Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer from grasping the contextuality between attribute and object, as well as the discriminability of visual features, and the long-tailed distribution of real-world compositional data. We propose a simple and scalable framework called Composition Transformer (CoT) to address these issues. CoT employs object and attribute experts in distinctive manners to generate representative embeddings, using the visual network hierarchically. The object expert extracts representative object embeddings from the final layer in a bottom-up manner, while the attribute expert makes attribute embeddings in a top-down manner with a proposed object-guided attention module that models contextuality explicitly. To remedy biased prediction caused by imbalanced data distribution, we develop a simple minority attribute augmentation (MAA) that synthesizes virtual samples by mixing two images and oversampling minority attribute classes. Our method achieves SoTA performance on several benchmarks, including MIT-States, C-GQA, and VAW-CZSL. We also demonstrate the effectiveness of CoT in improving visual discrimination and addressing the model bias from the imbalanced data distribution. The code is available at https://github.com/HanjaeKim98/CoT.
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning
The Hong Kong Polytechnic University（香港理工大学）；The Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）；The Hong Kong University of Science and Technology（香港科技大学）；Huazhong University of Science and Technology（华中科技大学）
Jiangnan University（江南大学）；University of New South Wales（新南威尔士大学）；Australian Artificial Intelligence Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能研究所）；Zhejiang University（浙江大学）
The task of Compositional Zero-Shot Learning (CZSL) is to recognize images of novel state-object compositions that are absent during the training stage. Previous methods of learning compositional embedding have shown effectiveness in closed-world CZSL. However, in Open-World CZSL (OW-CZSL), their performance tends to degrade significantly due to the large cardinality of possible compositions. Some recent works separately predict simple primitives (i.e., states and objects) to reduce cardinality. However, they consider simple primitives as independent probability distributions, ignoring the hea…
EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家级重点实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究所）；Xi’an Jiaotong University（西安交通大学）
Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning
School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education)（交通运输大数据与人工智能教育部重点实验室）
University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images, given only a subset of them during training and no prior on the unseen compositions. In this setting, models operate on a huge output space, containing all possible state-object compositions. While previous works tackle the problem by learning embeddings for the compositions jointly, here we revisit a simple CZSL baseline and predict the primitives, i.e. states and objects, independently. To ensure that the model develops primitive-specific features, we equip the state…
Zero-shot Compositional Action Recognition with Neural Logic Constraints
College of Computer Science and Technology（计算机科学与技术学院）；Zhejiang University（浙江大学）；AI Chip Center for Emerging Smart Systems（新兴智能系统人工智能芯片中心）；The Hong Kong University of Science and Technology（香港科学与技术大学）
From Model Patterns to Abstract Semantics in Compositional Zero-Shot Learning
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Key Laboratory of Network System and Network Culture（网络系统与网络文化北京市重点实验室）；Key Laboratory of Interactive Technology and Experience System（交互技术与体验系统重点实验室）
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；School of Computer Science, Peking University（北京大学计算机学院）
Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Engineering, Newcastle University（纽卡斯尔大学工程学院）；Department of Computer Science, Durham University（杜伦大学计算机科学系）；Harbin Institute of Technology（哈尔滨工业大学）；School of Artificial Intelligence, Nanjing University of Science and Technology（南京理工大学人工智能学院）
Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning
PowerChina Huadong Engineering Corporation Limited（国家电力投资集团华东工程公司）；Hangzhou Dianzi University（杭州电子科技大学）；The University of Manchester（曼彻斯特大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Zhejiang University（浙江大学）
Compositional zero-shot learning aims to recognize unseen compositions of seen visual primitives of object classes and their states. While all primitives (states and objects) are observable during training in some combination, their complex interaction makes this task especially hard. For example, wet changes the visual appearance of a dog very differently from a bicycle. Furthermore, we argue that relationships between compositions go beyond shared states or objects. A cluttered office can contain a busy table; even though these compositions don't share a state or object, the presence of a bu…
Peking University（北京大学）；University of California, Berkeley（加州大学伯克利分校）；South China University of Technology（华南理工大学）；PengCheng Laboratory（鹏程实验室）；Carnegie Mellon University（卡内基梅隆大学）
Few-shot learning (FSL) aims at recognizing novel classes given only few training samples, which still remains a great challenge for deep learning. However, humans can easily recognize novel classes with only few samples. A key component of such ability is the compositional recognition that human can perform, which has been well studied in cognitive science but is not well explored in FSL. Inspired by such capability of humans, to imitate humans' ability of learning visual primitives and composing primitives to recognize novel classes, we propose an approach to FSL to learn a feature represent…
Compositional Zero-shot Learning via Progressive Language-based Observations
AI Chip Center for Emerging Smart Systems（新兴智能系统人工智能芯片中心）；The Hong Kong University of Science（香港科学大学）；Zhejiang University College of Computer Science（浙江大学计算机科学学院）
Multi-Sourced Compositional Generalization in Visual Question Answering
Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China（北京智能信息科技重点实验室，计算机科学与技术学院，北京理工大学，中国）；Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China（广东机器感知与智能计算实验室，深圳MSU-BIT大学，中国）
University of Tübingen（图宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；TUM（慕尼黑工业大学）；Google（谷歌）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging because the same state can for example alter the visual appearance of a dog drastically differently from a car. As a solution, we propose a novel graph formulation called Compositional Graph Embedding (CGE) that learns image features, compositional classifiers, and latent representations of visual primitives in an end-to-end manner. The key to our approach is exploiting the dep…
