文本到图像（T2I）生成已通过扩散模型和自回归模型得到积极研究。最近，掩码生成Transformer作为自回归模型的替代方案受到关注，通过双向注意力和并行解码克服因果注意力和自回归解码的固有局限性，从而实现高效且高质量的图像生成。然而，组合式T2I生成仍然具有挑战性，因为即使最先进的扩散模型也常常无法准确绑定属性并实现适当的文本-图像对齐。虽然扩散模型已针对此问题进行了广泛研究，但掩码生成Transformer表现出类似的局限性，却尚未在此背景下被探索。为解决这一问题，我们提出了Unmasking with Contrastive Attention Guidance（UNCAGE），一种新颖的无需训练的方法，通过利用注意力图优先对清晰表示单个对象的令牌进行去掩码，从而提高组合保真度。UNCAGE在多个基准和指标上的定量和定性评估中均持续提升性能，且推理开销可忽略不计。我们的代码可在https://github.com/furiosa-ai/uncage获取。
英文摘要：
Text-to-image (T2I) generation has been actively studied using Diffusion Models and Autoregressive Models. Recently, Masked Generative Transformers have gained attention as an alternative to Autoregressive Models to overcome the inherent limitations of causal attention and autoregressive decoding through bidirectional attention and parallel decoding, enabling efficient and high-quality image generation. However, compositional T2I generation remains challenging, as even state-of-the-art Diffusion Models often fail to accurately bind attributes and achieve proper text-image alignment. While Diffusion Models have been extensively studied for this issue, Masked Generative Transformers exhibit similar limitations but have not been explored in this context. To address this, we propose Unmasking with Contrastive Attention Guidance (UNCAGE), a novel training-free method that improves compositional fidelity by leveraging attention maps to prioritize the unmasking of tokens that clearly represent individual objects. UNCAGE consistently improves performance in both quantitative and qualitative evaluations across multiple benchmarks and metrics, with negligible inference overhead. Our code is available at https://github.com/furiosa-ai/uncage.
University of Maryland（马里兰大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Google Research（谷歌研究院）
We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models. The learning mechanisms are complementary to one another: contrastive learning shapes the embedding space across a batch of image samples; masked autoencoders focus on reconstruction of the low-frequency spatial correlations in a single image sample; and noise prediction encourages the reconstruction of the…
Tsinghua University（清华大学）；OpenAI；Peking University（北京大学）；KAUST（阿卜杜拉国王科技大学）；Mila（米拉）；University of California, Merced（加州大学默塞德分校）；Google Research（谷歌研究院）
Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images. Most existing methods address this challenge by using scene layouts, which are image-like representations of scene graphs designed to capture the coarse structures of scene images. Because scene layouts are manually crafted, the alignment with images may not be fully optimized, causing suboptimal compliance between the generated images and the original scene graphs. To tackle this issue, we pr…
MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）
Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive Representation Learning (MACRL) for self-supervised visual pre-training. In particular, MACRL leverages the effectiveness of both masked image modelling and contrastive learning. We adopt an asymmetric setting for the siamese network (i.e., encoder-decoder structure in both branches), where one branch with higher mask ratio and stronger data augmentation, while the other adopt…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Adobe Research（奥多比研究院）
We introduce a new method for diverse foreground generation with explicit control over various factors. Existing image inpainting based foreground generation methods often struggle to generate diverse results and rarely allow users to explicitly control specific factors of variation (e.g., varying the facial identity or expression for face inpainting results). We leverage contrastive learning with latent codes to generate diverse foreground results for the same masked input. Specifically, we define two sets of latent codes, where one controls a pre-defined factor (``known''), and the other con…
Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their efficiencies. In particular, self-supervised learning based methods are spurring interest due to their capability of learning diverse representations without additional labels. Among self-supervised learning tactics, contrastive learning is one specific framework validating their superiority in various fields, including anomaly detection. However, the primary objec…
