Authors: Guangming Liu, Qi Liu, Jing Liang
In this paper, we propose a novel locally statistical active contour model (LACM) based on Aubert-Aujol (AA) denoising model and variational level set method, which can be used for SAR images segmentation with intensity inhomogeneity. Then we transform the proposed model into a global optimization model by using convex relaxation technique. Firstly, we apply the Split Bregman technique to transform the global optimization model into two alternating optimization processes of Shrink operator and Laplace operator, which is called SB_LACM model. Moreover, we propose two fast models to solve the global optimization model , which are more efficient than the SB_LACM model. The first model is: we add the proximal function to transform the global optimization model to a general ROF model[29], which can be solved by a fast denoising algorithm proposed by R.-Q.Jia, and H.Zhao; Thus we obtain a fast segmentation algorithm with global optimization solver that does not involve partial differential equations or difference equation, and only need simple difference computation. The second model is: we use a different splitting approach than one model to transform the global optimization model into a differentiable term and a general ROF model term, which can be solved by the same technique as the first model. Experiments using some challenging synthetic images and Envisat SAR images demonstrate the superiority of our proposed models with respect to the state-of-the-art models.
Authors: Houcheng Su, Daixian Liu, Mengzhu Wang, Wei Wang
Fully test-time adaptation (FTTA) adapts a model that is trained on a source domain to a target domain during the testing phase, where the two domains follow different distributions and source data is unavailable during the training phase. Existing methods usually adopt entropy minimization to reduce the uncertainty of target prediction results, and improve the FTTA performance accordingly. However, they fail to ensure the diversity in target prediction results. Recent domain adaptation study has shown that maximizing the sum of singular values of prediction results can simultaneously enhance their confidence (discriminability) and diversity. However, during the training phase, larger singular values usually take up a dominant position in loss maximization. This results in the model being more inclined to enhance discriminability for easily distinguishable classes, and the improvement in diversity is insufficiently effective. Furthermore, the adaptation and prediction in FTTA only use data from the current batch, which may lead to the risk of overfitting. To address the aforementioned issues, we propose maximizing the sum of singular values while minimizing their variance. This enables the model's focus toward the smaller singular values, enhancing discriminability between more challenging classes and effectively increasing the diversity of prediction results. Moreover, we incorporate data from the previous batch to realize semantic data augmentation for the current batch, reducing the risk of overfitting. Extensive experiments on benchmark datasets show our proposed approach outperforms some compared state-of-the-art FTTA methods.
Authors: Philippe Rufin, Sherrie Wang, Sá Nogueira Lisboa, Jan Hemmerling, Mirela G. Tulbure, Patrick Meyfroidt
Transfer learning allows for resource-efficient geographic transfer of pre-trained field delineation models. However, the scarcity of labeled data for complex and dynamic smallholder landscapes, particularly in Sub-Saharan Africa, remains a major bottleneck for large-area field delineation. This study explores opportunities of using sparse field delineation pseudo labels for fine-tuning models across geographies and sensor characteristics. We build on a FracTAL ResUNet trained for crop field delineation in India (median field size of 0.24 ha) and use this pre-trained model to generate pseudo labels in Mozambique (median field size of 0.06 ha). We designed multiple pseudo label selection strategies and compared the quantities, area properties, seasonal distribution, and spatial agreement of the pseudo labels against human-annotated training labels (n = 1,512). We then used the human-annotated labels and the pseudo labels for model fine-tuning and compared predictions against human field annotations (n = 2,199). Our results indicate i) a good baseline performance of the pre-trained model in both field delineation and field size estimation, and ii) the added value of regional fine-tuning with performance improvements in nearly all experiments. Moreover, we found iii) substantial performance increases when using only pseudo labels (up to 77% of the IoU increases and 68% of the RMSE decreases obtained by human labels), and iv) additional performance increases when complementing human annotations with pseudo labels. Pseudo labels can be efficiently generated at scale and thus facilitate domain adaptation in label-scarce settings. The workflow presented here is a stepping stone for overcoming the persisting data gaps in heterogeneous smallholder agriculture of Sub-Saharan Africa, where labels are commonly scarce.
Authors: Shanghua Liu, Anna Hedström, Deepak Hanike Basavegowda, Cornelia Weltzien, Marina M.-C. Höhne
Grasslands are known for their high biodiversity and ability to provide multiple ecosystem services. Challenges in automating the identification of indicator plants are key obstacles to large-scale grassland monitoring. These challenges stem from the scarcity of extensive datasets, the distributional shifts between generic and grassland-specific datasets, and the inherent opacity of deep learning models. This paper delves into the latter two challenges, with a specific focus on transfer learning and eXplainable Artificial Intelligence (XAI) approaches to grassland monitoring, highlighting the novelty of XAI in this domain. We analyze various transfer learning methods to bridge the distributional gaps between generic and grassland-specific datasets. Additionally, we showcase how explainable AI techniques can unveil the model's domain adaptation capabilities, employing quantitative assessments to evaluate the model's proficiency in accurately centering relevant input features around the object of interest. This research contributes valuable insights for enhancing model performance through transfer learning and measuring domain adaptability with explainable AI, showing significant promise for broader applications within the agricultural community.
Authors: Shivangi Aneja, Justus Thies, Angela Dai, Matthias Nießner
We introduce FaceTalk, a novel generative approach designed for synthesizing high-fidelity 3D motion sequences of talking human heads from input audio signal. To capture the expressive, detailed nature of human heads, including hair, ears, and finer-scale eye movements, we propose to couple speech signal with the latent space of neural parametric head models to create high-fidelity, temporally coherent motion sequences. We propose a new latent diffusion model for this task, operating in the expression space of neural parametric head models, to synthesize audio-driven realistic head sequences. In the absence of a dataset with corresponding NPHM expressions to audio, we optimize for these correspondences to produce a dataset of temporally-optimized NPHM expressions fit to audio-video recordings of people talking. To the best of our knowledge, this is the first work to propose a generative approach for realistic and high-quality motion synthesis of volumetric human heads, representing a significant advancement in the field of audio-driven 3D animation. Notably, our approach stands out in its ability to generate plausible motion sequences that can produce high-fidelity head animation coupled with the NPHM shape space. Our experimental results substantiate the effectiveness of FaceTalk, consistently achieving superior and visually natural motion, encompassing diverse facial expressions and styles, outperforming existing methods by 75% in perceptual user study evaluation.
Authors: Manu Goyal, Laura J. Tafe, James X. Feng, Kristen E. Muller, Liesbeth Hondelink, Jessica L. Bentz, Saeed Hassanpour
Endometrial cancer, the sixth most common cancer in females worldwide, presents as a heterogeneous group with certain types prone to recurrence. Precise histologic evaluation of endometrial cancer is essential for effective patient management and determining the best treatment modalities. This study introduces EndoNet, a transformer-based deep learning approach for histologic classification of endometrial cancer. EndoNet uses convolutional neural networks for extracting histologic features and a vision transformer for aggregating these features and classifying slides based on their visual characteristics. The model was trained on 929 digitized hematoxylin and eosin-stained whole slide images of endometrial cancer from hysterectomy cases at Dartmouth Health. It classifies these slides into low grade (Endometroid Grades 1 and 2) and high-grade (endometroid carcinoma FIGO grade 3, uterine serous carcinoma, carcinosarcoma) categories. EndoNet was evaluated on an internal test set of 218 slides and an external test set of 100 random slides from the public TCGA database. The model achieved a weighted average F1-score of 0.92 (95% CI: 0.87-0.95) and an AUC of 0.93 (95% CI: 0.88-0.96) on the internal test, and 0.86 (95% CI: 0.80-0.94) for F1-score and 0.86 (95% CI: 0.75-0.93) for AUC on the external test. Pending further validation, EndoNet has the potential to assist pathologists in classifying challenging gynecologic pathology tumors and enhancing patient care.
Authors: Joshua Wang
We propose a PnP algorithm for a camera constrained to two-dimensional movement (applicable, for instance, to many wheeled robotics platforms). Leveraging this assumption allows performance improvements over 3D PnP algorithms due to the reduction in search space dimensionality. It also reduces the incidence of ambiguous pose estimates (as, in most cases, the spurious solutions fall outside the plane of movement). Our algorithm finds an approximate solution using geometric criteria and refines its prediction iteratively. We compare this algorithm to existing 3D PnP algorithms in the cases of general and coplanar point configurations.
Authors: Raghav Goyal, Wan-Cyuan Fan, Mennatullah Siam, Leonid Sigal
Video Object Segmentation (VOS) has became increasingly important with availability of larger datasets and more complex and realistic settings, which involve long videos with global motion (e.g, in egocentric settings), depicting small objects undergoing both rigid and non-rigid (including state) deformations. While a number of recent approaches have been explored for this task, these data characteristics still present challenges. In this work we propose a novel, DETR-style encoder-decoder architecture, which focuses on systematically analyzing and addressing aforementioned challenges. Specifically, our model enables on-line inference with long videos in a windowed fashion, by breaking the video into clips and propagating context among them using time-coded memory. We illustrate that short clip length and longer memory with learned time-coding are important design choices for achieving state-of-the-art (SoTA) performance. Further, we propose multi-scale matching and decoding to ensure sensitivity and accuracy for small objects. Finally, we propose a novel training strategy that focuses learning on portions of the video where an object undergoes significant deformations -- a form of "soft" hard-negative mining, implemented as loss-reweighting. Collectively, these technical contributions allow our model to achieve SoTA performance on two complex datasets -- VISOR and VOST. A series of detailed ablations validate our design choices as well as provide insights into the importance of parameter choices and their impact on performance.
Authors: Abhinau K. Venkataramanan, Cosmin Stejerean, Ioannis Katsavounidis, Alan C. Bovik
Recent years have seen steady growth in the popularity and availability of High Dynamic Range (HDR) content, particularly videos, streamed over the internet. As a result, assessing the subjective quality of HDR videos, which are generally subjected to compression, is of increasing importance. In particular, we target the task of full-reference quality assessment of compressed HDR videos. The state-of-the-art (SOTA) approach HDRMAX involves augmenting off-the-shelf video quality models, such as VMAF, with features computed on non-linearly transformed video frames. However, HDRMAX increases the computational complexity of models like VMAF. Here, we show that an efficient class of video quality prediction models named FUNQUE+ achieves SOTA accuracy. This shows that the FUNQUE+ models are flexible alternatives to VMAF that achieve higher HDR video quality prediction accuracy at lower computational cost.
Authors: Mykola Lavreniuk, Shariq Farooq Bhat, Matthias Müller, Peter Wonka
This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We propose two major enhancements. First, we develop the Inverse Multi-Attentive Feature Refinement (IMAFR) module which enhances feature learning capabilities by aggregating spatial information from higher pyramid levels. Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone. The resulting architecture is suitable for a wide variety of tasks and we demonstrate its performance in the context of single-image depth estimation with a specialized decoder using classification-based bins and referring segmentation with an off-the-shelf decoder. Comprehensive experiments conducted on established datasets show that EVP achieves state-of-the-art results in single-image depth estimation for indoor (NYU Depth v2, 11.8% RMSE improvement over VPD) and outdoor (KITTI) environments, as well as referring segmentation (RefCOCO, 2.53 IoU improvement over ReLA). The code and pre-trained models are publicly available at https://github.com/Lavreniuk/EVP.
Authors: Quoc-Huy Trinh
Polyp segmentation, a contentious issue in medical imaging, has seen numerous proposed methods aimed at improving the quality of segmented masks. Currently, state-of-the-art techniques yield impressive results. However, the sheer size of these models poses challenges for practical industry applications. To address this, we present a Knowledge Distillation framework, incorporating attention supervision and the symmetrical guiding method. This framework is designed to facilitate knowledge transfer from a teacher model to a more compact student model with fewer parameters. Our experimental evaluation of the framework assesses its effectiveness in enabling the student model to acquire knowledge from the teacher efficiently. Additionally, our method serves to prevent the student model from incorporating redundant features that could lead to inaccurate predictions. Consequently, our method, boasting approximately 5 million parameters, achieves competitive results comparable to the state-of-the-art approaches. The implementation can be found at: https://github.com/huyquoctrinh/KDAS3
Authors: M. Eren Akbiyik, Nedko Savov, Danda Pani Paudel, Nikola Popovic, Christian Vater, Otmar Hilliges, Luc Van Gool, Xi Wang
Understanding the decision-making process of drivers is one of the keys to ensuring road safety. While the driver intent and the resulting ego-motion trajectory are valuable in developing driver-assistance systems, existing methods mostly focus on the motions of other vehicles. In contrast, we focus on inferring the ego trajectory of a driver's vehicle using their gaze data. For this purpose, we first collect a new dataset, GEM, which contains high-fidelity ego-motion videos paired with drivers' eye-tracking data and GPS coordinates. Next, we develop G-MEMP, a novel multimodal ego-trajectory prediction network that combines GPS and video input with gaze data. We also propose a new metric called Path Complexity Index (PCI) to measure the trajectory complexity. We perform extensive evaluations of the proposed method on both GEM and DR(eye)VE, an existing benchmark dataset. The results show that G-MEMP significantly outperforms state-of-the-art methods in both benchmarks. Furthermore, ablation studies demonstrate over 20% improvement in average displacement using gaze data, particularly in challenging driving scenarios with a high PCI. The data, code, and models can be found at https://eth-ait.github.io/g-memp/.
Authors: Liangchen Song, Liangliang Cao, Jiatao Gu, Yifan Jiang, Junsong Yuan, Hao Tang
The advancement of text-driven 3D content editing has been blessed by the progress from 2D generative diffusion models. However, a major obstacle hindering the widespread adoption of 3D content editing is its time-intensive processing. This challenge arises from the iterative and refining steps required to achieve consistent 3D outputs from 2D image-based generative models. Recent state-of-the-art methods typically require optimization time ranging from tens of minutes to several hours to edit a 3D scene using a single GPU. In this work, we propose that by incorporating correspondence regularization into diffusion models, the process of 3D editing can be significantly accelerated. This approach is inspired by the notion that the estimated samples during diffusion should be multiview-consistent during the diffusion generation process. By leveraging this multiview consistency, we can edit 3D content at a much faster speed. In most scenarios, our proposed technique brings a 10$\times$ speed-up compared to the baseline method and completes the editing of a 3D scene in 2 minutes with comparable quality.
Authors: Ethan Thomas, Salman Aslam
Cardiovascular diseases, particularly heart failure, are a leading cause of death globally. The early detection of heart failure through routine echocardiogram screenings is often impeded by the high cost and labor-intensive nature of these procedures, a barrier that can mean the difference between life and death. This paper presents ConFormer, a novel deep learning model designed to automate the estimation of Ejection Fraction (EF) and Left Ventricular Wall Thickness from echocardiograms. The implementation of ConFormer has the potential to enhance preventative cardiology by enabling cost-effective, accessible, and comprehensive heart health monitoring, thereby saving countless lives. The source code is available at https://github.com/Aether111/ConFormer.
Authors: Wonbong Jang, Lourdes Agapito
We propose NViST, a transformer-based model for novel-view synthesis from a single image, trained on a large-scale dataset of in-the-wild images with complex backgrounds. NViST transforms image inputs directly into a radiance field, adopting a scalable transformer-based architecture. In practice, NViST exploits the self-supervised features learnt by a masked autoencoder (MAE), and learns a novel decoder that translates features to 3D tokens via cross-attention and adaptive layer normalization. Our model is efficient at inference since only a single forward-pass is needed to predict a 3D representation, unlike methods that require test-time optimization or sampling such as 3D-aware diffusion models. We tackle further limitations of current new-view synthesis models. First, unlike most generative models that are trained in a category-specific manner, often on synthetic datasets or on masked inputs, our model is trained on MVImgNet, a large-scale dataset of real-world, casually-captured videos containing hundreds of object categories with diverse backgrounds. Secondly, our model does not require canonicalization of the training data - i.e. aligning all objects with a frontal view - only needing relative pose at training time which removes a substantial barrier to it being used on casually captured datasets. We show results on unseen objects and categories on MVImgNet and even casual phone captures. We conduct qualitative and quantitative evaluations on MVImgNet and ShapeNet to show that our model represents a step forward towards enabling true in-the-wild novel-view synthesis from a single image.
