Recently, representation learning with contrastive learning algorithms has been successfully applied to challenging unlabeled datasets. However, these methods are unable to distinguish important features from unimportant ones under simply unsupervised settings, and definitions of importance vary according to the type of downstream task or analysis goal, such as the identification of objects or backgrounds. In this paper, we focus on unsupervised image clustering as the downstream task and propose a representation learning method that enhances features critical to the clustering task. We extend a clustering-friendly contrastive learning method and incorporate a contrastive analysis approach, which utilizes a reference dataset to separate important features from unimportant ones, into the design of loss functions. Conducting an experimental evaluation of image clustering for three datasets with characteristic backgrounds, we show that for all datasets, our method achieves higher clustering scores compared with conventional contrastive analysis and deep clustering methods.
Segmenting salient objects in an image is an important vision task with ubiquitous applications. The problem becomes more challenging in the presence of a cluttered and textured background, low resolution and/or low contrast images. Even though existing algorithms perform well in segmenting most of the object(s) of interest, they often end up segmenting false positives due to resembling salient objects in the background. In this work, we tackle this problem by iteratively attending to image patches in a recurrent fashion and subsequently enhancing the predicted segmentation mask. Saliency feat…
In this paper, our goal is salient building outline enhancement and extraction from images taken from consumer cameras using L0 smoothing. We address weak outlines and over-smoothing problem. Weak outlines are often undetected by edge extractors or easily smoothed out. We propose an iterative method, including the smoothing cell and sharpening cell. In the smoothing cell, we iteratively enlarge the smoothing level of the L0 smoothing. In the sharpening cell, we use Hough Transform to extract lines, based on the assumption that salient outlines for buildings are usually straight, and enhance th…
STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detection
School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；Yunnan Key Laboratory of Service Computing, Yunnan University of Finance and Economics（云南财经大学服务计算重点实验室）；Innovation Academy for Microsatellites of Chinese Academy of Science（中国科学院微卫星创新院）；Institute for Urban Governance, Shanghai University（上海大学城市治理研究院）
National Institute of Technology Warangal（瓦朗加尔国家理工学院）；Institute for Development and Research in Banking Technology（银行技术发展与研究院）
Video Salient Document Detection (VSDD) is an essential task of practical computer vision, which aims to highlight visually salient document regions in video frames. Previous techniques for VSDD focus on learning features without considering the cooperation among and across the appearance and motion cues and thus fail to perform in practical scenarios. Moreover, most of the previous techniques demand high computational resources, which limits the usage of such systems in resource-constrained settings. To handle these issues, we propose VS-Net, which captures multi-scale spatiotemporal informat…
Nankai University（南开大学）；ETH Zurich（苏黎世联邦理工学院）；University of Electronic Science and Technology of China（电子科技大学）
Recent progress on salient object detection (SOD) mainly benefits from multi-scale learning, where the high-level and low-level features collaborate in locating salient objects and discovering fine details, respectively. However, most efforts are devoted to low-level feature learning by fusing multi-scale features or enhancing boundary representations. High-level features, which although have long proven effective for many other tasks, yet have been barely studied for SOD. In this paper, we tap into this gap and show that enhancing high- level features is essential for SOD as well. To this end…
The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However, two critical problems need to be solved for two-modality SOD. One problem is two-modality fusion. The other problem is the HRFormer output's fusion. To address the first problem, a supplementary modality is injected into the primary modality by using global optimization and an attention mechanism to select and purify the modality at the input level. To solv…
Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
Beijing Jiaotong University（北京交通大学）；University of Birmingham（英国伯明翰大学）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS部）；Microsoft, UK（微软公司（英国））
Beijing Jiaotong University（北京交通大学）；National University of Singapore（新加坡国立大学）
To detect salient objects accurately, existing methods usually design complex backbone network architectures to learn and fuse powerful features. However, the saliency inference module that performs saliency prediction from the fused features receives much less attention on its architecture design and typically adopts only a few fully convolutional layers. In this paper, we find the limited capacity of the saliency inference module indeed makes a fundamental performance bottleneck, and enhancing its capacity is critical for obtaining better saliency prediction. Correspondingly, we propose a de…
Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Images
School of Computer Science and Technology, Hainan University（海南大学计算机科学与技术学院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）
Nankai University（南开大学）；IIAI（IIAI（阿联酋创新人工智能研究院））；Northwestern Polytechnical University（西北工业大学）；The University of Hong Kong（香港大学）；Terminus Group（特斯联集团）
Although current salient object detection (SOD) works have achieved significant progress, they are limited when it comes to the integrity of the predicted salient regions. We define the concept of integrity at both a micro and macro level. Specifically, at the micro level, the model should highlight all parts that belong to a certain salient object. Meanwhile, at the macro level, the model needs to discover all salient objects in a given image. To facilitate integrity learning for SOD, we design a novel Integrity Cognition Network (ICON), which explores three important components for learning …
Soochow University（苏州大学）；Hefei University of Technology（合肥工业大学）；University of Georgia（佐治亚大学）；University of Science and Technology of China（中国科学技术大学）
We propose a novel and unsupervised representation learning model, i.e., Robust Block-Diagonal Adaptive Locality-constrained Latent Representation (rBDLR). rBDLR is able to recover multi-subspace structures and extract the adaptive locality-preserving salient features jointly. Leveraging on the Frobenius-norm based latent low-rank representation model, rBDLR jointly learns the coding coefficients and salient features, and improves the results by enhancing the robustness to outliers and errors in given data, preserving local information of salient features adaptively and ensuring the block-diag…
Boundary-semantic collaborative guidance network with dual-stream feedback mechanism for salient object detection in optical remote sensing imagery
State-Province Joint Engineering Laboratory of Spatial Information Technology of High-Speed Rail Safety, Southwest Jiaotong University（西南交通大学高速铁路安全空间信息技术省部共建工程实验室）
DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
Biometric recognition systems have advanced significantly in the last decade and their use in specific applications will increase in the near future. The ability to conduct meaningful comparisons and assessments will be crucial to successful deployment and increasing biometric adoption. The best modality used as unimodal biometric systems are unable to fully address the problem of higher recognition rate. Multimodal biometric systems are able to mitigate some of the limitations encountered in unimodal biometric systems, such as non-universality, distinctiveness, non-acceptability, noisy sensor…
LGCA: Enhancing Semantic Representation via Progressive Expansion
University of Science, Vietnam National University Ho Chi Minh City, Vietnam（越南胡志明市国家大学科学大学）；National University of Singapore, Singapore（新加坡国立大学）；AISIA Lab, Ho Chi Minh City, Vietnam（越南胡志明市AISIA实验室）