We present a novel framework for exemplar based image translation. Recent advanced methods for this task mainly focus on establishing cross-domain semantic correspondence, which sequentially dominates image generation in the manner of local style control. Unfortunately, cross-domain semantic matching is challenging; and matching errors ultimately degrade the quality of generated images. To overcome this challenge, we improve the accuracy of matching on the one hand, and diminish the role of matching in image generation on the other hand. To achieve the former, we propose a masked and adaptive …
INESC TEC；Faculdade de Engenharia da Universidade do Porto（波尔图大学工程学院）；Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形学研究所IGD）；TU Darmstadt（达姆施塔特工业大学）
SARS-CoV-2 has presented direct and indirect challenges to the scientific community. One of the most prominent indirect challenges advents from the mandatory use of face masks in a large number of countries. Face recognition methods struggle to perform identity verification with similar accuracy on masked and unmasked individuals. It has been shown that the performance of these methods drops considerably in the presence of face masks, especially if the reference image is unmasked. We propose FocusFace, a multi-task architecture that uses contrastive learning to be able to accurately perform ma…
Nanyang Technological University（南洋理工大学）；Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY)（南洋理工大学-不列颠哥伦比亚大学活跃老年生活卓越联合研究中心（LILY））
Recent advances in skeleton-based person re-identification (re-ID) obtain impressive performance via either hand-crafted skeleton descriptors or skeleton representation learning with deep learning paradigms. However, they typically require skeletal pre-modeling and label information for training, which leads to limited applicability of these methods. In this paper, we focus on unsupervised skeleton-based person re-ID, and present a generic Simple Masked Contrastive learning (SimMC) framework to learn effective representations from unlabeled 3D skeletons for person re-ID. Specifically, to fully…
Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task on discretized video tokens generated via VQ-VAE. Unlike language, where the text tokens are more independent, neighboring video tokens typically have strong correlations (e.g., consecutive video frames usually look very similar), and hence uniformly masking individual tokens will make the task too trivial to learn useful representations. To deal with this is…
Contrastive Masked Autoencoders for Character-Level Open-Set Writer Identification
University of Technology Sydney（悉尼科技大学）；Australian AI Institute（澳大利亚人工智能研究所）；School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院计算机科学学院）
Nankai University（南开大学）；Bytedance Inc.（字节跳动公司）；University of Science and Technology Beijing（北京科技大学）
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This work shows that CMAE also trivially generalizes well on video action recognition without modifying the architecture and the loss criterion. By directly replacing the original pixel shift with the temporal shift, our CMAE for visual action recognition, CMAE-V for short, can generate stronger feature representations than its counterpart based on pure masked autoencoders. Notably, CMAE-V, with a hybrid architecture, can…
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget
Faculty of Computer Science, University of Vienna, Vienna, Austria（维也纳大学计算机科学学院）；UniVie Doctoral School Computer Science, University of Vienna（维也纳大学计算机科学博士学院）；Institute of Advanced Research in Artificial Intelligence (IARAI)（高级人工智能研究所）
提出 MAE-CT 方法，结合 MIM 的效率与 ID 的对象聚焦能力，通过 NNCLR 目标在预训练 MAE 顶层诱导语义聚类，无需标签且计算开销低，在 ViT 模型上多项指标达 SOTA。
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text alignment. In this paper, we show that the inferior fine-tuning performance of these pre-training approaches can be significantly improved by a simple post-processing in the form of feature distillation (FD). The feature distillation converts the old representations to new representations that have a few desirable properties just like those representations produced b…
Alibaba Group（阿里巴巴集团）；Beihang University（北京航空航天大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
We present a simple yet effective end-to-end Video-language Pre-training (VidLP) framework, Masked Contrastive Video-language Pretraining (MAC), for video-text retrieval tasks. Our MAC aims to reduce video representation's spatial and temporal redundancy in the VidLP model by a mask sampling mechanism to improve pre-training efficiency. Comparing conventional temporal sparse sampling, we propose to randomly mask a high ratio of spatial regions and only feed visible regions into the encoder as sparse spatial sampling. Similarly, we adopt the mask sampling technique for text inputs for consisten…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；UT Austin（德克萨斯大学奥斯汀分校）；IBM Research AI（IBM研究院人工智能部门）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Goethe University Frankfurt（法兰克福大学）