Authors: Jack Urbanek, Florian Bordes, Pietro Astolfi, Mary Williamson, Vasu Sharma, Adriana Romero-Soriano
Curation methods for massive vision-language datasets trade off between dataset size and quality. However, even the highest quality of available curated captions are far too short to capture the rich visual detail in an image. To show the value of dense and highly-aligned image-text pairs, we collect the Densely Captioned Images (DCI) dataset, containing 8012 natural images human-annotated with mask-aligned descriptions averaging above 1000 words each. With precise and reliable captions associated with specific parts of an image, we can evaluate vision-language models' (VLMs) understanding of image content with a novel task that matches each caption with its corresponding subcrop. As current models are often limited to 77 text tokens, we also introduce a summarized version (sDCI) in which each caption length is limited. We show that modern techniques that make progress on standard benchmarks do not correspond with significant improvement on our sDCI based benchmark. Lastly, we finetune CLIP using sDCI and show significant improvements over the baseline despite a small training set. By releasing the first human annotated dense image captioning dataset, we hope to enable the development of new benchmarks or fine-tuning recipes for the next generation of VLMs to come.
Authors: Teodora Popordanoska, Gorjan Radevski, Tinne Tuytelaars, Matthew B. Blaschko
In the face of dataset shift, model calibration plays a pivotal role in ensuring the reliability of machine learning systems. Calibration error (CE) is an indicator of the alignment between the predicted probabilities and the classifier accuracy. While prior works have delved into the implications of dataset shift on calibration, existing CE estimators assume access to labels from the target domain, which are often unavailable in practice, i.e., when the model is deployed and used. This work addresses such challenging scenario, and proposes a novel CE estimator under label shift, which is characterized by changes in the marginal label distribution $p(Y)$, while keeping the conditional $p(X|Y)$ constant between the source and target distributions. Our contribution is an approach, which, by leveraging importance re-weighting of the labeled source distribution, provides consistent and asymptotically unbiased CE estimation with respect to the shifted target distribution. Empirical results across diverse real-world datasets, under various conditions and label-shift intensities, demonstrate the effectiveness and reliability of the proposed estimator.
Authors: Muxin Zhang, Qiao Feng, Zhuo Su, Chao Wen, Zhou Xue, Kun Li
3D human generation is increasingly significant in various applications. However, the direct use of 2D generative methods in 3D generation often results in significant loss of local details, while methods that reconstruct geometry from generated images struggle with global view consistency. In this work, we introduce Joint2Human, a novel method that leverages 2D diffusion models to generate detailed 3D human geometry directly, ensuring both global structure and local details. To achieve this, we employ the Fourier occupancy field (FOF) representation, enabling the direct production of 3D shapes as preliminary results using 2D generative models. With the proposed high-frequency enhancer and the multi-view recarving strategy, our method can seamlessly integrate the details from different views into a uniform global shape.To better utilize the 3D human prior and enhance control over the generated geometry, we introduce a compact spherical embedding of 3D joints. This allows for effective application of pose guidance during the generation process. Additionally, our method is capable of generating 3D humans guided by textual inputs. Our experimental results demonstrate the capability of our method to ensure global structure, local details, high resolution, and low computational cost, simultaneously. More results and code can be found on our project page at this http URL
Authors: Frank P.-W. Lo, Jianing Qiu, Zeyu Wang, Junhong Chen, Bo Xiao, Wu Yuan, Stamatia Giannarou, Gary Frost, Benny Lo
Conventional approaches to dietary assessment are primarily grounded in self-reporting methods or structured interviews conducted under the supervision of dietitians. These methods, however, are often subjective, potentially inaccurate, and time-intensive. Although artificial intelligence (AI)-based solutions have been devised to automate the dietary assessment process, these prior AI methodologies encounter challenges in their ability to generalize across a diverse range of food types, dietary behaviors, and cultural contexts. This results in AI applications in the dietary field that possess a narrow specialization and limited accuracy. Recently, the emergence of multimodal foundation models such as GPT-4V powering the latest ChatGPT has exhibited transformative potential across a wide range of tasks (e.g., Scene understanding and image captioning) in numerous research domains. These models have demonstrated remarkable generalist intelligence and accuracy, capable of processing various data modalities. In this study, we explore the application of multimodal ChatGPT within the realm of dietary assessment. Our findings reveal that GPT-4V excels in food detection under challenging conditions with accuracy up to 87.5% without any fine-tuning or adaptation using food-specific datasets. By guiding the model with specific language prompts (e.g., African cuisine), it shifts from recognizing common staples like rice and bread to accurately identifying regional dishes like banku and ugali. Another GPT-4V's standout feature is its contextual awareness. GPT-4V can leverage surrounding objects as scale references to deduce the portion sizes of food items, further enhancing its accuracy in translating food weight into nutritional content. This alignment with the USDA National Nutrient Database underscores GPT-4V's potential to advance nutritional science and dietary assessment techniques.
Authors: Jean-Paul Mazellier, Antoine Boujon, Méline Bour-Lang, Maël Erharhd, Julien Waechter, Emilie Wernert, Pietro Mascagni, Nicolas Padoy
This technical report presents MOSaiC 3.6.2, a web-based collaborative platform designed for the annotation and evaluation of medical videos. MOSaiC is engineered to facilitate video-based assessment and accelerate surgical data science projects. We provide an overview of MOSaiC's key functionalities, encompassing group and video management, annotation tools, ontologies, assessment capabilities, and user administration. Finally, we briefly describe several medical data science studies where MOSaiC has been instrumental in the dataset development.
Authors: Sicheng Wang, Hao Jiang, Lei Xiang
Recent deep multi-view stereo (MVS) methods have widely incorporated transformers into cascade network for high-resolution depth estimation, achieving impressive results. However, existing transformer-based methods are constrained by their computational costs, preventing their extension to finer stages. In this paper, we propose a novel cross-scale transformer (CT) that processes feature representations at different stages without additional computation. Specifically, we introduce an adaptive matching-aware transformer (AMT) that employs different interactive attention combinations at multiple scales. This combined strategy enables our network to capture intra-image context information and enhance inter-image feature relationships. Besides, we present a dual-feature guided aggregation (DFGA) that embeds the coarse global semantic information into the finer cost volume construction to further strengthen global and local feature awareness. Meanwhile, we design a feature metric loss (FM Loss) that evaluates the feature bias before and after transformation to reduce the impact of feature mismatch on depth estimation. Extensive experiments on DTU dataset and Tanks and Temples (T\&T) benchmark demonstrate that our method achieves state-of-the-art results. Code is available at https://github.com/wscstrive/CT-MVSNet.
Authors: Xiran Zhou, Yi Wen, Honghao Li, Kaiyuan Li, Zhenfeng Shao, Zhigang Yan, Xiao Xie
Maps are fundamental medium to visualize and represent the real word in a simple and 16 philosophical way. The emergence of the 3rd wave information has made a proportion of maps are available to be generated ubiquitously, which would significantly enrich the dimensions and perspectives to understand the characteristics of the real world. However, a majority of map dataset have never been discovered, acquired and effectively used, and the map data used in many applications might not be completely fitted for the authentic demands of these applications. This challenge is emerged due to the lack of numerous well-labelled benchmark datasets for implementing the deep learning approaches into identifying complicated map content. Thus, we develop a large-scale benchmark dataset that includes well-labelled dataset for map text annotation recognition, map scene classification, map super-resolution reconstruction, and map style transferring. Furthermore, these well-labelled datasets would facilitate the state-of-the-art machine intelligence technologies to conduct map feature detection, map pattern recognition and map content retrieval. We hope our efforts would be useful for AI-enhanced cartographical applications.
Authors: Wenbin Zou, Hongxia Gao, Tian Ye, Liang Chen, Weipeng Yang, Shasha Huang, Hongsheng Chen, Sixiang Chen
Night photography often struggles with challenges like low light and blurring, stemming from dark environments and prolonged exposures. Current methods either disregard priors and directly fitting end-to-end networks, leading to inconsistent illumination, or rely on unreliable handcrafted priors to constrain the network, thereby bringing the greater error to the final result. We believe in the strength of data-driven high-quality priors and strive to offer a reliable and consistent prior, circumventing the restrictions of manual priors. In this paper, we propose Clearer Night Image Restoration with Vector-Quantized Codebook (VQCNIR) to achieve remarkable and consistent restoration outcomes on real-world and synthetic benchmarks. To ensure the faithful restoration of details and illumination, we propose the incorporation of two essential modules: the Adaptive Illumination Enhancement Module (AIEM) and the Deformable Bi-directional Cross-Attention (DBCA) module. The AIEM leverages the inter-channel correlation of features to dynamically maintain illumination consistency between degraded features and high-quality codebook features. Meanwhile, the DBCA module effectively integrates texture and structural information through bi-directional cross-attention and deformable convolution, resulting in enhanced fine-grained detail and structural fidelity across parallel decoders. Extensive experiments validate the remarkable benefits of VQCNIR in enhancing image quality under low-light conditions, showcasing its state-of-the-art performance on both synthetic and real-world datasets. The code is available at https://github.com/AlexZou14/VQCNIR.
Authors: Haolin Qin, Daquan Zhou, Tingfa Xu, Ziyang Bian, Jianan Li
Transformers have astounding representational power but typically consume considerable computation which is quadratic with image resolution. The prevailing Swin transformer reduces computational costs through a local window strategy. However, this strategy inevitably causes two drawbacks: (1) the local window-based self-attention hinders global dependency modeling capability; (2) recent studies point out that local windows impair robustness. To overcome these challenges, we pursue a preferable trade-off between computational cost and performance. Accordingly, we propose a novel factorization self-attention mechanism (FaSA) that enjoys both the advantages of local window cost and long-range dependency modeling capability. By factorizing the conventional attention matrix into sparse sub-attention matrices, FaSA captures long-range dependencies while aggregating mixed-grained information at a computational cost equivalent to the local window-based self-attention. Leveraging FaSA, we present the factorization vision transformer (FaViT) with a hierarchical structure. FaViT achieves high performance and robustness, with linear computational complexity concerning input image spatial resolution. Extensive experiments have shown FaViT's advanced performance in classification and downstream tasks. Furthermore, it also exhibits strong model robustness to corrupted and biased data and hence demonstrates benefits in favor of practical applications. In comparison to the baseline model Swin-T, our FaViT-B2 significantly improves classification accuracy by 1% and robustness by 7%, while reducing model parameters by 14%. Our code will soon be publicly available at https://github.com/q2479036243/FaViT.
Authors: Manuel Rebol, Krzysztof Pietroszek, Claudia Ranniger, Colton Hood, Adam Rutenberg, Neal Sikka, David Li, Christian Gütl
Medical procedures are an essential part of healthcare delivery, and the acquisition of procedural skills is a critical component of medical education. Unfortunately, procedural skill is not evenly distributed among medical providers. Skills may vary within departments or institutions, and across geographic regions, depending on the provider's training and ongoing experience. We present a mixed reality real-time communication system to increase access to procedural skill training and to improve remote emergency assistance. Our system allows a remote expert to guide a local operator through a medical procedure. RGBD cameras capture a volumetric view of the local scene including the patient, the operator, and the medical equipment. The volumetric capture is augmented onto the remote expert's view to allow the expert to spatially guide the local operator using visual and verbal instructions. We evaluated our mixed reality communication system in a study in which experts teach the ultrasound-guided placement of a central venous catheter (CVC) to students in a simulation setting. The study compares state-of-the-art video communication against our system. The results indicate that our system enhances and offers new possibilities for visual communication compared to video teleconference-based training.
Authors: Xiao Yang, Enmin Song, Guangzhi Ma, Yunfeng Zhu, Dongming Yu, Bowen Ding, Xianyuan Wang
Colon cancer is expected to become the second leading cause of cancer death in the United States in 2023. Although colonoscopy is one of the most effective methods for early prevention of colon cancer, up to 30% of polyps may be missed by endoscopists, thereby increasing patients' risk of developing colon cancer. Though deep neural networks have been proven to be an effective means of enhancing the detection rate of polyps. However, the variation of polyp size brings the following problems: (1) it is difficult to design an efficient and sufficient multi-scale feature fusion structure; (2) matching polyps of different sizes with fixed-size anchor boxes is a hard challenge. These problems reduce the performance of polyp detection and also lower the model's training and detection efficiency. To address these challenges, this paper proposes a new model called YOLO-OB. Specifically, we developed a bidirectional multiscale feature fusion structure, BiSPFPN, which could enhance the feature fusion capability across different depths of a CNN. We employed the ObjectBox detection head, which used a center-based anchor-free box regression strategy that could detect polyps of different sizes on feature maps of any scale. Experiments on the public dataset SUN and the self-collected colon polyp dataset Union demonstrated that the proposed model significantly improved various performance metrics of polyp detection, especially the recall rate. Compared to the state-of-the-art results on the public dataset SUN, the proposed method achieved a 6.73% increase on recall rate from 91.5% to 98.23%. Furthermore, our YOLO-OB was able to achieve real-time polyp detection at a speed of 39 frames per second using a RTX3090 graphics card. The implementation of this paper can be found here: https://github.com/seanyan62/YOLO-OB.
Authors: Wentao Pan, Zhe Xu, Jiangpeng Yan, Zihan Wu, Raymond Kai-yu Tong, Xiu Li, Jianhua Yao
Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is widely used as a benchmark scheme. Despite its effectiveness, we observe that such scheme struggles with satisfactory segmentation for the local regions. This can be because it originally stems from the image classification task and lacks specialized mechanisms to capture fine-grained local semantics that prioritizes in dense prediction. To address this issue, we propose a novel framework called \texttt{MaskMatch}, which enables fine-grained locality learning to achieve better dense segmentation. On top of the original teacher-student framework, we design a masked modeling proxy task that encourages the student model to predict the segmentation given the unmasked image patches (even with 30\% only) and enforces the predictions to be consistent with pseudo-labels generated by the teacher model using the complete image. Such design is motivated by the intuition that if the predictions are more consistent given insufficient neighboring information, stronger fine-grained locality perception is achieved. Besides, recognizing the importance of reliable pseudo-labels in the above locality learning and the original consistency learning scheme, we design a multi-scale ensembling strategy that considers context at different levels of abstraction for pseudo-label generation. Extensive experiments on benchmark datasets demonstrate the superiority of our method against previous approaches and its plug-and-play flexibility.
Authors: Yi Xin, Junlong Du, Qiang Wang, Ke Yan, Shouhong Ding
Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific decoders. However, the complexity of the decoders increases with the number of tasks. To tackle this challenge, we integrate the decoder-free vision-language model CLIP, which exhibits robust zero-shot generalization capability. Recently, parameter-efficient transfer learning methods have been extensively explored with CLIP for adapting to downstream tasks, where prompt tuning showcases strong potential. Nevertheless, these methods solely fine-tune a single modality (text or visual), disrupting the modality structure of CLIP. In this paper, we first propose Multi-modal Alignment Prompt (MmAP) for CLIP, which aligns text and visual modalities during fine-tuning process. Building upon MmAP, we develop an innovative multi-task prompt learning framework. On the one hand, to maximize the complementarity of tasks with high similarity, we utilize a gradient-driven task grouping method that partitions tasks into several disjoint groups and assign a group-shared MmAP to each group. On the other hand, to preserve the unique characteristics of each task, we assign an task-specific MmAP to each task. Comprehensive experiments on two large multi-task learning datasets demonstrate that our method achieves significant performance improvements compared to full fine-tuning while only utilizing approximately 0.09% of trainable parameters.
Authors: Guiqin Wang, Peng Zhao, Yanjiang Shi, Cong Zhao, Shusen Yang
Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus on designing loss functions and fusing cross-modal information. This overlooks the spatial-temporal feature semantics, resulting in limited advancements in model compression. Addressing this gap, our paper introduces an innovative knowledge distillation framework, with the generative model for training a lightweight student model. In particular, the framework is organized into two steps: the initial phase is Feature Representation, wherein a generative model-based attention module is trained to represent feature semantics; Subsequently, the Generative-based Feature Distillation phase encompasses both Generative Distillation and Attention Distillation, with the objective of transferring attention-based feature semantics with the generative model. The efficacy of our approach is demonstrated through comprehensive experiments on diverse popular datasets, proving considerable enhancements in video action recognition task. Moreover, the effectiveness of our proposed framework is validated in the context of more intricate video action detection task. Our code is available at https://github.com/aaai-24/Generative-based-KD.
