Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can learning disentangled representation further improve the accuracy of visual dynamics prediction in object-centric models?" While there has been some attempt to learn such disentangled representations for the case of static images \citep{nsb}, to the best of our knowledge, ours is the first work which tries to do this in a general setting for video, without making any specific assumptions about the kind of attributes that an object might have. The key building block of our architecture is the notion of a {\em block}, where several blocks together constitute an object. Each block is represented as a linear combination of a given number of learnable concept vectors, which is iteratively refined during the learning process. The blocks in our model are discovered in an unsupervised manner, by attending over object masks, in a style similar to discovery of slots \citep{slot_attention}, for learning a dense object-centric representation. We employ self-attention via transformers over the discovered blocks to predict the next state resulting in discovery of visual dynamics. We perform a series of experiments on several benchmark 2-D, and 3-D datasets demonstrating that our architecture (1) can discover semantically meaningful blocks (2) help improve accuracy of dynamics prediction compared to SOTA object-centric models (3) perform significantly better in OOD setting where the specific attribute combinations are not seen earlier during training. Our experiments highlight the importance discovery of disentangled representation for visual dynamics prediction.
Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and compose triplets by a matching process. In contrast, we decouple the triplet prediction into human-object pair detection and interaction classification. Our main motivation is that detecting the human-object instances and classifying interactions accurately needs to learn representations that focus…
Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）深圳大数据研究院）；Sun Yat-sen University（中山大学）；Pazhou Lab（琶洲实验室）
Deep neural networks (DNNs) have been widely adopted in brain lesion detection and segmentation. However, locating small lesions in 2D MRI slices is challenging, and requires to balance between the granularity of 3D context aggregation and the computational complexity. In this paper, we propose a novel view-disentangled transformer to enhance the extraction of MRI features for more accurate tumour detection. First, the proposed transformer harvests long-range correlation among different positions in a 3D brain scan. Second, the transformer models a stack of slice features as multiple 2D views …
3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations during the evolution from skeleton to mesh, including joint-joint, joint-vertex and vertex-vertex relations, which often leads to implausible results. To address this issue, we propose a novel solution, called GATOR, that contains an encoder of Graph-Aware Transformer (GAT) and a decoder with Motion-Disentangled Regression (MDR) to explore these multiple relations. Specifically, GAT combines a GCN and a graph-aware self…
Pohang University of Science and Technology (POSTECH)（浦项科技大学）；Yonsei University（延世大学）
Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction, but they require a substantial number of parameters and expensive computations. Due to the large memory overhead and slow inference speed, it is difficult to deploy such models for practical use. In this paper, we propose a novel transformer encoder-decoder architecture for 3D human mesh reconstruction from a single image, called FastMETRO. We identify the performance bottleneck in the encoder-based transformers is caused by the token design which introduces high complex…
Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either impractical due to long training times and large memory consumption or forego key inductive biases. In this work, we introduce EfficientMORL, an efficient framework for the unsupervised learning of object-centric representations. We show that optimization challenges caused by requiring both symmetry and disentanglement can in fact be addressed by high-cost iterative …
Person re-identification (re-ID) under various occlusions has been a long-standing challenge as person images with different types of occlusions often suffer from misalignment in image matching and ranking. Most existing methods tackle this challenge by aligning spatial features of body parts according to external semantic cues or feature similarities but this alignment approach is complicated and sensitive to noises. We design DRL-Net, a disentangled representation learning network that handles occluded re-ID without requiring strict person image alignment or any additional supervision. Lever…
Télécom Paris, Institut Polytechnique de Paris（巴黎高等电信学院，巴黎综合理工学院）；InterDigital R&I（InterDigital研究与创新部门）
High quality facial image editing is a challenging problem in the movie post-production industry, requiring a high degree of control and identity preservation. Previous works that attempt to tackle this problem may suffer from the entanglement of facial attributes and the loss of the person's identity. Furthermore, many algorithms are limited to a certain task. To tackle these limitations, we propose to edit facial attributes via the latent space of a StyleGAN generator, by training a dedicated latent transformation network and incorporating explicit disentanglement and identity preservation t…
Technical University of Munich（慕尼黑工业大学）；German Aerospace Center（德国航空航天中心）
Monocular height estimation (MHE) from remote sensing imagery has high potential in generating 3D city models efficiently for a quick response to natural disasters. Most existing works pursue higher performance. However, there is little research exploring the interpretability of MHE networks. In this paper, we target at exploring how deep neural networks predict height from a single monocular image. Towards a comprehensive understanding of MHE networks, we propose to interpret them from multiple levels: 1) Neurons: unit-level dissection. Exploring the semantic and height selectivity of the lea…
ZAYAN: Disentangled Contrastive Transformer for Tabular Remote Sensing Data
Lane Dept. of Computer Science and Electrical Engineering（兰恩计算机科学与电气工程系）；Dept. of Geology & Geography（地质与地理系）；West Virginia University（西弗吉尼亚大学）；Department of Computer Science and Engineering（计算机科学与工程系）；Green University of Bangladesh（孟加拉国绿色大学）；Stamford University Bangladesh（班加罗尔斯坦福大学）