CSAIL, MIT（麻省理工学院计算机科学与人工智能实验室）；Harvard University（哈佛大学）；Department of Radiological Sciences, UCLA（加州大学洛杉矶分校放射科学系）；Beth Israel Deaconess Medical Center（贝丝以色列女执事医疗中心）；Massachusetts General Hospital（麻省总医院）；Microsoft Research New England（微软新英格兰研究院）
This work interprets the internal representations of deep neural networks trained for classification of diseased tissue in 2D mammograms. We propose an expert-in-the-loop interpretation method to label the behavior of internal units in convolutional neural networks (CNNs). Expert radiologists identify that the visual patterns detected by the units are correlated with meaningful medical phenomena such as mass tissue and calcificated vessels. We demonstrate that several trained CNN models are able to produce explanatory descriptions to support the final classification decisions. We view this as …
Michigan State University（密歇根州立大学）；University of Michigan（密歇根大学）
This work explores the zero-shot compositional learning ability of large pre-trained vision-language models(VLMs) within the prompt-based learning framework and propose a model (\textit{PromptCompVL}) to solve the compositonal zero-shot learning (CZSL) problem. \textit{PromptCompVL} makes two design choices: first, it uses a soft-prompting instead of hard-prompting to inject learnable parameters to reprogram VLMs for compositional learning. Second, to address the compositional challenge, it uses the soft-embedding layer to learn primitive concepts in different combinations. By combining both s…
Semantically Guided Dynamic Visual Prototype Refinement for Compositional Zero-Shot Learning
National Key Laboratory of Radar Signal Processing, Xidian University（雷达信号处理国家级重点实验室，西安电子科技大学）；Research Institute of Systems Engineering, Academy of Military Science（系统工程研究所，军事科学院）
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
The Hong Kong Polytechnic University（香港理工大学）；Hong Kong Baptist University（香港浸会大学）；Shenzhen University（深圳大学）；Jilin University（吉林大学）；Hong Kong University of Science and Technology（香港科技大学）
National University of Singapore（新加坡国立大学）；NUS Graduate School for Integrative Sciences & Engineering（新加坡国立大学综合科学与工程研究生院）
This paper proposes a novel model for recognizing images with composite attribute-object concepts, notably for composite concepts that are unseen during model training. We aim to explore the three key properties required by the task --- relation-aware, consistent, and decoupled --- to learn rich and robust features for primitive concepts that compose attribute-object pairs. To this end, we propose the Blocked Message Passing Network (BMP-Net). The model consists of two modules. The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extra…
SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院）；Zhengzhou Advanced Research Institute of Harbin Institute of Technology（哈尔滨工业大学郑州先进研究院）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳先进技术大学人工智能研究院）
PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；University of Science and Technology of China（中国科学技术大学）
University of Tübingen（蒂宾根大学）；ETH Zurich（苏黎世联邦理工学院）；Max Planck Institute (MPI) for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions of state and object visual primitives seen during training. A problem with standard CZSL is the assumption of knowing which unseen compositions will be available at test time. In this work, we overcome this assumption operating on the open world setting, where no limit is imposed on the compositional space at test time, and the search space contains a large number of unseen compositions. To address this problem, we propose a new approach, Compositional Cosine Graph Embeddings (Co-CGE), based on two principles. First,…
Learning compact and interpretable representations is a very natural task, which has not been solved satisfactorily even for simple binary datasets. In this paper, we review various ways of composing experts for binary data and argue that competitive forms of interaction are best suited to learn low-dimensional representations. We propose a new composition rule that discourages experts from focusing on similar structures and that penalizes opposing votes strongly so that abstaining from voting becomes more attractive. We also introduce a novel sequential initialization procedure, which is base…
Technische Universität München（慕尼黑工业大学）；Mercateo AG（Mercateo股份公司）
Humans are able to identify and categorize novel compositions of known concepts. The task in Compositional Zero-Shot learning (CZSL) is to learn composition of primitive concepts, i.e. objects and states, in such a way that even their novel compositions can be zero-shot classified. In this work, we do not assume any prior knowledge on the feasibility of novel compositions i.e.open-world setting, where infeasible compositions dominate the search space. We propose a Compositional Variational Graph Autoencoder (CVGAE) approach for learning the variational embeddings of the primitive concepts (nod…
Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation
School of Computer Science and Technology, China University of Petroleum (East China)（中国石油大学（华东）计算机科学与技术学院）；Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳理工大学人工智能研究院）；College of Computer Science, Northwest University（西北大学计算机科学学院）
CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models
Massachusetts Institute of Technology（麻省理工学院）；Brigham and Women’s Hospital（布里奇沃特医院）；American University in Cairo（开罗美国大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Information Technology University（信息科技大学）；University of Ontario Institute of Technology（安大略理工大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstruction
Lancaster University, United Kingdom（兰卡斯特大学，英国）；The University of Queensland, Australia（昆士兰大学，澳大利亚）；The Hong Kong Polytechnic University, China（香港理工大学，中国）；University at Buffalo, United States of America（布法罗大学，美国）
Australian National University（澳大利亚国立大学）；Mitsubishi Electric Research Labs（三菱电机研究实验室）
The world is fundamentally compositional, so it is natural to think of visual recognition as the recognition of basic visually primitives that are composed according to well-defined rules. This strategy allows us to recognize unseen complex concepts from simple visual primitives. However, the current trend in visual recognition follows a data greedy approach where huge amounts of data are required to learn models for any desired visual concept. In this paper, we build on the compositionality principle and develop an "algebra" to compose classifiers for complex visual concepts. To this end, we …