Authors: Jiangming Shi, Shanshan Zheng, Xiangbo Yin, Yang Lu, Yuan Xie, Yanyun Qu
Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for FL, which together with the class-distribution imbalance further enhances the difficulty of FL. Great progress has been made in large vision-language models, such as Contrastive Language-Image Pre-training (CLIP), which paves a new way for image classification and object recognition. Inspired by the success of CLIP on few-shot and zero-shot learning, we use CLIP to optimize the federated learning between server and client models under its vision-language supervision. It is promising to mitigate the user heterogeneity and class-distribution balance due to the powerful cross-modality representation and rich open-vocabulary prior knowledge. In this paper, we propose the CLIP-guided FL (CLIP2FL) method on heterogeneous and long-tailed data. In CLIP2FL, the knowledge of the off-the-shelf CLIP model is transferred to the client-server models, and a bridge is built between the client and server. Specifically, for client-side learning, knowledge distillation is conducted between client models and CLIP to improve the ability of client-side feature representation. For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model. A prototype contrastive learning with the supervision of the text encoder of CLIP is introduced to generate federated features depending on the client-side gradients, and they are used to retrain a balanced server classifier.
Authors: Kawisorn Kamtue, Jose M.F. Moura, Orathai Sangpetch, Paulo Garcia
While deep learning has been very successful in computer vision, real world operating conditions such as lighting variation, background clutter, or occlusion hinder its accuracy across several tasks. Prior work has shown that hybrid models -- combining neural networks and heuristics/algorithms -- can outperform vanilla deep learning for several computer vision tasks, such as classification or tracking. We consider the case of object tracking, and evaluate a hybrid model (PhyOT) that conceptualizes deep neural networks as ``sensors'' in a Kalman filter setup, where prior knowledge, in the form of Newtonian laws of motion, is used to fuse sensor observations and to perform improved estimations. Our experiments combine three neural networks, performing position, indirect velocity and acceleration estimation, respectively, and evaluate such a formulation on two benchmark datasets: a warehouse security camera dataset that we collected and annotated and a traffic camera open dataset. Results suggest that our PhyOT can track objects in extreme conditions that the state-of-the-art deep neural networks fail while its performance in general cases does not degrade significantly from that of existing deep learning approaches. Results also suggest that our PhyOT components are generalizable and transferable.
Authors: Shuailei Ma, Yuefeng Wang, Ying Wei, Jiaqi Fan, Xinyu Sun, Peihao Chen, Enming Zhang
Open World Object Detection (OWOD) is a novel computer vision task with a considerable challenge, bridging the gap between classic object detection (OD) benchmarks and real-world object detection. In addition to detecting and classifying seen/known objects, OWOD algorithms are expected to localize all potential unseen/unknown objects and incrementally learn them. The large pre-trained vision-language grounding models (VLM,eg, GLIP) have rich knowledge about the open world, but are limited by text prompts and cannot localize indescribable objects. However, there are many detection scenarios which pre-defined language descriptions are unavailable during inference. In this paper, we attempt to specialize the VLM model for OWOD task by distilling its open-world knowledge into a language-agnostic detector. Surprisingly, we observe that the combination of a simple knowledge distillation approach and the automatic pseudo-labeling mechanism in OWOD can achieve better performance for unknown object detection, even with a small amount of data. Unfortunately, knowledge distillation for unknown objects severely affects the learning of detectors with conventional structures for known objects, leading to catastrophic forgetting. To alleviate these problems, we propose the down-weight loss function for knowledge distillation from vision-language to single vision modality. Meanwhile, we decouple the learning of localization and recognition to reduce the impact of category interactions of known and unknown objects on the localization learning process. Comprehensive experiments performed on MS-COCO and PASCAL VOC demonstrate the effectiveness of our methods.
Authors: Affan Yasin, Rubia Fatima
The research introduces a novel plant disease detection model based on Convolutional Neural Networks (CNN) for plant image classification, marking a significant contribution to image categorization. The innovative training approach enables a streamlined and efficient system implementation. The model classifies two distinct plant diseases into four categories, presenting a novel technique for plant disease identification. In Experiment 1, Inception-V3, Dense-Net-121, ResNet-101-V2, and Xception models were employed for CNN training. The newly created plant disease image dataset includes 1963 tomato plant images and 7316 corn plant images from the PlantVillage dataset. Of these, 1374 tomato images and 5121 corn images were used for training, while 589 tomato images and 2195 corn images were used for testing/validation. Results indicate that the Xception model outperforms the other three models, yielding val_accuracy values of 95.08% and 92.21% for the tomato and corn datasets, with corresponding val_loss values of 0.3108 and 0.4204, respectively. In Experiment 2, CNN with Batch Normalization achieved disease detection rates of approximately 99.89% in the training set and val_accuracy values exceeding 97.52%, accompanied by a val_loss of 0.103. Experiment 3 employed a CNN architecture as the base model, introducing additional layers in Model 2, skip connections in Model 3, and regularizations in Model 4. Detailed experiment results and model efficiency are outlined in the paper's sub-section 1.5. Experiment 4 involved combining all corn and tomato images, utilizing various models, including MobileNet (val_accuracy=86.73%), EfficientNetB0 (val_accuracy=93.973%), Xception (val_accuracy=74.91%), InceptionResNetV2 (val_accuracy=31.03%), and CNN (59.79%). Additionally, our proposed model achieved a val_accuracy of 84.42%.
Authors: Kezheng Xiong, Maoji Zheng, Qingshan Xu, Chenglu Wen, Siqi Shen, Cheng Wang
Point cloud registration, a fundamental task in 3D computer vision, has remained largely unexplored in cross-source point clouds and unstructured scenes. The primary challenges arise from noise, outliers, and variations in scale and density. However, neglected geometric natures of point clouds restricts the performance of current methods. In this paper, we propose a novel method termed SPEAL to leverage skeletal representations for effective learning of intrinsic topologies of point clouds, facilitating robust capture of geometric intricacy. Specifically, we design the Skeleton Extraction Module to extract skeleton points and skeletal features in an unsupervised manner, which is inherently robust to noise and density variances. Then, we propose the Skeleton-Aware GeoTransformer to encode high-level skeleton-aware features. It explicitly captures the topological natures and inter-point-cloud skeletal correlations with the noise-robust and density-invariant skeletal representations. Next, we introduce the Correspondence Dual-Sampler to facilitate correspondences by augmenting the correspondence set with skeletal correspondences. Furthermore, we construct a challenging novel large-scale cross-source point cloud dataset named KITTI CrossSource for benchmarking cross-source point cloud registration methods. Extensive quantitative and qualitative experiments are conducted to demonstrate our approach's superiority and robustness on both cross-source and same-source datasets. To the best of our knowledge, our approach is the first to facilitate point cloud registration with skeletal geometric priors.
Authors: Renjie Wu, Hu Wang, Feras Dayoub, Hsiang-Ting Chen
Augmented Reality (AR) devices, emerging as prominent mobile interaction platforms, face challenges in user safety, particularly concerning oncoming vehicles. While some solutions leverage onboard camera arrays, these cameras often have limited field-of-view (FoV) with front or downward perspectives. Addressing this, we propose a new out-of-view semantic segmentation task and Segment Beyond View (SBV), a novel audio-visual semantic segmentation method. SBV supplements the visual modality, which miss the information beyond FoV, with the auditory information using a teacher-student distillation model (Omni2Ego). The model consists of a vision teacher utilising panoramic information, an auditory teacher with 8-channel audio, and an audio-visual student that takes views with limited FoV and binaural audio as input and produce semantic segmentation for objects outside FoV. SBV outperforms existing models in comparative evaluations and shows a consistent performance across varying FoV ranges and in monaural audio settings.
Authors: Xiangtao Meng, Li Wang, Shanqing Guo, Lei Ju, Qingchuan Zhao
While DeepFake applications are becoming popular in recent years, their abuses pose a serious privacy threat. Unfortunately, most related detection algorithms to mitigate the abuse issues are inherently vulnerable to adversarial attacks because they are built atop DNN-based classification models, and the literature has demonstrated that they could be bypassed by introducing pixel-level perturbations. Though corresponding mitigation has been proposed, we have identified a new attribute-variation-based adversarial attack (AVA) that perturbs the latent space via a combination of Gaussian prior and semantic discriminator to bypass such mitigation. It perturbs the semantics in the attribute space of DeepFake images, which are inconspicuous to human beings (e.g., mouth open) but can result in substantial differences in DeepFake detection. We evaluate our proposed AVA attack on nine state-of-the-art DeepFake detection algorithms and applications. The empirical results demonstrate that AVA attack defeats the state-of-the-art black box attacks against DeepFake detectors and achieves more than a 95% success rate on two commercial DeepFake detectors. Moreover, our human study indicates that AVA-generated DeepFake images are often imperceptible to humans, which presents huge security and privacy concerns.
Authors: Ziyan Wang, Giljoo Nam, Aljaz Bozic, Chen Cao, Jason Saragih, Michael Zollhoefer, Jessica Hodgins
Hair plays a significant role in personal identity and appearance, making it an essential component of high-quality, photorealistic avatars. Existing approaches either focus on modeling the facial region only or rely on personalized models, limiting their generalizability and scalability. In this paper, we present a novel method for creating high-fidelity avatars with diverse hairstyles. Our method leverages the local similarity across different hairstyles and learns a universal hair appearance prior from multi-view captures of hundreds of people. This prior model takes 3D-aligned features as input and generates dense radiance fields conditioned on a sparse point cloud with color. As our model splits different hairstyles into local primitives and builds prior at that level, it is capable of handling various hair topologies. Through experiments, we demonstrate that our model captures a diverse range of hairstyles and generalizes well to challenging new hairstyles. Empirical results show that our method improves the state-of-the-art approaches in capturing and generating photorealistic, personalized avatars with complete hair.
Authors: Ru Li, Jia Liu, Guanghui Liu, Shengping Zhang, Bing Zeng, Shuaicheng Liu
In this paper, we propose SpectralNeRF, an end-to-end Neural Radiance Field (NeRF)-based architecture for high-quality physically based rendering from a novel spectral perspective. We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning different wavelengths, 2) the combination of these spectrum maps for the RGB output. Our SpectralNeRF follows these two steps through the proposed multi-layer perceptron (MLP)-based architecture (SpectralMLP) and Spectrum Attention UNet (SAUNet). Given the ray origin and the ray direction, the SpectralMLP constructs the spectral radiance field to obtain spectrum maps of novel views, which are then sent to the SAUNet to produce RGB images of white-light illumination. Applying NeRF to build up the spectral rendering is a more physically-based way from the perspective of ray-tracing. Further, the spectral radiance fields decompose difficult scenes and improve the performance of NeRF-based methods. Comprehensive experimental results demonstrate the proposed SpectralNeRF is superior to recent NeRF-based methods when synthesizing new views on synthetic and real datasets. The codes and datasets are available at https://github.com/liru0126/SpectralNeRF.
Authors: Yi-Chun Chen, Arnav Jhala
We investigate the challenges of style transfer in multi-modal visual narratives. Among static visual narratives such as comics and manga, there are distinct visual styles in terms of presentation. They include style features across multiple dimensions, such as panel layout, size, shape, and color. They include both visual and text media elements. The layout of both text and media elements is also significant in terms of narrative communication. The sequential transitions between panels are where readers make inferences about the narrative world. These feature differences provide an interesting challenge for style transfer in which there are distinctions between the processing of features for each modality. We introduce the notion of comprehension-preserving style transfer (CPST) in such multi-modal domains. CPST requires not only traditional metrics of style transfer but also metrics of narrative comprehension. To spur further research in this area, we present an annotated dataset of comics and manga and an initial set of algorithms that utilize separate style transfer modules for the visual, textual, and layout parameters. To test whether the style transfer preserves narrative semantics, we evaluate this algorithm through visual story cloze tests inspired by work in computational cognition of narrative systems. Understanding the connection between style and narrative semantics provides insight for applications ranging from informational brochure designs to data storytelling.
Authors: Guoqing Chao, Yi Jiang, Dianhui Chu
Incomplete multi-view clustering becomes an important research problem, since multi-view data with missing values are ubiquitous in real-world applications. Although great efforts have been made for incomplete multi-view clustering, there are still some challenges: 1) most existing methods didn't make full use of multi-view information to deal with missing values; 2) most methods just employ the consistent information within multi-view data but ignore the complementary information; 3) For the existing incomplete multi-view clustering methods, incomplete multi-view representation learning and clustering are treated as independent processes, which leads to performance gap. In this work, we proposed a novel Incomplete Contrastive Multi-View Clustering method with high-confidence guiding (ICMVC). Firstly, we proposed a multi-view consistency relation transfer plus graph convolutional network to tackle missing values problem. Secondly, instance-level attention fusion and high-confidence guiding are proposed to exploit the complementary information while instance-level contrastive learning for latent representation is designed to employ the consistent information. Thirdly, an end-to-end framework is proposed to integrate multi-view missing values handling, multi-view representation learning and clustering assignment for joint optimization. Experiments compared with state-of-the-art approaches demonstrated the effectiveness and superiority of our method. Our code is publicly available at https://github.com/liunian-Jay/ICMVC.
Authors: Yi Guo, Yiqian He, Xiaoyang Li, Haotong Qin, Van Tung Pham, Yang Zhang, Shouda Liu
Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices. In order to train a small network (student) under the guidance of a large network (teacher), the intuitive method is regularizing the feature maps or logits of the student using the teacher's information. However, existing methods either over-restrict the student to learn all information from the teacher, which lead to some bad local minimum, or use various fancy and elaborate modules to process and align features, which are complex and lack generality. In this work, we proposed an abstract and general paradigm for the KD task, referred to as DIMensionality Reduction KD (RdimKD), which solely relies on dimensionality reduction, with a very minor modification to naive L2 loss. RdimKD straightforwardly utilizes a projection matrix to project both the teacher's and student's feature maps onto a low-dimensional subspace, which are then optimized during training. RdimKD achieves the goal in the simplest way that not only does the student get valuable information from the teacher, but it also ensures sufficient flexibility to adapt to the student's low-capacity reality. Our extensive empirical findings indicate the effectiveness of RdimKD across various learning tasks and diverse network architectures.
Authors: Rixin Zhou, Ding Xia, Yi Zhang, Honglin Pang, Xi Yang, Chuntao Li
In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are always difficult to tune hyperparameters for extensive data and computationally time-consuming. Therefore, we propose a neural network that can effectively utilize neighbor textures with contour shape information to fundamentally improve performance. First, we employ a graph-based network to extract the local contour and texture features of fragments. Then, for the pair-searching task, we adopt a linear transformer-based module to integrate these local features and use contrastive loss to encode the global features of each fragment. For the pair-matching task, we design a weighted fusion module to dynamically fuse extracted local contour and texture features, and formulate a similarity matrix for each pair of fragments to calculate the matching score and infer the adjacent segment of contours. To faithfully evaluate our proposed network, we created a new image fragment dataset through an algorithm we designed that tears complete images into irregular fragments. The experimental results show that our proposed network achieves excellent pair-searching accuracy, reduces matching errors, and significantly reduces computational time. Details, sourcecode, and data are available in our supplementary material.
Authors: Yi-Chun Chen, Arnav Jhala
Understanding how humans communicate and perceive narratives is important for media technology research and development. This is particularly important in current times when there are tools and algorithms that are easily available for amateur users to create high-quality content. Narrative media develops over time a set of recognizable patterns of features across similar artifacts. Genre is one such grouping of artifacts for narrative media with similar patterns, tropes, and story structures. While much work has been done on genre-based classifications in text and video, we present a novel approach to do a multi-modal analysis of genre based on comics and manga-style visual narratives. We present a systematic feature analysis of an annotated dataset that includes a variety of western and eastern visual books with annotations for high-level narrative patterns. We then present a detailed analysis of the contributions of high-level features to genre classification for this medium. We highlight some of the limitations and challenges of our existing computational approaches in modeling subjective labels. Our contributions to the community are: a dataset of annotated manga books, a multi-modal analysis of visual panels and text in a constrained and popular medium through high-level features, and a systematic process for incorporating subjective narrative patterns in computational models.
Authors: Hui EnPang, Zhongang Cai, Lei Yang, Qingyi Tao, Zhonghua Wu, Tianwei Zhang, Ziwei Liu
Whole-body pose and shape estimation aims to jointly predict different behaviors (e.g., pose, hand gesture, facial expression) of the entire human body from a monocular image. Existing methods often exhibit degraded performance under the complexity of in-the-wild scenarios. We argue that the accuracy and reliability of these models are significantly affected by the quality of the predicted \textit{bounding box}, e.g., the scale and alignment of body parts. The natural discrepancy between the ideal bounding box annotations and model detection results is particularly detrimental to the performance of whole-body pose and shape estimation. In this paper, we propose a novel framework to enhance the robustness of whole-body pose and shape estimation. Our framework incorporates three new modules to address the above challenges from three perspectives: \textbf{1) Localization Module} enhances the model's awareness of the subject's location and semantics within the image space. \textbf{2) Contrastive Feature Extraction Module} encourages the model to be invariant to robust augmentations by incorporating contrastive loss with dedicated positive samples. \textbf{3) Pixel Alignment Module} ensures the reprojected mesh from the predicted camera and body model parameters are accurate and pixel-aligned. We perform comprehensive experiments to demonstrate the effectiveness of our proposed framework on body, hands, face and whole-body benchmarks. Codebase is available at \url{https://github.com/robosmplx/robosmplx}.
