Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot attention, which utilizes attention mechanisms to iteratively refine slot representations. However, a major drawback of most object-centric models, including slot attention, is their reliance on predefining the number of slots. This not only necessitates prior knowledge of the dataset but also overlooks the inherent variability in the number of objects present in each instance. To overcome this fundamental limitation, we present a novel complexity-aware object auto-encoder framework. Within this framework, we introduce an adaptive slot attention (AdaSlot) mechanism that dynamically determines the optimal number of slots based on the content of the data. This is achieved by proposing a discrete slot sampling module that is responsible for selecting an appropriate number of slots from a candidate list. Furthermore, we introduce a masked slot decoder that suppresses unselected slots during the decoding process. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models. Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention research. Project will be available at https://kfan21.github.io/AdaSlot/
Future Slot Prediction for Unsupervised Object Discovery in Surgical Video
PCASO Laboratory, Department of Surgery, University of Pennsylvania（匹兹堡大学外科实验室、外科系、匹兹堡大学）；Department of Computer and Information Science, University of Pennsylvania（计算机与信息科学系、匹兹堡大学）
Slot-BERT: Self-supervised Object Discovery in Surgical Video
Outcomes Laboratory, Department of Surgery, University of Pennsylvania, Philadelphia, PA, USA.；Department of Computer；Information Science, University of Pennsylvania, Philadelphia, PA, USA.；Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada.；Surgical Artificial Intelligence Research Academy, University Health Network, Toronto, ON, Canada.
Contrastive Training of Complex-Valued Autoencoders for Object Discovery
The Swiss AI Lab, IDSIA, USI & SUPSI（瑞士AI实验室，IDSIA，USI与SUPSI）；Center for Brain Science, Harvard University（哈佛大学脑科学中心）；AI Initiative, KAUST（阿卜杜拉国王科技大学AI计划）
Component Adaptive Clustering for Generalized Category Discovery
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）
ETH Zurich（苏黎世联邦理工学院）；Max-Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Google Research（谷歌研究院）
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bi…
FORLA: Federated Object-centric Representation Learning with Slot Attention
PCASO Laboratory, Dept. of Surgery, University of Pennsylvania（宾夕法尼亚大学外科部PCASO实验室）；Dept. of Computer and Information Science, University of Pennsylvania（宾夕法尼亚大学计算机与信息科学系）
University of Amsterdam（阿姆斯特丹大学）；Bosch Center for AI（博世人工智能中心）
Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works on unsupervised object discovery focus on slot-based approaches, which explicitly separate the latent representations of individual objects. While the result is easily interpretable, it usually requires the design of involved architectures. In contrast to this, we propose a comparatively simple approach - the Complex AutoEncoder (CAE) - that creates distributed object-centric representations. Following a coding scheme…
Slot Attention with Re-Initialization and Self-Distillation
Department of Electrical Engineering and Automation（电气工程与自动化系）；Aalto University（阿尔托大学）；Department of Computer Science（计算机科学系）；Center for Machine Vision and Signal Analysis（机器视觉与信号分析中心）；University of Oulu（奥卢大学）
本文提出 DIAS 方法，通过槽重初始化和自蒸馏减少冗余槽，提升对象为中心学习的对象发现与识别性能。
Predicting Video Slot Attention Queries from Random Slot-Feature Pairs
Department of Electrical Engineering and Automation, Aalto University（艾罗大学电气工程与自动化系）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学研究生院人工智能学院）；Department of Computer Science, Aalto University（艾罗大学计算机科学系）；Center for Machine Vision and Signal Analysis, University of Oulu（奥卢大学机器视觉与信号分析中心）
Smoothing Slot Attention Iterations and Recurrences
Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland（电气工程与自动化系，阿alto大学，埃斯波，芬兰）；Department of Computer Science, Aalto University, Espoo, Finland（计算机科学系，阿alto大学，埃斯波，芬兰）；Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland（机器视觉与信号分析中心，奥卢大学，奥卢，芬兰）
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；University of Amsterdam（阿姆斯特丹大学）；University of Tübingen（蒂宾根大学）；Archimedes/Athena RC（阿基米德/雅典娜研究中心）
CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection
School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）；Department of Electrical & Computer Engineering, National University of Singapore（电气与计算机工程系，新加坡国立大学）；School of Information and Electronics, Beijing Institute of Technology（信息与电子学院，北京理工大学）
Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks, none of which may be effective for the specific defense at hand. Our key observation is that adaptive attacks are composed of reusable building blocks that can be formalized in a search space and used to automatically discover attacks for unknown defenses. We evaluated our approach on 24 adversarial defenses and show that it outperforms AutoAttack, the current state-of-the-art…
Sun Yat-Sen University（中山大学）；Guangdong University of Technology（广东工业大学）
As a promising solution of reducing annotation cost, training multi-label models with partial positive labels (MLR-PPL), in which merely few positive labels are known while other are missing, attracts increasing attention. Due to the absence of any negative labels, previous works regard unknown labels as negative and adopt traditional MLR algorithms. To reject noisy labels, recent works regard large loss samples as noise but ignore the semantic correlation different multi-label images. In this work, we propose to explore semantic correlation among different images to facilitate the MLR-PPL tas…
East China Normal University（华东师范大学）；Shanghai Advanced Research Institute, CAS（中国科学院上海高等研究院）；Videt Tech.（Videt科技公司）
Crowd counting, i.e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications. A key component for the crowd counting systems is the construction of counting models which are robust to various scenarios under facts such as camera perspective and physical barriers. In this paper, we present an adaptive scenario discovery framework for crowd counting. The system is structured with two parallel pathways that are trained with different sizes of the receptive field to represent different scales and crowd densities. Afte…
Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization
Department of Electrical Engineering and Automation, Aalto University, Finland（艾尔沃斯大学电气工程与自动化系）；Department of Computer Science, Aalto University, Finland（艾尔沃斯大学计算机科学系）；Center for Machine Vision and Signal Analysis, University of Oulu, Finland（奥卢大学机器视觉与信号分析中心）
Tongji University（同济大学）；Hong Kong Polytechnic University（香港理工大学）
Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the quality of the training-set, yet complicated aerial scenarios like occlusion or out of view can reduce its reliability. In this work, a novel time slot-based distillation approach is proposed to efficiently and effectively optimize the training-set's quality on the fly. A cooperative energy minimization function is established to score the historical samples adaptively. To accelerate the scoring process, frames with…
As deep learning approaches to scene recognition emerge, they have continued to leverage discriminative regions at multiple scales, building on practices established by conventional image classification research. However, approaches remain largely generic, and do not carefully consider the special properties of scenes. In this paper, inspired by the intuitive differences between scenes and objects, we propose Adi-Red, an adaptive approach to discriminative region discovery for scene recognition. Adi-Red uses a CNN classifier, which was pre-trained using only image-level scene labels, to discov…
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…
We present Language-mediated, Object-centric Representation Learning (LORL), a paradigm for learning disentangled, object-centric scene representations from vision and language. LORL builds upon recent advances in unsupervised object discovery and segmentation, notably MONet and Slot Attention. While these algorithms learn an object-centric representation just by reconstructing the input image, LORL enables them to further learn to associate the learned representations to concepts, i.e., words for object categories, properties, and spatial relationships, from language input. These object-centr…
Alibaba Group（阿里巴巴集团）；Central South University（中南大学）
Face clustering has attracted rising research interest recently to take advantage of massive amounts of face images on the web. State-of-the-art performance has been achieved by Graph Convolutional Networks (GCN) due to their powerful representation capacity. However, existing GCN-based methods build face graphs mainly according to kNN relations in the feature space, which may lead to a lot of noise edges connecting two faces of different classes. The face features will be polluted when messages pass along these noise edges, thus degrading the performance of GCNs. In this paper, a novel algori…