Tissue-Contrastive Semi-Masked Autoencoders for Segmentation Pretraining on Chest CT
Hangzhou City University（杭州城市大学）；Southwest Hospital, Army Medical University (Third Military Medical University)（陆军军医大学（第三军医大学）西南医院）；Zhejiang University（浙江大学）
Shenzhen University（深圳大学）；Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University（中山大学孙逸仙纪念医院）
Breast cancer is one of the leading causes of cancer deaths in women. As the primary output of breast screening, breast ultrasound (US) video contains exclusive dynamic information for cancer diagnosis. However, training models for video analysis is non-trivial as it requires a voluminous dataset which is also expensive to annotate. Furthermore, the diagnosis of breast lesion faces unique challenges such as inter-class similarity and intra-class variation. In this paper, we propose a pioneering approach that directly utilizes US videos in computer-aided breast cancer diagnosis. It leverages ma…
CMViM: Contrastive Masked Vim Autoencoder for 3D Multi-modal Representation Learning for AD classification
The Hong Kong Polytechnic University（香港理工大学）；University of Electronic Science and Technology of China（电子科技大学）；Shandong University（山东大学）；Research Institute for Smart Ageing, The Hong Kong Polytechnic University（香港理工大学智能老龄化研究院）
CLAR: Learning 3D Representations for Robotic Manipulation by Fusing Masked Reconstruction with Multi-Level Contrastive Alignment
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所SKL-MAIS）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Carnegie Mellon University（卡内基梅隆大学）；Galbot；CFCS, School of Computer Science, Peking University（北京大学计算机科学与技术学院CFCS）
Sun Yat-sen University（中山大学）；The Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-sen University), Ministry of Education（机器智能与先进计算教育部重点实验室（中山大学））；JD AI Research（京东人工智能研究院）
BERT-type structure has led to the revolution of vision-language pre-training and the achievement of state-of-the-art results on numerous vision-language downstream tasks. Existing solutions dominantly capitalize on the multi-modal inputs with mask tokens to trigger mask-based proxy pre-training tasks (e.g., masked language modeling and masked object/frame prediction). In this work, we argue that such masked inputs would inevitably introduce noise for cross-modal matching proxy task, and thus leave the inherent vision-language association under-explored. As an alternative, we derive a particul…
Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning
Paul C. Lauterbur Research Center for Biomedical Imaging（保罗·C·劳特伯生物医学成像研究中心）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Pengcheng Laboratory（鹏城实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Harvard University（哈佛大学）；Shanghai AI Lab（上海人工智能实验室）
As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale unsupervised learning in 3D has yet to emerge due to two stumbling blocks: the inefficiency of matching RGB-D frames as contrastive views and the annoying mode collapse phenomenon mentioned in previous works. Turning the two stumbling blocks into empirical stepping stones, we first propose an efficient and effective contrastive learning framework, which generates…
Contrastive masked auto-encoders based self-supervised hashing for 2D image and 3D point cloud cross-modal retrieval
Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology（华中科技大学武汉光电国家研究中心）；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 Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）；School of Computer Science and Cyber Engineering, Guangzhou University（广州大学计算机科学与网络工程学院）
Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics
Department of Artificial Intelligence, Yonsei University（延世大学人工智能系）；Department of Computer Science, Yonsei University（延世大学计算机科学系）；Yonsei University College of Medicine（延世大学医学院）
Deep learning has achieved great success in recent years with the aid of advanced neural network structures and large-scale human-annotated datasets. However, it is often costly and difficult to accurately and efficiently annotate large-scale datasets, especially for some specialized domains where fine-grained labels are required. In this setting, coarse labels are much easier to acquire as they do not require expert knowledge. In this work, we propose a contrastive learning method, called $\textbf{Mask}$ed $\textbf{Con}$trastive learning~($\textbf{MaskCon}$) to address the under-explored prob…