Authors: Yi Xin, Junlong Du, Qiang Wang, Zhiwen Lin, Ke Yan
Large-scale pre-trained models have achieved remarkable success in various computer vision tasks. A standard approach to leverage these models is to fine-tune all model parameters for downstream tasks, which poses challenges in terms of computational and storage costs. Recently, inspired by Natural Language Processing (NLP), parameter-efficient transfer learning has been successfully applied to vision tasks. However, most existing techniques primarily focus on single-task adaptation, and despite limited research on multi-task adaptation, these methods often exhibit suboptimal training and inference efficiency. In this paper, we first propose an once-for-all Vision Multi-Task Adapter (VMT-Adapter), which strikes approximately O(1) training and inference efficiency w.r.t task number. Concretely, VMT-Adapter shares the knowledge from multiple tasks to enhance cross-task interaction while preserves task-specific knowledge via independent knowledge extraction modules. Notably, since task-specific modules require few parameters, VMT-Adapter can handle an arbitrary number of tasks with a negligible increase of trainable parameters. We also propose VMT-Adapter-Lite, which further reduces the trainable parameters by learning shared parameters between down- and up-projections. Extensive experiments on four dense scene understanding tasks demonstrate the superiority of VMT-Adapter(-Lite), achieving a 3.96%(1.34%) relative improvement compared to single-task full fine-tuning, while utilizing merely ~1% (0.36%) trainable parameters of the pre-trained model.
Authors: Hao Shao, Yang Zhang, Qibin Hou
We present a new boundary sensitive framework for polyp segmentation, called Polyper. Our method is motivated by a clinical approach that seasoned medical practitioners often leverage the inherent features of interior polyp regions to tackle blurred boundaries.Inspired by this, we propose explicitly leveraging polyp regions to bolster the model's boundary discrimination capability while minimizing computation. Our approach first extracts boundary and polyp regions from the initial segmentation map through morphological operators. Then, we design the boundary sensitive attention that concentrates on augmenting the features near the boundary regions using the interior polyp regions's characteristics to generate good segmentation results. Our proposed method can be seamlessly integrated with classical encoder networks, like ResNet-50, MiT-B1, and Swin Transformer. To evaluate the effectiveness of Polyper, we conduct experiments on five publicly available challenging datasets, and receive state-of-the-art performance on all of them. Code is available at https://github.com/haoshao-nku/medical_seg.git.
Authors: Zhenrong Liu, Yang Li, Yi Gong, Yik-Chung Wu
In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stability. Concurrently, we judiciously select only a subset of neurons in each layer of the network while training individual tasks to learn the past tasks' feature representation matrix in low-rank. This increases the null space dimension when designing network parameters for subsequent tasks, thereby enhancing the plasticity. Using CIFAR-100 and TinyImageNet as benchmark datasets for continual learning, the proposed approach consistently outperforms state-of-the-art methods.
Authors: Animesh Karnewar, Andrea Vedaldi, Niloy J. Mitra, David Novotny
The recently introduced Forward-Diffusion method allows to train a 3D diffusion model using only 2D images for supervision. However, it does not easily generalise to different 3D representations and requires a computationally expensive auto-regressive sampling process to generate the underlying 3D scenes. In this paper, we propose GOEn: Gradient Origin Encoding (pronounced "gone"). GOEn can encode input images into any type of 3D representation without the need to use a pre-trained image feature extractor. It can also handle single, multiple or no source view(s) alike, by design, and tries to maximise the information transfer from the views to the encodings. Our proposed GOEnFusion model pairs GOEn encodings with a realisation of the Forward-Diffusion model which addresses the limitations of the vanilla Forward-Diffusion realisation. We evaluate how much information the GOEn mechanism transfers to the encoded representations, and how well it captures the prior distribution over the underlying 3D scenes, through the lens of a partial AutoEncoder. Lastly, the efficacy of the GOEnFusion model is evaluated on the recently proposed OmniObject3D dataset while comparing to the state-of-the-art Forward and non-Forward-Diffusion models and other 3D generative models.
Authors: Hanyang Kong, Dongze Lian, Michael Bi Mi, Xinchao Wang
We introduce DreamDrone, an innovative method for generating unbounded flythrough scenes from textual prompts. Central to our method is a novel feature-correspondence-guidance diffusion process, which utilizes the strong correspondence of intermediate features in the diffusion model. Leveraging this guidance strategy, we further propose an advanced technique for editing the intermediate latent code, enabling the generation of subsequent novel views with geometric consistency. Extensive experiments reveal that DreamDrone significantly surpasses existing methods, delivering highly authentic scene generation with exceptional visual quality. This approach marks a significant step in zero-shot perpetual view generation from textual prompts, enabling the creation of diverse scenes, including natural landscapes like oases and caves, as well as complex urban settings such as Lego-style street views. Our code is publicly available.
Authors: Zexiang Liu, Yangguang Li, Youtian Lin, Xin Yu, Sida Peng, Yan-Pei Cao, Xiaojuan Qi, Xiaoshui Huang, Ding Liang, Wanli Ouyang
Recent advancements in text-to-3D generation technology have significantly advanced the conversion of textual descriptions into imaginative well-geometrical and finely textured 3D objects. Despite these developments, a prevalent limitation arises from the use of RGB data in diffusion or reconstruction models, which often results in models with inherent lighting and shadows effects that detract from their realism, thereby limiting their usability in applications that demand accurate relighting capabilities. To bridge this gap, we present UniDream, a text-to-3D generation framework by incorporating unified diffusion priors. Our approach consists of three main components: (1) a dual-phase training process to get albedo-normal aligned multi-view diffusion and reconstruction models, (2) a progressive generation procedure for geometry and albedo-textures based on Score Distillation Sample (SDS) using the trained reconstruction and diffusion models, and (3) an innovative application of SDS for finalizing PBR generation while keeping a fixed albedo based on Stable Diffusion model. Extensive evaluations demonstrate that UniDream surpasses existing methods in generating 3D objects with clearer albedo textures, smoother surfaces, enhanced realism, and superior relighting capabilities.
Authors: Qingsong Yan, Qiang Wang, Kaiyong Zhao, Jie Chen, Bo Li, Xiaowen Chu, Fei Deng
Neural Radiance Fields (NeRF) have demonstrated impressive performance in novel view synthesis. However, NeRF and most of its variants still rely on traditional complex pipelines to provide extrinsic and intrinsic camera parameters, such as COLMAP. Recent works, like NeRFmm, BARF, and L2G-NeRF, directly treat camera parameters as learnable and estimate them through differential volume rendering. However, these methods work for forward-looking scenes with slight motions and fail to tackle the rotation scenario in practice. To overcome this limitation, we propose a novel \underline{c}amera parameter \underline{f}ree neural radiance field (CF-NeRF), which incrementally reconstructs 3D representations and recovers the camera parameters inspired by incremental structure from motion (SfM). Given a sequence of images, CF-NeRF estimates the camera parameters of images one by one and reconstructs the scene through initialization, implicit localization, and implicit optimization. To evaluate our method, we use a challenging real-world dataset NeRFBuster which provides 12 scenes under complex trajectories. Results demonstrate that CF-NeRF is robust to camera rotation and achieves state-of-the-art results without providing prior information and constraints.
Authors: Kian Eng Ong, Sivaji Retta, Ramarajulu Srinivasan, Shawn Tan, Jun Liu
Cattle farming is one of the important and profitable agricultural industries. Employing intelligent automated precision livestock farming systems that can count animals, track the animals and their poses will raise productivity and significantly reduce the heavy burden on its already limited labor pool. To achieve such intelligent systems, a large cattle video dataset is essential in developing and training such models. However, many current animal datasets are tailored to few tasks or other types of animals, which result in poorer model performance when applied to cattle. Moreover, they do not provide top-down views of cattle. To address such limitations, we introduce CattleEyeView dataset, the first top-down view multi-task cattle video dataset for a variety of inter-related tasks (i.e., counting, detection, pose estimation, tracking, instance segmentation) that are useful to count the number of cows and assess their growth and well-being. The dataset contains 753 distinct top-down cow instances in 30,703 frames (14 video sequences). We perform benchmark experiments to evaluate the model's performance for each task. The dataset and codes can be found at https://github.com/AnimalEyeQ/CattleEyeView.
Authors: Marie Bø-Sande, Edvin Benjaminsen, Neel Kanwal, Saul Fuster, Helga Hardardottir, Ingrid Lundal, Emiel A.M. Janssen, Kjersti Engan
Melanoma is a type of cancer that begins in the cells controlling the pigment of the skin, and it is often referred to as the most dangerous skin cancer. Diagnosing melanoma can be time-consuming, and a recent increase in melanoma incidents indicates a growing demand for a more efficient diagnostic process. This paper presents a pipeline for melanoma diagnostics, leveraging two convolutional neural networks, a diagnosis, and a prognosis model. The diagnostic model is responsible for localizing malignant patches across whole slide images and delivering a patient-level diagnosis as malignant or benign. Further, the prognosis model utilizes the diagnostic model's output to provide a patient-level prognosis as good or bad. The full pipeline has an F1 score of 0.79 when tested on data from the same distribution as it was trained on.
Authors: Yibo Zhao, Liang Peng, Yang Yang, Zekai Luo, Hengjia Li, Yao Chen, Wei Zhao, qinglin lu, Wei Liu, Boxi Wu
Diffusion models have exhibited impressive prowess in the text-to-image task. Recent methods add image-level controls, e.g., edge and depth maps, to manipulate the generation process together with text prompts to obtain desired images. This controlling process is globally operated on the entire image, which limits the flexibility of control regions. In this paper, we introduce a new simple yet practical task setting: local control. It focuses on controlling specific local areas according to user-defined image conditions, where the rest areas are only conditioned by the original text prompt. This manner allows the users to flexibly control the image generation in a fine-grained way. However, it is non-trivial to achieve this goal. The naive manner of directly adding local conditions may lead to the local control dominance problem. To mitigate this problem, we propose a training-free method that leverages the updates of noised latents and parameters in the cross-attention map during the denosing process to promote concept generation in non-control areas. Moreover, we use feature mask constraints to mitigate the degradation of synthesized image quality caused by information differences inside and outside the local control area. Extensive experiments demonstrate that our method can synthesize high-quality images to the prompt under local control conditions. Code is available at https://github.com/YibooZhao/Local-Control.
Authors: Osmar Luiz Ferreira de Carvalho, Osmar Abilio de Carvalho Junior, Anesmar Olino de Albuquerque, Daniel Guerreiro e Silva
Offshore wind farms represent a renewable energy source with a significant global growth trend, and their monitoring is strategic for territorial and environmental planning. This study's primary objective is to detect offshore wind plants at an instance level using semantic segmentation models and Sentinel-1 time series. The secondary objectives are: (a) to develop a database consisting of labeled data and S-1 time series; (b) to compare the performance of five deep semantic segmentation architectures (U-Net, U-Net++, Feature Pyramid Network - FPN, DeepLabv3+, and LinkNet); (c) develop a novel augmentation strategy that shuffles the positions of the images within the time series; (d) investigate different dimensions of time series intervals (1, 5, 10, and 15 images); and (e) evaluate the semantic-to-instance conversion procedure. LinkNet was the top-performing model, followed by U-Net++ and U-Net, while FPN and DeepLabv3+ presented the worst results. The evaluation of semantic segmentation models reveals enhanced Intersection over Union (IoU) (25%) and F-score metrics (18%) with the augmentation of time series images. The study showcases the augmentation strategy's capability to mitigate biases and precisely detect invariant targets. Furthermore, the conversion from semantic to instance segmentation demonstrates its efficacy in accurately isolating individual instances within classified regions - simplifying training data and reducing annotation effort and complexity.
Authors: Tangfei Liao, Xiaoqin Zhang, Li Zhao, Tao Wang, Guobao Xiao
Correspondence pruning aims to find correct matches (inliers) from an initial set of putative correspondences, which is a fundamental task for many applications. The process of finding is challenging, given the varying inlier ratios between scenes/image pairs due to significant visual differences. However, the performance of the existing methods is usually limited by the problem of lacking visual cues (\eg texture, illumination, structure) of scenes. In this paper, we propose a Visual-Spatial Fusion Transformer (VSFormer) to identify inliers and recover camera poses accurately. Firstly, we obtain highly abstract visual cues of a scene with the cross attention between local features of two-view images. Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning. Additionally, to mine the consistency of correspondences, we also design a novel module that combines the KNN-based graph and the transformer, effectively capturing both local and global contexts. Extensive experiments have demonstrated that the proposed VSFormer outperforms state-of-the-art methods on outdoor and indoor benchmarks.
Authors: Yafei Hu, Quanting Xie, Vidhi Jain, Jonathan Francis, Jay Patrikar, Nikhil Keetha, Seungchan Kim, Yaqi Xie, Tianyi Zhang, Zhibo Zhao, Yu-Quan Chong, Chen Wang, Katia Sycara, Matthew Johnson-Roberson, Dhruv Batra, Xiaolong Wang, Sebastian Scherer, Zsolt Kira, Fei Xia, Yonatan Bisk
Building general-purpose robots that can operate seamlessly, in any environment, with any object, and utilizing various skills to complete diverse tasks has been a long-standing goal in Artificial Intelligence. Unfortunately, however, most existing robotic systems have been constrained - having been designed for specific tasks, trained on specific datasets, and deployed within specific environments. These systems usually require extensively-labeled data, rely on task-specific models, have numerous generalization issues when deployed in real-world scenarios, and struggle to remain robust to distribution shifts. Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i.e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of robotics, and also exploring (ii) what a robotics-specific foundation model would look like. We begin by providing an overview of what constitutes a conventional robotic system and the fundamental barriers to making it universally applicable. Next, we establish a taxonomy to discuss current work exploring ways to leverage existing foundation models for robotics and develop ones catered to robotics. Finally, we discuss key challenges and promising future directions in using foundation models for enabling general-purpose robotic systems. We encourage readers to view our ``living`` GitHub repository of resources, including papers reviewed in this survey as well as related projects and repositories for developing foundation models for robotics.
Authors: Marcos Barcina-Blanco, Jesus L. Lobo, Pablo Garcia-Bringas, Javier Del Ser
In real-world scenarios classification models are often required to perform robustly when predicting samples belonging to classes that have not appeared during its training stage. Open Set Recognition addresses this issue by devising models capable of detecting unknown classes from samples arriving during the testing phase, while maintaining a good level of performance in the classification of samples belonging to known classes. This review comprehensively overviews the recent literature related to Open Set Recognition, identifying common practices, limitations, and connections of this field with other machine learning research areas, such as continual learning, out-of-distribution detection, novelty detection, and uncertainty estimation. Our work also uncovers open problems and suggests several research directions that may motivate and articulate future efforts towards more safe Artificial Intelligence methods.
Authors: Ronja Güldenring, Rasmus Eckholdt Andersen, Lazaros Nalpantidis
Robot perception is far from what humans are capable of. Humans do not only have a complex semantic scene understanding but also extract fine-grained intra-object properties for the salient ones. When humans look at plants, they naturally perceive the plant architecture with its individual leaves and branching system. In this work, we want to advance the granularity in plant understanding for agricultural precision robots. We develop a model to extract fine-grained phenotypic information, such as leaf-, stem-, and vein instances. The underlying dataset RumexLeaves is made publicly available and is the first of its kind with keypoint-guided polyline annotations leading along the line from the lowest stem point along the leaf basal to the leaf apex. Furthermore, we introduce an adapted metric POKS complying with the concept of keypoint-guided polylines. In our experimental evaluation, we provide baseline results for our newly introduced dataset while showcasing the benefits of POKS over OKS.
