequences of up to an unprecedented two million tokens while maintaining high retrieval accuracy. Experiments with language modeling tasks show perplexity improvement as the number of processed input segments increases. These results underscore the effectiveness of our method, which has significant potential to enhance long-term dependency handling in natural language understanding and generation tasks, as well as enable large-scale context processing for memory-intensive applications.

Zhaoyang Zhang, Wenqi Shao, Yixiao Ge, Xiaogang Wang, Jinwei Gu, Ping Luo

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classification, object detection, and instance segmentation. Furthermore, our approach surpasses previous memory-based techniques in tasks such as language modeling and displays the ability to be applied to a broader range of situations.

Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du 等

The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE architecture with parallel Feed Forward Network (FFN) experts leads to significant parameter and computational overheads that hinder its efficient deployment. In addition, the naive MoE linear router is suboptimal in assigning task-specific features to multiple experts which limits its further scalability. In this work, we propose an efficient MoE architecture with weight sharing across the experts. Inspired by the idea of linear feature modulation (FM), our architecture implicitly instantiates multiple experts via learnable activation modulations on a single shared expert block. The proposed Feature Modulated Expert (FME) serves as a building block for the novel Mixture-of-Feature-Modulation-Experts (MoFME) architecture, which can scale up the number of experts with low overhead. We further propose an Uncertainty-aware Router (UaR) to assign task-specific features to different FM modules with well-calibrated weights. This enables MoFME to effectively learn diverse expert functions for multiple tasks. The conducted experiments on the multi-deweather task show that our MoFME outperforms the state-of-the-art in the image restoration quality by 0.1-0.2 dB while saving more than 74% of parameters and 20% inference time over the conventional MoE counterpart. Experiments on the downstream segmentation and classification tasks further demonstrate the generalizability of MoFME to real open-world applications.

Dongmei Zhang, Chang Li, Renrui Zhang, Shenghao Xie, Wei Xue, Xiaodong Xie, Shanghang Zhang

The superior performances of pre-trained foundation models in various visual tasks underscore their potential to enhance the 2D models' open-vocabulary ability. Existing methods explore analogous applications in the 3D space. However, most of them only center around knowledge extraction from singular foundation models, which limits the open-vocabulary ability of 3D models. We hypothesize that leveraging complementary pre-trained knowledge from various foundation models can improve knowledge transfer from 2D pre-trained visual language models to the 3D space. In this work, we propose FM-OV3D, a method of Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection, which improves the open-vocabulary localization and recognition abilities of 3D model by blending knowledge from multiple pre-trained foundation models, achieving true open-vocabulary without facing constraints from original 3D datasets. Specifically, to learn the open-vocabulary 3D localization ability, we adopt the open-vocabulary localization knowledge of the Grounded-Segment-Anything model. For open-vocabulary 3D recognition ability, We leverage the knowledge of generative foundation models, including GPT-3 and Stable Diffusion models, and cross-modal discriminative models like CLIP. The experimental results on two popular benchmarks for open-vocabulary 3D object detection show that our model efficiently learns knowledge from multiple foundation models to enhance the open-vocabulary ability of the 3D model and successfully achieves state-of-the-art performance in open-vocabulary 3D object detection tasks. Code is released at https://github.com/dmzhang0425/FM-OV3D.git.

Zhidong Yu, Wei Yang, Xike Xie, Zhenbo Shi

Continual Semantic Segmentation (CSS) is an emerging trend, where catastrophic forgetting has been a perplexing problem. In this paper, we propose a Text-to-Image Knowledge Preservation (TIKP) framework to address this issue. TIKP applies Text-to-Image techniques to CSS by automatically generating prompts and content adaptation. It extracts associations between the labels of seen data and constructs text-level prompts based on these associations, which are preserved and maintained at each incremental step. During training, these prompts generate correlated images to mitigate the catastrophic forgetting. Particularly, as the generated images may have different distributions from the original data, TIKP transfers the knowledge by a content adaption loss, which determines the role played by the generated images in incremental training based on the similarity. In addition, for the classifier, we use the previous model from a different perspective: misclassifying new classes into old objects instead of the background. We propose a knowledge distillation loss based on wrong labels, enabling us to attribute varying weights to individual objects during the distillation process. Extensive experiments conducted in the same setting show that TIKP outperforms state-of-the-art methods by a large margin on benchmark datasets.