Simon Fraser University（西蒙弗雷泽大学）；Autodesk Research（欧特克研究院）
We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-and-extrude modeling operations. Our model utilizes distinct Transformer architectures to encode topological, geometric, and extrusion variations of construction sequences into disentangled codebooks. Autoregressive Transformer decoders generate CAD construction sequences sharing certain properties specified by the codebook vectors. Extensive experiments demonstrate that our disentangled codebook representation generates diverse and high-quality CAD models, enhan…
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features expressive for the task of object segmentation in images. In this paper, we build on the self-supervision task of masked autoencoding and explore its effectiveness for explicitly learning object-centric representations with transformers. To this end, we design an object-centric autoencoder using transformers only and train it end-to-end to reconstruct full …
Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Tencent（腾讯）；National University of Singapore（新加坡国立大学）；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）；Shenzhen Qiji Technology Co., Ltd.（深圳奇基科技有限公司）
In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos. We build upon prior work in video prediction via an autoregressive transformer over the discrete latent space of compressed videos, with an added modification to model object-centric information via bounding boxes. Due to better compressibility of object-centric representations, we can improve training efficiency by allowing the model to only access object information for long…
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）
Vision transformers have achieved great successes in many computer vision tasks. Most methods generate vision tokens by splitting an image into a regular and fixed grid and treating each cell as a token. However, not all regions are equally important in human-centric vision tasks, e.g., the human body needs a fine representation with many tokens, while the image background can be modeled by a few tokens. To address this problem, we propose a novel Vision Transformer, called Token Clustering Transformer (TCFormer), which merges tokens by progressive clustering, where the tokens can be merged fr…
Disentangled Multimodal Brain MR Image Translation via Transformer-based Modality Infuser
Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School（马萨诸塞州总医院与哈佛医学院戈登医学影像中心）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Tencent AI Lab（腾讯人工智能实验室）；Tsinghua University（清华大学）
Existing methods for face image manipulation generally focus on editing the expression, changing some predefined attributes, or applying different filters. However, users lack the flexibility of controlling the shapes of different semantic facial parts in the generated face. In this paper, we propose an approach to compute a disentangled shape representation for a face image, namely the FaceShapeGene. The proposed FaceShapeGene encodes the shape information of each semantic facial part separately into a 1D latent vector. On the basis of the FaceShapeGene, a novel part-wise face image editing s…
Beihang University（北京航空航天大学）；Sun Yat-sen University（中山大学）；Pazhou Lab（琶洲实验室）；ByteDance AI Lab（字节跳动人工智能实验室）；University of Sydney（悉尼大学）
In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on humans, HC-STVG aims to localize a spatiotemporal tube of the target person from an untrimmed video based on a given textural description. This task is useful, especially for healthcare and security-related applications, where the surveillance videos can be extremely long but only a specific person during a specific period of time is concerned. HC-STVG is a video grounding task that requires both spatial (where) and…
WcDT: World-centric Diffusion Transformer for Traffic Scene Generation
Cardiff University（卡迪夫大学）；University of Minnesota - Twin Cities（明尼苏达大学双城分校）；Mississippi State University（密西西比州立大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Toronto（多伦多大学）；University of Virginia（弗吉尼亚大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Multispectral Detection Transformer with Infrared-Centric Feature Fusion
Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology (GIST)（人工智能研究生院，全州科学技术院（GIST））；School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST)（电气工程与计算机科学学院，全州科学技术院（GIST））
The Instance-centric Transformer for the RVOS Track of LSVOS Challenge: 3rd Place Solution
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）；Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院）；University of Science and Technology Beijing (USTB)（北京科技大学）
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…
Macau University of Science and Technology（澳门科技大学）；Alibaba Group（阿里巴巴集团）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we define several metrics, including Dynamic Data Proportion (DDP) and Knowledge Assimilation Rate (KAR), to investigate the training process, and divide it into three periods accordingly: formation, growth and exploration. In particular, at the last stage of training, we observe that only a tiny portion of training examples is used to optimize the model. Given the data-hungry nature of ViTs, we thus ask a simple but i…
Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is often difficult to maintain the original content of the image during the reverse diffusion. To address this, here we present a novel diffusion-based unsupervised image translation method using disentangled style and content representation. Specifically, inspired by the splicing Vision Transformer, we extract intermediate keys of multihead self attention layer f…
University of Science and Technology of China（中国科学技术大学）；University of Chinese Academy of Sciences（中国科学院大学）；Microsoft（微软）
In this paper, we are interested in the bottom-up paradigm of estimating human poses from an image. We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions. We present a simple yet effective approach, named disentangled keypoint regression (DEKR). We adopt adaptive convolutions through pixel-wise spatial transformer to activate the pixels in the keypoint regions and accordingly learn representati…
Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it s…
Integrating AI for Human-Centric Breast Cancer Diagnostics: A Multi-Scale and Multi-View Swin Transformer Framework
Concordia Institute for Information Systems Engineering (CIISE)（康科迪亚信息系统工程研究所）；Concordia University（康科迪亚大学）；Thomas Jefferson University Hospital（泰勒斯·杰弗里斯大学医院）；College of Computing & Informatics（计算与信息学院）；Drexel University（德雷塞尔大学）