Authors: Zhaochen Li, Fengheng Li, Wei Feng, Honghe Zhu, An Liu, Yaoyu Li, Zheng Zhang, Jingjing Lv, Xin Zhu, Junjie Shen, Zhangang Lin, Jingping Shao, Zhenglu Yang
End-to-end product poster generation significantly optimizes design efficiency and reduces production costs. Prevailing methods predominantly rely on image-inpainting methods to generate clean background images for given products. Subsequently, poster layout generation methods are employed to produce corresponding layout results. However, the background images may not be suitable for accommodating textual content due to their complexity, and the fixed location of products limits the diversity of layout results. To alleviate these issues, we propose a novel product poster generation framework named P\&R. The P\&R draws inspiration from the workflow of designers in creating posters, which consists of two stages: Planning and Rendering. At the planning stage, we propose a PlanNet to generate the layout of the product and other visual components considering both the appearance features of the product and semantic features of the text, which improves the diversity and rationality of the layouts. At the rendering stage, we propose a RenderNet to generate the background for the product while considering the generated layout, where a spatial fusion module is introduced to fuse the layout of different visual components. To foster the advancement of this field, we propose the first end-to-end product poster generation dataset PPG30k, comprising 30k exquisite product poster images along with comprehensive image and text annotations. Our method outperforms the state-of-the-art product poster generation methods on PPG30k. The PPG30k will be released soon.
Authors: Vincent Tao Hu, Yunlu Chen, Mathilde Caron, Yuki M. Asano, Cees G. M. Snoek, Bjorn Ommer
Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like DINO. However, recent studies have revealed that the feature representation derived from diffusion model itself is discriminative for numerous downstream tasks as well, which prompts us to propose a framework to extract guidance from, and specifically for, diffusion models. Our research has yielded several significant contributions. Firstly, the guidance signals from diffusion models are on par with those from class-conditioned diffusion models. Secondly, feature regularization, when based on the Sinkhorn-Knopp algorithm, can further enhance feature discriminability in comparison to unconditional diffusion models. Thirdly, we have constructed an online training approach that can concurrently derive guidance from diffusion models for diffusion models. Lastly, we have extended the application of diffusion models along the constant velocity path of ODE to achieve a more favorable balance between sampling steps and fidelity. The performance of our methods has been outstanding, outperforming related baseline comparisons in large-resolution datasets, such as ImageNet256, ImageNet256-100 and LSUN-Churches. Our code will be released.
Authors: Qibo Chen, Weizhong Jin, Shuchang Li, Mengdi Liu, Li Yu, Jian Jiang, Xiaozheng Wang
Text prompts are crucial for generalizing pre-trained open-set object detection models to new categories. However, current methods for text prompts are limited as they require manual feedback when generalizing to new categories, which restricts their ability to model complex scenes, often leading to incorrect detection results. To address this limitation, we propose a novel visual prompt method that learns new category knowledge from a few labeled images, which generalizes the pre-trained detection model to the new category. To allow visual prompts to represent new categories adequately, we propose a statistical-based prompt construction module that is not limited by predefined vocabulary lengths, thus allowing more vectors to be used when representing categories. We further utilize the category dictionaries in the pre-training dataset to design task-specific similarity dictionaries, which make visual prompts more discriminative. We evaluate the method on the ODinW dataset and show that it outperforms existing prompt learning methods and performs more consistently in combinatorial inference.
Authors: Keywoong Bae, Suan Lee, Wookey Lee
In our contemporary academic inquiry, we present "Diffusion-C," a foundational methodology to analyze the generative restrictions of Diffusion Models, particularly those akin to GANs, DDPM, and DDIM. By employing input visual data that has been subjected to a myriad of corruption modalities and intensities, we elucidate the performance characteristics of those Diffusion Models. The noise component takes center stage in our analysis, hypothesized to be a pivotal element influencing the mechanics of deep learning systems. In our rigorous expedition utilizing Diffusion-C, we have discerned the following critical observations: (I) Within the milieu of generative models under the Diffusion taxonomy, DDPM emerges as a paragon, consistently exhibiting superior performance metrics. (II) Within the vast spectrum of corruption frameworks, the fog and fractal corruptions notably undermine the functional robustness of both DDPM and DDIM. (III) The vulnerability of Diffusion Models to these particular corruptions is significantly influenced by topological and statistical similarities, particularly concerning the alignment between mean and variance. This scholarly work highlights Diffusion-C's core understandings regarding the impacts of various corruptions, setting the stage for future research endeavors in the realm of generative models.
Authors: Chaoya Jiang, Wei ye, Haiyang Xu, Qinghao Ye, Ming Yan, Ji Zhang, Shikun Zhang
Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up training data volume in SMCL presents considerable obstacles in terms of computational cost and data inefficiency. To improve data efficiency in VLP, we propose Text-aware Image Mixing (TiMix), which integrates mix-based data augmentation techniques into SMCL, yielding significant performance improvements without significantly increasing computational overhead. We provide a theoretical analysis of TiMixfrom a mutual information (MI) perspective, showing that mixed data samples for cross-modal contrastive learning implicitly serve as a regularizer for the contrastive loss. The experimental results demonstrate that TiMix exhibits a comparable performance on downstream tasks, even with a reduced amount of training data and shorter training time, when benchmarked against existing methods. This work empirically and theoretically demonstrates the potential of data mixing for data-efficient and computationally viable VLP, benefiting broader VLP model adoption in practical scenarios.
Authors: Runwei Guan, Haocheng Zhao, Shanliang Yao, Ka Lok Man, Xiaohui Zhu, Limin Yu, Yong Yue, Jeremy Smith, Eng Gee Lim, Weiping Ding, Yutao Yue
Urban water-surface robust perception serves as the foundation for intelligent monitoring of aquatic environments and the autonomous navigation and operation of unmanned vessels, especially in the context of waterway safety. It is worth noting that current multi-sensor fusion and multi-task learning models consume substantial power and heavily rely on high-power GPUs for inference. This contributes to increased carbon emissions, a concern that runs counter to the prevailing emphasis on environmental preservation and the pursuit of sustainable, low-carbon urban environments. In light of these concerns, this paper concentrates on low-power, lightweight, multi-task panoptic perception through the fusion of visual and 4D radar data, which is seen as a promising low-cost perception method. We propose a framework named Achelous++ that facilitates the development and comprehensive evaluation of multi-task water-surface panoptic perception models. Achelous++ can simultaneously execute five perception tasks with high speed and low power consumption, including object detection, object semantic segmentation, drivable-area segmentation, waterline segmentation, and radar point cloud semantic segmentation. Furthermore, to meet the demand for developers to customize models for real-time inference on low-performance devices, a novel multi-modal pruning strategy known as Heterogeneous-Aware SynFlow (HA-SynFlow) is proposed. Besides, Achelous++ also supports random pruning at initialization with different layer-wise sparsity, such as Uniform and Erdos-Renyi-Kernel (ERK). Overall, our Achelous++ framework achieves state-of-the-art performance on the WaterScenes benchmark, excelling in both accuracy and power efficiency compared to other single-task and multi-task models. We release and maintain the code at https://github.com/GuanRunwei/Achelous.
Authors: Xinyi Liu, Qian Zhao, Jie Liang, Hui Zeng, Deyu Meng, Lei Zhang
Guided image restoration (GIR), such as guided depth map super-resolution and pan-sharpening, aims to enhance a target image using guidance information from another image of the same scene. Currently, joint image filtering-inspired deep learning-based methods represent the state-of-the-art for GIR tasks. Those methods either deal with GIR in an end-to-end way by elaborately designing filtering-oriented deep neural network (DNN) modules, focusing on the feature-level fusion of inputs; or explicitly making use of the traditional joint filtering mechanism by parameterizing filtering coefficients with DNNs, working on image-level fusion. The former ones are good at recovering contextual information but tend to lose fine-grained details, while the latter ones can better retain textual information but might lead to content distortions. In this work, to inherit the advantages of both methodologies while mitigating their limitations, we proposed a Simultaneous Feature and Image Guided Fusion (SFIGF) network, that simultaneously considers feature and image-level guided fusion following the guided filter (GF) mechanism. In the feature domain, we connect the cross-attention (CA) with GF, and propose a GF-inspired CA module for better feature-level fusion; in the image domain, we fully explore the GF mechanism and design GF-like structure for better image-level fusion. Since guided fusion is implemented in both feature and image domains, the proposed SFIGF is expected to faithfully reconstruct both contextual and textual information from sources and thus lead to better GIR results. We apply SFIGF to 4 typical GIR tasks, and experimental results on these tasks demonstrate its effectiveness and general availability.
Authors: Chen Feng, Duolikun Danier, Fan Zhang, David Bull
Professionally generated content (PGC) streamed online can contain visual artefacts that degrade the quality of user experience. These artefacts arise from different stages of the streaming pipeline, including acquisition, post-production, compression, and transmission. To better guide streaming experience enhancement, it is important to detect specific artefacts at the user end in the absence of a pristine reference. In this work, we address the lack of a comprehensive benchmark for artefact detection within streamed PGC, via the creation and validation of a large database, BVI-Artefact. Considering the ten most relevant artefact types encountered in video streaming, we collected and generated 480 video sequences, each containing various artefacts with associated binary artefact labels. Based on this new database, existing artefact detection methods are benchmarked, with results showing the challenging nature of this tasks and indicating the requirement of more reliable artefact detection methods. To facilitate further research in this area, we have made BVI-Artifact publicly available at https://chenfeng-bristol.github.io/BVI-Artefact/
Authors: Xueying Wang, Juyong Zhang
Recently, the reconstruction of high-fidelity 3D head models from static portrait image has made great progress. However, most methods require multi-view or multi-illumination information, which therefore put forward high requirements for data acquisition. In this paper, we study the reconstruction of high-fidelity 3D head models from arbitrary monocular videos. Non-rigid structure from motion (NRSFM) methods have been widely used to solve such problems according to the two-dimensional correspondence between different frames. However, the inaccurate correspondence caused by high-complex hair structures and various facial expression changes would heavily influence the reconstruction accuracy. To tackle these problems, we propose a prior-guided dynamic implicit neural network. Specifically, we design a two-part dynamic deformation field to transform the current frame space to the canonical one. We further model the head geometry in the canonical space with a learnable signed distance field (SDF) and optimize it using the volumetric rendering with the guidance of two-main head priors to improve the reconstruction accuracy and robustness. Extensive ablation studies and comparisons with state-of-the-art methods demonstrate the effectiveness and robustness of our proposed method.
Authors: Chen Feng, Duolikun Danier, Haoran Wang, Fan Zhang, David Bull
Deep learning-based video quality assessment (deep VQA) has demonstrated significant potential in surpassing conventional metrics, with promising improvements in terms of correlation with human perception. However, the practical deployment of such deep VQA models is often limited due to their high computational complexity and large memory requirements. To address this issue, we aim to significantly reduce the model size and runtime of one of the state-of-the-art deep VQA methods, RankDVQA, by employing a two-phase workflow that integrates pruning-driven model compression with multi-level knowledge distillation. The resulting lightweight quality metric, RankDVQA-mini, requires less than 10% of the model parameters compared to its full version (14% in terms of FLOPs), while still retaining a quality prediction performance that is superior to most existing deep VQA methods. The source code of the RankDVQA-mini has been released at https://chenfeng-bristol.github.io/RankDVQA-mini/ for public evaluation.
Authors: Zhiyue Liu, Jinyuan Liu, Fanrong Ma
Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the CLIP's cross-modal association ability for image captioning, relying solely on textual information under unsupervised settings. However, not only does a modality gap exist between CLIP text and image features, but a discrepancy also arises between training and inference due to the unavailability of real-world images, which hinders the cross-modal alignment in text-only captioning. This paper proposes a novel method to address these issues by incorporating synthetic image-text pairs. A pre-trained text-to-image model is deployed to obtain images that correspond to textual data, and the pseudo features of generated images are optimized toward the real ones in the CLIP embedding space. Furthermore, textual information is gathered to represent image features, resulting in the image features with various semantics and the bridged modality gap. To unify training and inference, synthetic image features would serve as the training prefix for the language decoder, while real images are used for inference. Additionally, salient objects in images are detected as assistance to enhance the learning of modality alignment. Experimental results demonstrate that our method obtains the state-of-the-art performance on benchmark datasets.
Authors: Hao Shao, Quansheng Zeng, Qibin Hou, Jufeng Yang
Efficiently capturing multi-scale information and building long-range dependencies among pixels are essential for medical image segmentation because of the various sizes and shapes of the lesion regions or organs. In this paper, we present Multi-scale Cross-axis Attention (MCA) to solve the above challenging issues based on the efficient axial attention. Instead of simply connecting axial attention along the horizontal and vertical directions sequentially, we propose to calculate dual cross attentions between two parallel axial attentions to capture global information better. To process the significant variations of lesion regions or organs in individual sizes and shapes, we also use multiple convolutions of strip-shape kernels with different kernel sizes in each axial attention path to improve the efficiency of the proposed MCA in encoding spatial information. We build the proposed MCA upon the MSCAN backbone, yielding our network, termed MCANet. Our MCANet with only 4M+ parameters performs even better than most previous works with heavy backbones (e.g., Swin Transformer) on four challenging tasks, including skin lesion segmentation, nuclei segmentation, abdominal multi-organ segmentation, and polyp segmentation. Code is available at https:// github.com/ haoshao-nku/ medical seg.git.
Authors: Chengfeng Zhao, Juze Zhang, Jiashen Du, Ziwei Shan, Junye Wang, Jingyi Yu, Jingya Wang, Lan Xu
We are living in a world surrounded by diverse and "smart" devices with rich modalities of sensing ability. Conveniently capturing the interactions between us humans and these objects remains far-reaching. In this paper, we present I'm-HOI, a monocular scheme to faithfully capture the 3D motions of both the human and object in a novel setting: using a minimal amount of RGB camera and object-mounted Inertial Measurement Unit (IMU). It combines general motion inference and category-aware refinement. For the former, we introduce a holistic human-object tracking method to fuse the IMU signals and the RGB stream and progressively recover the human motions and subsequently the companion object motions. For the latter, we tailor a category-aware motion diffusion model, which is conditioned on both the raw IMU observations and the results from the previous stage under over-parameterization representation. It significantly refines the initial results and generates vivid body, hand, and object motions. Moreover, we contribute a large dataset with ground truth human and object motions, dense RGB inputs, and rich object-mounted IMU measurements. Extensive experiments demonstrate the effectiveness of I'm-HOI under a hybrid capture setting. Our dataset and code will be released to the community.
Authors: Fan Ma, Xiaojie Jin, Heng Wang, Yuchen Xian, Jiashi Feng, Yi Yang
Recent advances in large video-language models have displayed promising outcomes in video comprehension. Current approaches straightforwardly convert video into language tokens and employ large language models for multi-modal tasks. However, this method often leads to the generation of irrelevant content, commonly known as "hallucination", as the length of the text increases and the impact of the video diminishes. To address this problem, we propose Vista-LLaMA, a novel framework that maintains the consistent distance between all visual tokens and any language tokens, irrespective of the generated text length. Vista-LLaMA omits relative position encoding when determining attention weights between visual and text tokens, retaining the position encoding for text and text tokens. This amplifies the effect of visual tokens on text generation, especially when the relative distance is longer between visual and text tokens. The proposed attention mechanism significantly reduces the chance of producing irrelevant text related to the video content. Furthermore, we present a sequential visual projector that projects the current video frame into tokens of language space with the assistance of the previous frame. This approach not only captures the temporal relationship within the video, but also allows less visual tokens to encompass the entire video. Our approach significantly outperforms various previous methods (e.g., Video-ChatGPT, MovieChat) on four challenging open-ended video question answering benchmarks. We reach an accuracy of 60.7 on the zero-shot NExT-QA and 60.5 on the zero-shot MSRVTT-QA, setting a new state-of-the-art performance. This project is available at https://jinxxian.github.io/Vista-LLaMA.
Authors: Jian Shi, Peter Wonka
We present \textit{VoxelKP}, a novel fully sparse network architecture tailored for human keypoint estimation in LiDAR data. The key challenge is that objects are distributed sparsely in 3D space, while human keypoint detection requires detailed local information wherever humans are present. We propose four novel ideas in this paper. First, we propose sparse selective kernels to capture multi-scale context. Second, we introduce sparse box-attention to focus on learning spatial correlations between keypoints within each human instance. Third, we incorporate a spatial encoding to leverage absolute 3D coordinates when projecting 3D voxels to a 2D grid encoding a bird's eye view. Finally, we propose hybrid feature learning to combine the processing of per-voxel features with sparse convolution. We evaluate our method on the Waymo dataset and achieve an improvement of $27\%$ on the MPJPE metric compared to the state-of-the-art, \textit{HUM3DIL}, trained on the same data, and $12\%$ against the state-of-the-art, \textit{GC-KPL}, pretrained on a $25\times$ larger dataset. To the best of our knowledge, \textit{VoxelKP} is the first single-staged, fully sparse network that is specifically designed for addressing the challenging task of 3D keypoint estimation from LiDAR data, achieving state-of-the-art performances. Our code is available at \url{https://github.com/shijianjian/VoxelKP}.