Senqiao Yang, Jiarui Wu, Jiaming Liu, Xiaoqi Li, Qizhe Zhang, Mingjie Pan, Yulu Gan, Zehui Chen, Shanghang Zhang

The visual prompts have provided an efficient manner in addressing visual cross-domain problems. Previous works introduce domain prompts to tackle the classification Test-Time Adaptation (TTA) problem by placing image-level prompts on the input and fine-tuning prompts for each target domain. However, since the image-level prompts mask out continuous spatial details in the prompt-allocated region, it will suffer from inaccurate contextual information and limited domain knowledge extraction, particularly when dealing with dense prediction TTA problems. To overcome these challenges, we propose a novel Sparse Visual Domain Prompts (SVDP) approach, which applies minimal trainable parameters (e.g., 0.1%) to pixels across the entire image and reserves more spatial information of the input. To better apply SVDP in extracting domain-specific knowledge, we introduce the Domain Prompt Placement (DPP) method to adaptively allocates trainable parameters of SVDP on the pixels with large distribution shifts. Furthermore, recognizing that each target domain sample exhibits a unique domain shift, we design Domain Prompt Updating (DPU) strategy to optimize prompt parameters differently for each sample, facilitating efficient adaptation to the target domain. Extensive experiments were conducted on widely-used TTA and continual TTA benchmarks, and our proposed method achieves state-of-the-art performance in both semantic segmentation and depth estimation tasks.

Fan Xu, Yu Zhao, Bingzhe Wu, Yueshan Huang, Qin Ren, Yang Xiao, Bing He, Jie Zheng, Jianhua Yao

One individual human’s immune repertoire consists of a huge set of adaptive immune receptors at a certain time point, representing the individual's adaptive immune state. Immune repertoire classification and associated receptor identification have the potential to make a transformative contribution to the development of novel vaccines and therapies. The vast number of instances and exceedingly low witness rate pose a great challenge to the immune repertoire classification, which can be formulated as a Massive Multiple Instance Learning (MMIL) problem. Traditional MIL methods, at both bag-level and instance-level, confront the issues of substantial computational burden or supervision ambiguity when handling massive instances. To address these issues, we propose a novel label disambiguation-based multimodal massive multiple instance learning approach (LaDM³IL) for immune repertoire classification. LaDM³IL adapts the instance-level MIL paradigm to deal with the issue of high computational cost and employs a specially-designed label disambiguation module for label correction, mitigating the impact of misleading supervision. To achieve a more comprehensive representation of each receptor, LaDM³IL leverages a multimodal fusion module with gating-based attention and tensor-fusion to integrate the information from gene segments and amino acid (AA) sequences of each immune receptor. Extensive experiments on the Cytomegalovirus (CMV) and Cancer datasets demonstrate the superior performance of the proposed LaDM³IL for both immune repertoire classification and associated receptor identification tasks. The code is publicly available at https://github.com/Josie-xufan/LaDM3IL.

Nannan Wu, Zhaobin Sun, Zengqiang Yan, Li Yu

Federated learning (FL) has emerged as a promising paradigm for training segmentation models on decentralized medical data, owing to its privacy-preserving property. However, existing research overlooks the prevalent annotation noise encountered in real-world medical datasets, which limits the performance ceilings of FL. In this paper, we, for the first time, identify and tackle this problem. For problem formulation, we propose a contour evolution for modeling non-independent and identically distributed (Non-IID) noise across pixels within each client and then extend it to the case of multi-source data to form a heterogeneous noise model (i.e., Non-IID annotation noise across clients). For robust learning from annotations with such two-level Non-IID noise, we emphasize the importance of data quality in model aggregation, allowing high-quality clients to have a greater impact on FL. To achieve this, we propose Federated learning with Annotation quAlity-aware AggregatIon, named FedA3I, by introducing a quality factor based on client-wise noise estimation. Specifically, noise estimation at each client is accomplished through the Gaussian mixture model and then incorporated into model aggregation in a layer-wise manner to up-weight high-quality clients. Extensive experiments on two real-world medical image segmentation datasets demonstrate the superior performance of FedA3I against the state-of-the-art approaches in dealing with cross-client annotation noise. The code is available at https://github.com/wnn2000/FedAAAI.