University Of Melbourne（墨尔本大学）；University of Moratuwa（莫拉图瓦大学）；National University of Singapore（新加坡国立大学）
The COVID-19 pandemic has drastically changed accepted norms globally. Within the past year, masks have been used as a public health response to limit the spread of the virus. This sudden change has rendered many face recognition based access control, authentication and surveillance systems ineffective. Official documents such as passports, driving license and national identity cards are enrolled with fully uncovered face images. However, in the current global situation, face matching systems should be able to match these reference images with masked face images. As an example, in an airport o…
Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning
University of Pisa（比萨大学）；University of Trento（特伦托大学）；FBK（布鲁诺·凯斯勒基金会）；INSAIT（保加利亚国际数学和信息学研究所）；ETH Zürich（苏黎世联邦理工学院）；Peking University（北京大学）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
本文提出 Point-CMAE，通过双重随机掩码、共享编码器与双解码器重建，并约束共同掩码 token 的特征一致性，在 MAE 点云预训练中引入显式对比学习，提升下游性能。
University of Chinese Academy of Sciences（中国科学院大学）；Meitu Inc.（美图公司）
Contrastive learning (CL) has shown great power in self-supervised learning due to its ability to capture insight correlations among large-scale data. Current CL models are biased to learn only the ability to discriminate positive and negative pairs due to the discriminative task setting. However, this bias would lead to ignoring its sufficiency for other downstream tasks, which we call the discriminative information overfitting problem. In this paper, we propose to tackle the above problems from the aspect of the Information Bottleneck (IB) principle, further pushing forward the frontier of C…
Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the pa…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）
Self-Supervised Video Hashing (SSVH) models learn to generate short binary representations for videos without ground-truth supervision, facilitating large-scale video retrieval efficiency and attracting increasing research attention. The success of SSVH lies in the understanding of video content and the ability to capture the semantic relation among unlabeled videos. Typically, state-of-the-art SSVH methods consider these two points in a two-stage training pipeline, where they firstly train an auxiliary network by instance-wise mask-and-predict tasks and secondly train a hashing model to prese…
Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While effective, contrastive learning approaches introduce sampling bias depending on the data augmentations used, which can degrade performance on downstream tasks. Moreover, these methods are limited to paired image-text data, and cannot leverage widely-available unpaired data. In this paper, we investigate whether a large multimodal model trained purely via ma…
HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Department of Automation, Tsinghua University（清华大学自动化系）；Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学北京信息科学与技术国家研究中心）
Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education, China（高可信软件技术教育部重点实验室（北京大学））；School of Computer Science, Peking University（北京大学计算机学院）；School of AI, Peking University（北京大学人工智能学院）；University of Hong Kong（香港大学）；School of EIC, Huazhong University of Science & Technology（华中科技大学电子信息与通信学院）；Baidu（百度）；UC Berkeley（加州大学伯克利分校）
Texas A&M University（得克萨斯农工大学）；Microsoft（微软）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) demonstrate that self-supervision is powerful to learn good representations. However, naively combining them is far from success. In this paper, we start by making the empirical observation that a naive joint optimization of CL and MIM losses leads to conflicting gradient directions - more severe as the layers go deeper. This motivates us to shift the paradigm from combining loss at the end, to choosing the proper learning method per network layer. Inspired by experimental observations, we find that MIM and CL are suitable …
ARC Lab（ARC实验室）；Peking University（北京大学）；Huazhong University of Science and Technology（华中科技大学）；Foundation Technology Center（基础技术中心）；Tsinghua University（清华大学）；Tencent PCG（腾讯平台与内容事业群）
Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. MIM recently dominates this line of research with state-of-the-art performance on vision Transformers (ViTs), where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great poten…