Authors: Jiafeng Mao, Xueting Wang, Kiyoharu Aizawa
The initial noise image has demonstrated a significant influence on image generation, and manipulating the initial noise image can effectively increase control over the generation. All of the current generation is based only on a single initial noise drawn from a normal distribution, which may not be suited to the desired content specified by the prompt. In this research, we propose a novel approach using pre-collected, semantically-informed pixel blocks from multiple initial noises for the initial image construction to enhance control over the image generation. The inherent tendencies of these pixel blocks can easily generate specific content, thus effectively guiding the generation process towards the desired content. The pursuit of tailored initial image construction inevitably leads to deviations from the normal distribution, and our experimental results show that the diffusion model exhibits a certain degree of tolerance towards the distribution of initial images. Our approach achieves state-of-the-art performance in the training-free layout-to-image synthesis task, demonstrating the adaptability of the initial image construction in guiding the content of the generated image. Our code will be made publicly available.
Authors: Haoming Liu, Yuanhe Guo, Shengjie Wang, Hongyi Wen
Diffusion models excel at generating high-quality images and are easy to extend, making them extremely popular among active users who have created an extensive collection of diffusion models with various styles by fine-tuning base models such as Stable Diffusion. Recent work has focused on uncovering semantic and visual information encoded in various components of a diffusion model, enabling better generation quality and more fine-grained control. However, those methods target improving a single model and overlook the vastly available collection of fine-tuned diffusion models. In this work, we study the combinations of diffusion models. We propose Diffusion Cocktail (Ditail), a training-free method that can accurately transfer content information between two diffusion models. This allows us to perform diverse generations using a set of diffusion models, resulting in novel images that are unlikely to be obtained by a single model alone. We also explore utilizing Ditail for style transfer, with the target style set by a diffusion model instead of an image. Ditail offers a more detailed manipulation of the diffusion generation, thereby enabling the vast community to integrate various styles and contents seamlessly and generate any content of any style.
Authors: Dongchen Han, Tianzhu Ye, Yizeng Han, Zhuofan Xia, Shiji Song, Gao Huang
The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel attention paradigm, Agent Attention, to strike a favorable balance between computational efficiency and representation power. Specifically, the Agent Attention, denoted as a quadruple $(Q, A, K, V)$, introduces an additional set of agent tokens $A$ into the conventional attention module. The agent tokens first act as the agent for the query tokens $Q$ to aggregate information from $K$ and $V$, and then broadcast the information back to $Q$. Given the number of agent tokens can be designed to be much smaller than the number of query tokens, the agent attention is significantly more efficient than the widely adopted Softmax attention, while preserving global context modelling capability. Interestingly, we show that the proposed agent attention is equivalent to a generalized form of linear attention. Therefore, agent attention seamlessly integrates the powerful Softmax attention and the highly efficient linear attention. Extensive experiments demonstrate the effectiveness of agent attention with various vision Transformers and across diverse vision tasks, including image classification, object detection, semantic segmentation and image generation. Notably, agent attention has shown remarkable performance in high-resolution scenarios, owning to its linear attention nature. For instance, when applied to Stable Diffusion, our agent attention accelerates generation and substantially enhances image generation quality without any additional training. Code is available at https://github.com/LeapLabTHU/Agent-Attention.
Authors: Jayeon Yoo, Dongkwan Lee, Inseop Chung, Donghyun Kim, Nojun Kwak
It is a well-known fact that the performance of deep learning models deteriorates when they encounter a distribution shift at test time. Test-time adaptation (TTA) algorithms have been proposed to adapt the model online while inferring test data. However, existing research predominantly focuses on classification tasks through the optimization of batch normalization layers or classification heads, but this approach limits its applicability to various model architectures like Transformers and makes it challenging to apply to other tasks, such as object detection. In this paper, we propose a novel online adaption approach for object detection in continually changing test domains, considering which part of the model to update, how to update it, and when to perform the update. By introducing architecture-agnostic and lightweight adaptor modules and only updating these while leaving the pre-trained backbone unchanged, we can rapidly adapt to new test domains in an efficient way and prevent catastrophic forgetting. Furthermore, we present a practical and straightforward class-wise feature aligning method for object detection to resolve domain shifts. Additionally, we enhance efficiency by determining when the model is sufficiently adapted or when additional adaptation is needed due to changes in the test distribution. Our approach surpasses baselines on widely used benchmarks, achieving improvements of up to 4.9\%p and 7.9\%p in mAP for COCO $\rightarrow$ COCO-corrupted and SHIFT, respectively, while maintaining about 20 FPS or higher.
Authors: Hu Zhang, Jianhua Xu, Tao Tang, Haiyang Sun, Xin Yu, Zi Huang, Kaicheng Yu
Traditional LiDAR-based object detection research primarily focuses on closed-set scenarios, which falls short in complex real-world applications. Directly transferring existing 2D open-vocabulary models with some known LiDAR classes for open-vocabulary ability, however, tends to suffer from over-fitting problems: The obtained model will detect the known objects, even presented with a novel category. In this paper, we propose OpenSight, a more advanced 2D-3D modeling framework for LiDAR-based open-vocabulary detection. OpenSight utilizes 2D-3D geometric priors for the initial discernment and localization of generic objects, followed by a more specific semantic interpretation of the detected objects. The process begins by generating 2D boxes for generic objects from the accompanying camera images of LiDAR. These 2D boxes, together with LiDAR points, are then lifted back into the LiDAR space to estimate corresponding 3D boxes. For better generic object perception, our framework integrates both temporal and spatial-aware constraints. Temporal awareness correlates the predicted 3D boxes across consecutive timestamps, recalibrating the missed or inaccurate boxes. The spatial awareness randomly places some ``precisely'' estimated 3D boxes at varying distances, increasing the visibility of generic objects. To interpret the specific semantics of detected objects, we develop a cross-modal alignment and fusion module to first align 3D features with 2D image embeddings and then fuse the aligned 3D-2D features for semantic decoding. Our experiments indicate that our method establishes state-of-the-art open-vocabulary performance on widely used 3D detection benchmarks and effectively identifies objects for new categories of interest.
Authors: Ayoub Arous, Andres F Lopez-Lopera, Nael Abu-Ghazaleh, Ihsen Alouani
In this paper, we investigate the following question: Can we obtain adversarially-trained models without training on adversarial examples? Our intuition is that training a model with inherent stochasticity, i.e., optimizing the parameters by minimizing a stochastic loss function, yields a robust expectation function that is non-stochastic. In contrast to related methods that introduce noise at the input level, our proposed approach incorporates inherent stochasticity by embedding Gaussian noise within the layers of the NN model at training time. We model the propagation of noise through the layers, introducing a closed-form stochastic loss function that encapsulates a noise variance parameter. Additionally, we contribute a formalized noise-aware gradient, enabling the optimization of model parameters while accounting for stochasticity. Our experimental results confirm that the expectation model of a stochastic architecture trained on benign distribution is adversarially robust. Interestingly, we find that the impact of the applied Gaussian noise's standard deviation on both robustness and baseline accuracy closely mirrors the impact of the noise magnitude employed in adversarial training. Our work contributes adversarially trained networks using a completely different approach, with empirically similar robustness to adversarial training.
Authors: Qinglong Cao, Zhengqin Xu, Yuntian Chen, Chao Ma, Xiaokang Yang
Prompt learning has emerged as an effective and data-efficient technique in large Vision-Language Models (VLMs). However, when adapting VLMs to specialized domains such as remote sensing and medical imaging, domain prompt learning remains underexplored. While large-scale domain-specific foundation models can help tackle this challenge, their concentration on a single vision level makes it challenging to prompt both vision and language modalities. To overcome this, we propose to leverage domain-specific knowledge from domain-specific foundation models to transfer the robust recognition ability of VLMs from generalized to specialized domains, using quaternion networks. Specifically, the proposed method involves using domain-specific vision features from domain-specific foundation models to guide the transformation of generalized contextual embeddings from the language branch into a specialized space within the quaternion networks. Moreover, we present a hierarchical approach that generates vision prompt features by analyzing intermodal relationships between hierarchical language prompt features and domain-specific vision features. In this way, quaternion networks can effectively mine the intermodal relationships in the specific domain, facilitating domain-specific vision-language contrastive learning. Extensive experiments on domain-specific datasets show that our proposed method achieves new state-of-the-art results in prompt learning.
Authors: Patrik Vacek, David Hurych, Karel Zimmermann, Patrick Perez, Tomas Svoboda
Learning without supervision how to predict 3D scene flows from point clouds is central to many vision systems. We propose a novel learning framework for this task which improves the necessary regularization. Relying on the assumption that scene elements are mostly rigid, current smoothness losses are built on the definition of ``rigid clusters" in the input point clouds. The definition of these clusters is challenging and has a major impact on the quality of predicted flows. We introduce two new consistency losses that enlarge clusters while preventing them from spreading over distinct objects. In particular, we enforce \emph{temporal} consistency with a forward-backward cyclic loss and \emph{spatial} consistency by considering surface orientation similarity in addition to spatial proximity. The proposed losses are model-independent and can thus be used in a plug-and-play fashion to significantly improve the performance of existing models, as demonstrated on two top-performing ones. We also showcase the effectiveness and generalization capability of our framework on four standard sensor-unique driving datasets, achieving state-of-the-art performance in 3D scene flow estimation. Our codes are available anonymously on \url{https://github.com/vacany/sac-flow}.
Authors: Mingjian Zhu, Hanting Chen, Mouxiao Huang, Wei Li, Hailin Hu, Jie Hu, Yunhe Wang
The misuse of AI imagery can have harmful societal effects, prompting the creation of detectors to combat issues like the spread of fake news. Existing methods can effectively detect images generated by seen generators, but it is challenging to detect those generated by unseen generators. They do not concentrate on amplifying the output discrepancy when detectors process real versus fake images. This results in a close output distribution of real and fake samples, increasing classification difficulty in detecting unseen generators. This paper addresses the unseen-generator detection problem by considering this task from the perspective of anomaly detection and proposes an adversarial teacher-student discrepancy-aware framework. Our method encourages smaller output discrepancies between the student and the teacher models for real images while aiming for larger discrepancies for fake images. We employ adversarial learning to train a feature augmenter, which promotes smaller discrepancies between teacher and student networks when the inputs are fake images. Our method has achieved state-of-the-art on public benchmarks, and the visualization results show that a large output discrepancy is maintained when faced with various types of generators.
Authors: Hang Guo, Tao Dai, Yuanchao Bai, Bin Chen, Shu-Tao Xia, Zexuan Zhu
Pre-training has shown promising results on various image restoration tasks, which is usually followed by full fine-tuning for each specific downstream task (e.g., image denoising). However, such full fine-tuning usually suffers from the problems of heavy computational cost in practice, due to the massive parameters of pre-trained restoration models, thus limiting its real-world applications. Recently, Parameter Efficient Transfer Learning (PETL) offers an efficient alternative solution to full fine-tuning, yet still faces great challenges for pre-trained image restoration models, due to the diversity of different degradations. To address these issues, we propose AdaptIR, a novel parameter efficient transfer learning method for adapting pre-trained restoration models. Specifically, the proposed method consists of a multi-branch inception structure to orthogonally capture local spatial, global spatial, and channel interactions. In this way, it allows powerful representations under a very low parameter budget. Extensive experiments demonstrate that the proposed method can achieve comparable or even better performance than full fine-tuning, while only using 0.6% parameters. Code is available at https://github.com/csguoh/AdaptIR.
Authors: Shuzhou Yang, Chong Mou, Jiwen Yu, Yuhan Wang, Xiandong Meng, Jian Zhang
Diffusion models have revolutionized text-driven video editing. However, applying these methods to real-world editing encounters two significant challenges: (1) the rapid increase in graphics memory demand as the number of frames grows, and (2) the inter-frame inconsistency in edited videos. To this end, we propose NVEdit, a novel text-driven video editing framework designed to mitigate memory overhead and improve consistent editing for real-world long videos. Specifically, we construct a neural video field, powered by tri-plane and sparse grid, to enable encoding long videos with hundreds of frames in a memory-efficient manner. Next, we update the video field through off-the-shelf Text-to-Image (T2I) models to impart text-driven editing effects. A progressive optimization strategy is developed to preserve original temporal priors. Importantly, both the neural video field and T2I model are adaptable and replaceable, thus inspiring future research. Experiments demonstrate that our approach successfully edits hundreds of frames with impressive inter-frame consistency.
Authors: Xuanyu Zhang, Runyi Li, Jiwen Yu, Youmin Xu, Weiqi Li, Jian Zhang
In the era where AI-generated content (AIGC) models can produce stunning and lifelike images, the lingering shadow of unauthorized reproductions and malicious tampering poses imminent threats to copyright integrity and information security. Current image watermarking methods, while widely accepted for safeguarding visual content, can only protect copyright and ensure traceability. They fall short in localizing increasingly realistic image tampering, potentially leading to trust crises, privacy violations, and legal disputes. To solve this challenge, we propose an innovative proactive forensics framework EditGuard, to unify copyright protection and tamper-agnostic localization, especially for AIGC-based editing methods. It can offer a meticulous embedding of imperceptible watermarks and precise decoding of tampered areas and copyright information. Leveraging our observed fragility and locality of image-into-image steganography, the realization of EditGuard can be converted into a united image-bit steganography issue, thus completely decoupling the training process from the tampering types. Extensive experiments demonstrate that our EditGuard balances the tamper localization accuracy, copyright recovery precision, and generalizability to various AIGC-based tampering methods, especially for image forgery that is difficult for the naked eye to detect. The project page is available at https://xuanyuzhang21.github.io/project/editguard/.
Authors: Qihang Zhang, Chaoyang Wang, Aliaksandr Siarohin, Peiye Zhuang, Yinghao Xu, Ceyuan Yang, Dahua Lin, Bolei Zhou, Sergey Tulyakov, Hsin-Ying Lee
We are witnessing significant breakthroughs in the technology for generating 3D objects from text. Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. Generating entire scenes, however, remains very challenging as a scene contains multiple 3D objects, diverse and scattered. In this work, we introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text. We marry the locality of objects with globality of scenes by introducing a hybrid 3D representation: explicit for objects and implicit for scenes. Remarkably, an object, being represented explicitly, can be either generated from text using conventional text-to-3D approaches, or provided by users. To configure the layout of the scene and automatically place objects, we apply the Particle Swarm Optimization technique during the optimization process. Furthermore, it is difficult for certain parts of the scene (e.g., corners, occlusion) to receive multi-view supervision, leading to inferior geometry. We incorporate an RGBD panorama diffusion model to mitigate it, resulting in high-quality geometry. Extensive evaluation supports that our approach achieves superior quality over previous approaches, enabling the generation of detailed and view-consistent 3D scenes.
Authors: Yuzhe Zhang, Jiawei Zhang, Hao Li, Zhouxia Wang, Luwei Hou, Dongqing Zou, Liheng Bian
Recovering degraded low-resolution text images is challenging, especially for Chinese text images with complex strokes and severe degradation in real-world scenarios. Ensuring both text fidelity and style realness is crucial for high-quality text image super-resolution. Recently, diffusion models have achieved great success in natural image synthesis and restoration due to their powerful data distribution modeling abilities and data generation capabilities. In this work, we propose an Image Diffusion Model (IDM) to restore text images with realistic styles. For diffusion models, they are not only suitable for modeling realistic image distribution but also appropriate for learning text distribution. Since text prior is important to guarantee the correctness of the restored text structure according to existing arts, we also propose a Text Diffusion Model (TDM) for text recognition which can guide IDM to generate text images with correct structures. We further propose a Mixture of Multi-modality module (MoM) to make these two diffusion models cooperate with each other in all the diffusion steps. Extensive experiments on synthetic and real-world datasets demonstrate that our Diffusion-based Blind Text Image Super-Resolution (DiffTSR) can restore text images with more accurate text structures as well as more realistic appearances simultaneously.
Authors: Weilong Chai, DanDan Zheng, Jiajiong Cao, Zhiquan Chen, Changbao Wang, Chenguang Ma
Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Though many acceleration methods have been proposed, they suffer from generation quality degradation or extra training cost generalizing to new fine-tuned models. To address these limitations, we propose a novel and universal Stable-Diffusion (SD) acceleration module called SpeedUpNet(SUN). SUN can be directly plugged into various fine-tuned SD models without extra training. This technique utilizes cross-attention layers to learn the relative offsets in the generated image results between negative and positive prompts achieving classifier-free guidance distillation with negative prompts controllable, and introduces a Multi-Step Consistency (MSC) loss to ensure a harmonious balance between reducing inference steps and maintaining consistency in the generated output. Consequently, SUN significantly reduces the number of inference steps to just 4 steps and eliminates the need for classifier-free guidance. It leads to an overall speedup of more than 10 times for SD models compared to the state-of-the-art 25-step DPM-solver++, and offers two extra advantages: (1) classifier-free guidance distillation with controllable negative prompts and (2) seamless integration into various fine-tuned Stable-Diffusion models without training. The effectiveness of the SUN has been verified through extensive experimentation. Project Page: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io
Authors: Kyra Ahrens, Hans Hergen Lehmann, Jae Hee Lee, Stefan Wermter
We address the Continual Learning (CL) problem, where a model has to learn a sequence of tasks from non-stationary distributions while preserving prior knowledge as it encounters new experiences. With the advancement of foundation models, CL research has shifted focus from the initial learning-from-scratch paradigm to the use of generic features from large-scale pre-training. However, existing approaches to CL with pre-trained models only focus on separating the class-specific features from the final representation layer and neglect the power of intermediate representations that capture low- and mid-level features naturally more invariant to domain shifts. In this work, we propose LayUP, a new class-prototype-based approach to continual learning that leverages second-order feature statistics from multiple intermediate layers of a pre-trained network. Our method is conceptually simple, does not require any replay buffer, and works out of the box with any foundation model. LayUP improves over the state-of-the-art on four of the seven class-incremental learning settings at a considerably reduced memory and computational footprint compared with the next best baseline. Our results demonstrate that fully exhausting the representational capacities of pre-trained models in CL goes far beyond their final embeddings.
Authors: Yuanyou Xu, Zongxin Yang, Yi Yang
Powered by large-scale text-to-image generation models, text-to-3D avatar generation has made promising progress. However, most methods fail to produce photorealistic results, limited by imprecise geometry and low-quality appearance. Towards more practical avatar generation, we present SEEAvatar, a method for generating photorealistic 3D avatars from text with SElf-Evolving constraints for decoupled geometry and appearance. For geometry, we propose to constrain the optimized avatar in a decent global shape with a template avatar. The template avatar is initialized with human prior and can be updated by the optimized avatar periodically as an evolving template, which enables more flexible shape generation. Besides, the geometry is also constrained by the static human prior in local parts like face and hands to maintain the delicate structures. For appearance generation, we use diffusion model enhanced by prompt engineering to guide a physically based rendering pipeline to generate realistic textures. The lightness constraint is applied on the albedo texture to suppress incorrect lighting effect. Experiments show that our method outperforms previous methods on both global and local geometry and appearance quality by a large margin. Since our method can produce high-quality meshes and textures, such assets can be directly applied in classic graphics pipeline for realistic rendering under any lighting condition. Project page at: https://seeavatar3d.github.io.
Authors: Baoyuan Wu, Shaokui Wei, Mingli Zhu, Meixi Zheng, Zihao Zhu, Mingda Zhang, Hongrui Chen, Danni Yuan, Li Liu, Qingshan Liu
Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some particular cases. This phenomenon poses a serious security threat to the practical application of ML systems, and several advanced attack paradigms have been developed to explore it, mainly including backdoor attacks, weight attacks, and adversarial examples. For each individual attack paradigm, various defense paradigms have been developed to improve the model robustness against the corresponding attack paradigm. However, due to the independence and diversity of these defense paradigms, it is difficult to examine the overall robustness of an ML system against different kinds of attacks.This survey aims to build a systematic review of all existing defense paradigms from a unified perspective. Specifically, from the life-cycle perspective, we factorize a complete machine learning system into five stages, including pre-training, training, post-training, deployment, and inference stages, respectively. Then, we present a clear taxonomy to categorize and review representative defense methods at each individual stage. The unified perspective and presented taxonomies not only facilitate the analysis of the mechanism of each defense paradigm but also help us to understand connections and differences among different defense paradigms, which may inspire future research to develop more advanced, comprehensive defenses.
Authors: Shijie Li, Farhad G. Zanjani, Haitam Ben Yahia, Yuki M. Asano, Juergen Gall, Amirhossein Habibian
Novel View Synthesis (NVS), which tries to produce a realistic image at the target view given source view images and their corresponding poses, is a fundamental problem in 3D Vision. As this task is heavily under-constrained, some recent work, like Zero123, tries to solve this problem with generative modeling, specifically using pre-trained diffusion models. Although this strategy generalizes well to new scenes, compared to neural radiance field-based methods, it offers low levels of flexibility. For example, it can only accept a single-view image as input, despite realistic applications often offering multiple input images. This is because the source-view images and corresponding poses are processed separately and injected into the model at different stages. Thus it is not trivial to generalize the model into multi-view source images, once they are available. To solve this issue, we try to process each pose image pair separately and then fuse them as a unified visual representation which will be injected into the model to guide image synthesis at the target-views. However, inconsistency and computation costs increase as the number of input source-view images increases. To solve these issues, the Multi-view Cross Former module is proposed which maps variable-length input data to fix-size output data. A two-stage training strategy is introduced to further improve the efficiency during training time. Qualitative and quantitative evaluation over multiple datasets demonstrates the effectiveness of the proposed method against previous approaches. The code will be released according to the acceptance.
Authors: Sabri Mustafa Kahya, Muhammet Sami Yavuz, Eckehard Steinbach
We propose HAROOD as a short-range FMCW radar-based human activity classifier and out-of-distribution (OOD) detector. It aims to classify human sitting, standing, and walking activities and to detect any other moving or stationary object as OOD. We introduce a two-stage network. The first stage is trained with a novel loss function that includes intermediate reconstruction loss, intermediate contrastive loss, and triplet loss. The second stage uses the first stage's output as its input and is trained with cross-entropy loss. It creates a simple classifier that performs the activity classification. On our dataset collected by 60 GHz short-range FMCW radar, we achieve an average classification accuracy of 96.51%. Also, we achieve an average AUROC of 95.04% as an OOD detector. Additionally, our extensive evaluations demonstrate the superiority of HAROOD over the state-of-the-art OOD detection methods in terms of standard OOD detection metrics.
Authors: Vincent Tao Hu, Wenzhe Yin, Pingchuan Ma, Yunlu Chen, Basura Fernando, Yuki M Asano, Efstratios Gavves, Pascal Mettes, Bjorn Ommer, Cees G. M. Snoek
Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks. Noticeably, our approach establishes a new state-of-the-art Fr\'echet Inception Distance on the KIT-ML dataset. What is more, we tailor a straightforward motion editing paradigm named \emph{sampling trajectory rewriting} leveraging the ODE-style generative models and apply it to various editing scenarios including motion prediction, motion in-between prediction, motion interpolation, and upper-body editing. Our code will be released.
Authors: Mingyang Chen, Bo Huang, Junda Lu, Bing Li, Yi Wang, Minhao Cheng, Wei Wang
Dataset distillation is the technique of synthesizing smaller condensed datasets from large original datasets while retaining necessary information to persist the effect. In this paper, we approach the dataset distillation problem from a novel perspective: we regard minimizing the prediction discrepancy on the real data distribution between models, which are respectively trained on the large original dataset and on the small distilled dataset, as a conduit for condensing information from the raw data into the distilled version. An adversarial framework is proposed to solve the problem efficiently. In contrast to existing distillation methods involving nested optimization or long-range gradient unrolling, our approach hinges on single-level optimization. This ensures the memory efficiency of our method and provides a flexible tradeoff between time and memory budgets, allowing us to distil ImageNet-1K using a minimum of only 6.5GB of GPU memory. Under the optimal tradeoff strategy, it requires only 2.5$\times$ less memory and 5$\times$ less runtime compared to the state-of-the-art. Empirically, our method can produce synthetic datasets just 10% the size of the original, yet achieve, on average, 94% of the test accuracy of models trained on the full original datasets including ImageNet-1K, significantly surpassing state-of-the-art. Additionally, extensive tests reveal that our distilled datasets excel in cross-architecture generalization capabilities.
Authors: Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxiao Dong, Ming Ding, Jie Tang
People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails, but struggle to understand and interact with GUIs, thus limiting their potential to increase automation levels. In this paper, we introduce CogAgent, an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders, CogAgent supports input at a resolution of 1120*1120, enabling it to recognize tiny page elements and text. As a generalist visual language model, CogAgent achieves the state of the art on five text-rich and four general VQA benchmarks, including VQAv2, OK-VQA, Text-VQA, ST-VQA, ChartQA, infoVQA, DocVQA, MM-Vet, and POPE. CogAgent, using only screenshots as input, outperforms LLM-based methods that consume extracted HTML text on both PC and Android GUI navigation tasks -- Mind2Web and AITW, advancing the state of the art. The model and codes are available at \url{https://github.com/THUDM/CogVLM}.
Authors: Maxime Di Folco, Cosmin I. Bercea, Julia A. Schnabel
Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. In this paper, we propose a novel interpretable approach that combines attribute regularization of the latent space within the framework of an adversarially trained variational autoencoder. Comparative experiments on a cardiac MRI dataset demonstrate the ability of the proposed method to address blurry reconstruction issues of variational autoencoder methods and improve latent space interpretability. Additionally, our analysis of a downstream task reveals that the classification of cardiac disease using the regularized latent space heavily relies on attribute regularized dimensions, demonstrating great interpretability by connecting the used attributes for prediction with clinical observations.
Authors: Jingxuan He, Lechao Cheng, Chaowei Fang, Zunlei Feng, Tingting Mu, Mingli Song
Compared to conventional semantic segmentation with pixel-level supervision, Weakly Supervised Semantic Segmentation (WSSS) with image-level labels poses the challenge that it always focuses on the most discriminative regions, resulting in a disparity between fully supervised conditions. A typical manifestation is the diminished precision on the object boundaries, leading to a deteriorated accuracy of WSSS. To alleviate this issue, we propose to adaptively partition the image content into deterministic regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing. For uncertain cues, we employ an activation-based masking strategy and seek to recover the local information with self-distilled knowledge. We further assume that the unmasked confident regions should be robust enough to preserve the global semantics. Building upon this, we introduce a complementary self-enhancement method that constrains the semantic consistency between these confident regions and an augmented image with the same class labels. Extensive experiments conducted on PASCAL VOC 2012 and MS COCO 2014 demonstrate that our proposed single-stage approach for WSSS not only outperforms state-of-the-art benchmarks remarkably but also surpasses multi-stage methodologies that trade complexity for accuracy. The code can be found at https://github.com/Jessie459/feature-self-reinforcement.
Authors: Jiaqi Tang, Hao Lu, Xiaogang Xu, Ruizheng Wu, Sixing Hu, Tong Zhang, Tsz Wa Cheng, Ming Ge, Ying-Cong Chen, Fugee Tsung
Artificial Intelligence (AI)-driven defect inspection is pivotal in industrial manufacturing. Yet, many methods, tailored to specific pipelines, grapple with diverse product portfolios and evolving processes. Addressing this, we present the Incremental Unified Framework (IUF) that can reduce the feature conflict problem when continuously integrating new objects in the pipeline, making it advantageous in object-incremental learning scenarios. Employing a state-of-the-art transformer, we introduce Object-Aware Self-Attention (OASA) to delineate distinct semantic boundaries. Semantic Compression Loss (SCL) is integrated to optimize non-primary semantic space, enhancing network adaptability for novel objects. Additionally, we prioritize retaining the features of established objects during weight updates. Demonstrating prowess in both image and pixel-level defect inspection, our approach achieves state-of-the-art performance, proving indispensable for dynamic and scalable industrial inspections. Our code will be released at https://github.com/jqtangust/IUF.
Authors: Shitong Sun, Fanghua Ye, Shaogang Gong
Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text. It has recently attracted attention due to the collaboration of information-rich images and concise language to precisely express the requirements of target images. Most of the existing composed image retrieval methods follow a supervised learning paradigm to perform training on a costly triplet dataset composed of a reference image, modified text, and a corresponding target image. To alleviate the demand for difficult-to-obtain labeled triplet data, recent methods have introduced zero-shot composed image retrieval (ZS-CIR), which aims to retrieve the target image without the supervision of human-labeled triplets but instead relies on image-text pairs or self-generated triplets. However, these methods are less computationally efficient due to the requirement of training and also less understandable, assuming that the interaction between image and text is conducted with implicit query embedding. In this work, we present a new Training-Free zero-shot Composed Image Retrieval (TFCIR) method which translates the query into explicit human-understandable text. This helps improve computation efficiency while maintaining the generalization of foundation models. Further, we introduce a Local Concept Reranking (LCR) mechanism to focus on discriminative local information extracted from the modified instruction. Extensive experiments on three ZS-CIR benchmarks show that the proposed approach can achieve comparable performances with state-of-the-art methods and significantly outperforms other training-free methods on the open domain datasets, CIRR and CIRCO, as well as the fashion domain dataset, FashionIQ.
Authors: Josh Stein, Maxime Di Folco, Julia A. Schnabel
The Segment Anything Model (SAM) has recently emerged as a significant breakthrough in foundation models, demonstrating remarkable zero-shot performance in object segmentation tasks. While SAM is designed for generalization, it exhibits limitations in handling specific medical imaging tasks that require fine-structure segmentation or precise boundaries. In this paper, we focus on the task of cardiac magnetic resonance imaging (cMRI) short-axis view segmentation using the SAM foundation model. We conduct a comprehensive investigation of the impact of different prompting strategies (including bounding boxes, positive points, negative points, and their combinations) on segmentation performance. We evaluate on two public datasets using the baseline model and models fine-tuned with varying amounts of annotated data, ranging from a limited number of volumes to a fully annotated dataset. Our findings indicate that prompting strategies significantly influence segmentation performance. Combining positive points with either bounding boxes or negative points shows substantial benefits, but little to no benefit when combined simultaneously. We further observe that fine-tuning SAM with a few annotated volumes improves segmentation performance when properly prompted. Specifically, fine-tuning with bounding boxes has a positive impact, while fine-tuning without bounding boxes leads to worse results compared to baseline.
Authors: Tong Wei, Bo-Lin Wang, Min-Ling Zhang
Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-world scenarios. This paper addresses the challenging task of long-tailed OOD detection, where the in-distribution data follows a long-tailed class distribution. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes, as the ability of a classifier to detect OOD instances is not strongly correlated with its accuracy on the in-distribution classes. To overcome this issue, we propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes. This approach allows us to build a detector with clear decision boundaries by training on OOD data using virtual labels. (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data. This technique encourages the model to pay more attention to the discriminative features of the tail classes. We provide a clue for separating in-distribution and OOD data by analyzing gradient noise. Through extensive experiments, we demonstrate that our method outperforms the current state-of-the-art on various benchmark datasets. Moreover, our method can be used as an add-on for existing long-tail learning approaches, significantly enhancing their OOD detection performance. Code is available at: https://github.com/Stomach-ache/Long-Tailed-OOD-Detection .
Authors: Yan Gao, Haojun Xu, Nannan Wang, Jie Li, Xinbo Gao
The global multi-object tracking (MOT) system can consider interaction, occlusion, and other ``visual blur'' scenarios to ensure effective object tracking in long videos. Among them, graph-based tracking-by-detection paradigms achieve surprising performance. However, their fully-connected nature poses storage space requirements that challenge algorithm handling long videos. Currently, commonly used methods are still generated trajectories by building one-forward associations across frames. Such matches produced under the guidance of first-order similarity information may not be optimal from a longer-time perspective. Moreover, they often lack an end-to-end scheme for correcting mismatches. This paper proposes the Composite Node Message Passing Network (CoNo-Link), a multi-scene generalized framework for modeling ultra-long frames information for association. CoNo-Link's solution is a low-storage overhead method for building constrained connected graphs. In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction, improving the graph neural network's feature representation capability. Specifically, we formulate the graph-building problem as a top-k selection task for some reliable objects or trajectories. Our model can learn better predictions on longer-time scales by adding composite nodes. As a result, our method outperforms the state-of-the-art in several commonly used datasets.
Authors: Kefu Yi, Kai Luo, Xiaolei Luo, Jiangui Huang, Hao Wu, Rongdong Hu, Wei Hao
Multi-object tracking (MOT) in video sequences remains a challenging task, especially in scenarios with significant camera movements. This is because targets can drift considerably on the image plane, leading to erroneous tracking outcomes. Addressing such challenges typically requires supplementary appearance cues or Camera Motion Compensation (CMC). While these strategies are effective, they also introduce a considerable computational burden, posing challenges for real-time MOT. In response to this, we introduce UCMCTrack, a novel motion model-based tracker robust to camera movements. Unlike conventional CMC that computes compensation parameters frame-by-frame, UCMCTrack consistently applies the same compensation parameters throughout a video sequence. It employs a Kalman filter on the ground plane and introduces the Mapped Mahalanobis Distance (MMD) as an alternative to the traditional Intersection over Union (IoU) distance measure. By leveraging projected probability distributions on the ground plane, our approach efficiently captures motion patterns and adeptly manages uncertainties introduced by homography projections. Remarkably, UCMCTrack, relying solely on motion cues, achieves state-of-the-art performance across a variety of challenging datasets, including MOT17, MOT20, DanceTrack and KITTI, with an exceptional speed of over 1000 FPS on a single CPU. More details and code are available at https://github.com/corfyi/UCMCTrack
Authors: Zhiyuan You, Zheyuan Li, Jinjin Gu, Zhenfei Yin, Tianfan Xue, Chao Dong
We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based approaches. DepictQA leverages Multi-modal Large Language Models (MLLMs), allowing for detailed, language-based, human-like evaluation of image quality. Unlike conventional Image Quality Assessment (IQA) methods relying on scores, DepictQA interprets image content and distortions descriptively and comparatively, aligning closely with humans' reasoning process. To build the DepictQA model, we establish a hierarchical task framework, and collect a multi-modal IQA training dataset, named M-BAPPS. To navigate the challenges in limited training data and processing multiple images, we propose to use multi-source training data and specialized image tags. Our DepictQA demonstrates a better performance than score-based methods on the BAPPS benchmark. Moreover, compared with general MLLMs, our DepictQA can generate more accurate reasoning descriptive languages. Our research indicates that language-based IQA methods have the potential to be customized for individual preferences. Datasets and codes will be released publicly.
Authors: Yuhang Yang, Wei Zhai, Hongchen Luo, Yang Cao, Zheng-Jun Zha
Learning 3D human-object interaction relation is pivotal to embodied AI and interaction modeling. Most existing methods approach the goal by learning to predict isolated interaction elements, e.g., human contact, object affordance, and human-object spatial relation, primarily from the perspective of either the human or the object. Which underexploit certain correlations between the interaction counterparts (human and object), and struggle to address the uncertainty in interactions. Actually, objects' functionalities potentially affect humans' interaction intentions, which reveals what the interaction is. Meanwhile, the interacting humans and objects exhibit matching geometric structures, which presents how to interact. In light of this, we propose harnessing these inherent correlations between interaction counterparts to mitigate the uncertainty and jointly anticipate the above interaction elements in 3D space. To achieve this, we present LEMON (LEarning 3D huMan-Object iNteraction relation), a unified model that mines interaction intentions of the counterparts and employs curvatures to guide the extraction of geometric correlations, combining them to anticipate the interaction elements. Besides, the 3D Interaction Relation dataset (3DIR) is collected to serve as the test bed for training and evaluation. Extensive experiments demonstrate the superiority of LEMON over methods estimating each element in isolation.
Authors: Qilong Li, Ji Liu, Yifan Sun, Chongsheng Zhang, Dejing Dou
In recent years, Deep Neural Networks (DNN) have emerged as a practical method for image recognition. The raw data, which contain sensitive information, are generally exploited within the training process. However, when the training process is outsourced to a third-party organization, the raw data should be desensitized before being transferred to protect sensitive information. Although masks are widely applied to hide important sensitive information, preventing inpainting masked images is critical, which may restore the sensitive information. The corresponding models should be adjusted for the masked images to reduce the degradation of the performance for recognition or classification tasks due to the desensitization of images. In this paper, we propose a mask-based image desensitization approach while supporting recognition. This approach consists of a mask generation algorithm and a model adjustment method. We propose exploiting an interpretation algorithm to maintain critical information for the recognition task in the mask generation algorithm. In addition, we propose a feature selection masknet as the model adjustment method to improve the performance based on the masked images. Extensive experimentation results based on multiple image datasets reveal significant advantages (up to 9.34% in terms of accuracy) of our approach for image desensitization while supporting recognition.
Authors: Imad Eddine Marouf, Subhankar Roy, Enzo Tartaglione, Stéphane Lathuilière
In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, such that the data from the previous tasks becomes unavailable while learning on the current task data. CL is essentially a balancing act between being able to learn on the new task (i.e., plasticity) and maintaining the performance on the previously learned concepts (i.e., stability). With an aim to address the stability-plasticity trade-off, we propose to perform weight-ensembling of the model parameters of the previous and current task. This weight-ensembled model, which we call Continual Model Averaging (or CoMA), attains high accuracy on the current task by leveraging plasticity, while not deviating too far from the previous weight configuration, ensuring stability. We also propose an improved variant of CoMA, named Continual Fisher-weighted Model Averaging (or CoFiMA), that selectively weighs each parameter in the weight ensemble by leveraging the Fisher information of the weights of the model. Both the variants are conceptually simple, easy to implement, and effective in attaining state-of-the-art performance on several standard CL benchmarks.
Authors: Yunze Liu, Changxi Chen, Li Yi
We focus on the human-humanoid interaction task optionally with an object. We propose a new task named online full-body motion reaction synthesis, which generates humanoid reactions based on the human actor's motions. The previous work only focuses on human interaction without objects and generates body reactions without hand. Besides, they also do not consider the task as an online setting, which means the inability to observe information beyond the current moment in practical situations. To support this task, we construct two datasets named HHI and CoChair and propose a unified method. Specifically, we propose to construct a social affordance representation. We first select a social affordance carrier and use SE(3)-Equivariant Neural Networks to learn the local frame for the carrier, then we canonicalize the social affordance. Besides, we propose a social affordance forecasting scheme to enable the reactor to predict based on the imagined future. Experiments demonstrate that our approach can effectively generate high-quality reactions on HHI and CoChair. Furthermore, we also validate our method on existing human interaction datasets Interhuman and Chi3D.
Authors: Yabing Wang, Fan Wang, Jianfeng Dong, Hao Luo
Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs. Current methods employ machine translation (MT) to construct pseudo-parallel data pairs, which are then used to learn a multi-lingual and multi-modal embedding space that aligns visual and target-language representations. However, the large heterogeneous gap between vision and text, along with the noise present in target language translations, poses significant challenges in effectively aligning their representations. To address these challenges, we propose a general framework, Cross-Lingual to Cross-Modal (CL2CM), which improves the alignment between vision and target language using cross-lingual transfer. This approach allows us to fully leverage the merits of multi-lingual pre-trained models (e.g., mBERT) and the benefits of the same modality structure, i.e., smaller gap, to provide reliable and comprehensive semantic correspondence (knowledge) for the cross-modal network. We evaluate our proposed approach on two multilingual image-text datasets, Multi30K and MSCOCO, and one video-text dataset, VATEX. The results clearly demonstrate the effectiveness of our proposed method and its high potential for large-scale retrieval.
Authors: Han Liang, Jiacheng Bao, Ruichi Zhang, Sihan Ren, Yuecheng Xu, Sibei Yang, Xin Chen, Jingyi Yu, Lan Xu
We have recently seen tremendous progress in realistic text-to-motion generation. Yet, the existing methods often fail or produce implausible motions with unseen text inputs, which limits the applications. In this paper, we present OMG, a novel framework, which enables compelling motion generation from zero-shot open-vocabulary text prompts. Our key idea is to carefully tailor the pretrain-then-finetune paradigm into the text-to-motion generation. At the pre-training stage, our model improves the generation ability by learning the rich out-of-domain inherent motion traits. To this end, we scale up a large unconditional diffusion model up to 1B parameters, so as to utilize the massive unlabeled motion data up to over 20M motion instances. At the subsequent fine-tuning stage, we introduce motion ControlNet, which incorporates text prompts as conditioning information, through a trainable copy of the pre-trained model and the proposed novel Mixture-of-Controllers (MoC) block. MoC block adaptively recognizes various ranges of the sub-motions with a cross-attention mechanism and processes them separately with the text-token-specific experts. Such a design effectively aligns the CLIP token embeddings of text prompts to various ranges of compact and expressive motion features. Extensive experiments demonstrate that our OMG achieves significant improvements over the state-of-the-art methods on zero-shot text-to-motion generation. Project page: https://tr3e.github.io/omg-page.
Authors: Zhuoyifan Zhang, Lu Zhang, Liang Wang, Haoming Wu
The research on neural radiance fields for new view synthesis has experienced explosive growth with the development of new models and extensions. The NERF algorithm, suitable for underwater scenes or scattering media, is also evolving. Existing underwater 3D reconstruction systems still face challenges such as extensive training time and low rendering efficiency. This paper proposes an improved underwater 3D reconstruction system to address these issues and achieve rapid, high-quality 3D reconstruction.To begin with, we enhance underwater videos captured by a monocular camera to correct the poor image quality caused by the physical properties of the water medium while ensuring consistency in enhancement across adjacent frames. Subsequently, we perform keyframe selection on the video frames to optimize resource utilization and eliminate the impact of dynamic objects on the reconstruction results. The selected keyframes, after pose estimation using COLMAP, undergo a three-dimensional reconstruction improvement process using neural radiance fields based on multi-resolution hash coding for model construction and rendering.
Authors: Jiwoo Chung, Sangeek Hyun, Jae-Pil Heo
Despite the impressive generative capabilities of diffusion models, existing diffusion model-based style transfer methods require inference-stage optimization (e.g. fine-tuning or textual inversion of style) which is time-consuming, or fails to leverage the generative ability of large-scale diffusion models. To address these issues, we introduce a novel artistic style transfer method based on a pre-trained large-scale diffusion model without any optimization. Specifically, we manipulate the features of self-attention layers as the way the cross-attention mechanism works; in the generation process, substituting the key and value of content with those of style image. This approach provides several desirable characteristics for style transfer including 1) preservation of content by transferring similar styles into similar image patches and 2) transfer of style based on similarity of local texture (e.g. edge) between content and style images. Furthermore, we introduce query preservation and attention temperature scaling to mitigate the issue of disruption of original content, and initial latent Adaptive Instance Normalization (AdaIN) to deal with the disharmonious color (failure to transfer the colors of style). Our experimental results demonstrate that our proposed method surpasses state-of-the-art methods in both conventional and diffusion-based style transfer baselines.
Authors: Kai Qiu, Huishuai Zhang, Zhirong Wu, Stephen Lin
Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model robustness, which is a critical aspect for safety, is often optimized for each specific task rather than at the pretraining stage. In this paper, we propose a method for pretraining certifiably robust models that can be readily finetuned for adaptation to a particular task. A key challenge is dealing with the compromise between semantic learning and robustness. We address this with a simple yet highly effective strategy based on significantly broadening the pretraining data distribution, which is shown to greatly benefit finetuning for downstream tasks. Through pretraining on a mixture of clean and various noisy images, we find that surprisingly strong certified accuracy can be achieved even when finetuning on only clean images. Furthermore, this strategy requires just a single model to deal with various noise levels, thus substantially reducing computational costs in relation to previous works that employ multiple models. Despite using just one model, our method can still yield results that are on par with, or even superior to, existing multi-model methods.
Authors: Qiankun Zuo, Ling Chen, Shuqiang Wang
Effective connectivity estimation plays a crucial role in understanding the interactions and information flow between different brain regions. However, the functional time series used for estimating effective connentivity is derived from certain software, which may lead to large computing errors because of different parameter settings and degrade the ability to model complex causal relationships between brain regions. In this paper, a brain diffuser with hierarchical transformer (BDHT) is proposed to estimate effective connectivity for mild cognitive impairment (MCI) analysis. To our best knowledge, the proposed brain diffuer is the first generative model to apply diffusion models in the application of generating and analyzing multimodal brain networks. Specifically, the BDHT leverages the structural connectivity to guide the reverse processes in an efficient way. It makes the denoising process more reliable and guarantees effective connectivity estimation accuracy. To improve denoising quality, the hierarchical denoising transformer is designed to learn multi-scale features in topological space. Furthermore, the GraphConFormer block can concentrate on both global and adjacent connectivity information. By stacking the multi-head attention and graph convolutional network, the proposed model enhances structure-function complementarity and improves the ability in noise estimation. Experimental evaluations of the denoising diffusion model demonstrate its effectiveness in estimating effective connectivity. The method achieves superior performance in terms of accuracy and robustness compared to existing approaches. It can captures both unidirectal and bidirectional interactions between brain regions, providing a comprehensive understanding of the brain's information processing mechanisms.
Authors: Oliver Grainge, Michael Milford, Indu Bodala, Sarvapali D. Ramchurn, Shoaib Ehsan
Visual Place Recognition (VPR) is a critical task for performing global re-localization in visual perception systems. It requires the ability to accurately recognize a previously visited location under variations such as illumination, occlusion, appearance and viewpoint. In the case of robotic systems and augmented reality, the target devices for deployment are battery powered edge devices. Therefore whilst the accuracy of VPR methods is important so too is memory consumption and latency. Recently new works have focused on the recall@1 metric as a performance measure with limited focus on resource utilization. This has resulted in methods that use deep learning models too large to deploy on low powered edge devices. We hypothesize that these large models are highly over-parameterized and can be optimized to satisfy the constraints of a low powered embedded system whilst maintaining high recall performance. Our work studies the impact of compact convolutional network architecture design in combination with full-precision and mixed-precision post-training quantization on VPR performance. Importantly we not only measure performance via the recall@1 score but also measure memory consumption and latency. We characterize the design implications on memory, latency and recall scores and provide a number of design recommendations for VPR systems under these resource limitations.
Authors: Yuqing Wang, Zhenyu Weng, Zhaokun Zhou, Shuaijian Ji, Zhongjie Ye, Yuesheng Zhu
Over the past years, Printed Mathematical Expression Recognition (PMER) has progressed rapidly. However, due to the insufficient context information captured by Convolutional Neural Networks, some mathematical symbols might be incorrectly recognized or missed. To tackle this problem, in this paper, a Dual Branch transformer-based Network (DBN) is proposed to learn both local and global context information for accurate PMER. In our DBN, local and global features are extracted simultaneously, and a Context Coupling Module (CCM) is developed to complement the features between the global and local contexts. CCM adopts an interactive manner so that the coupled context clues are highly correlated to each expression symbol. Additionally, we design a Dynamic Soft Target (DST) strategy to utilize the similarities among symbol categories for reasonable label generation. Our experimental results have demonstrated that DBN can accurately recognize mathematical expressions and has achieved state-of-the-art performance.
Authors: Yuan Sun, Xuan Wang, Yunfan Zhang, Jie Zhang, Caigui Jiang, Yu Guo, Fei Wang
We present a method named iComMa to address the 6D pose estimation problem in computer vision. The conventional pose estimation methods typically rely on the target's CAD model or necessitate specific network training tailored to particular object classes. Some existing methods address mesh-free 6D pose estimation by employing the inversion of a Neural Radiance Field (NeRF), aiming to overcome the aforementioned constraints. However, it still suffers from adverse initializations. By contrast, we model the pose estimation as the problem of inverting the 3D Gaussian Splatting (3DGS) with both the comparing and matching loss. In detail, a render-and-compare strategy is adopted for the precise estimation of poses. Additionally, a matching module is designed to enhance the model's robustness against adverse initializations by minimizing the distances between 2D keypoints. This framework systematically incorporates the distinctive characteristics and inherent rationale of render-and-compare and matching-based approaches. This comprehensive consideration equips the framework to effectively address a broader range of intricate and challenging scenarios, including instances with substantial angular deviations, all while maintaining a high level of prediction accuracy. Experimental results demonstrate the superior precision and robustness of our proposed jointly optimized framework when evaluated on synthetic and complex real-world data in challenging scenarios.
Authors: Michael Jungo, Lars Vögtlin, Atefeh Fakhari, Nathan Wegmann, Rolf Ingold, Andreas Fischer, Anna Scius-Bertrand
Handwriting recognition is a key technology for accessing the content of old manuscripts, helping to preserve cultural heritage. Deep learning shows an impressive performance in solving this task. However, to achieve its full potential, it requires a large amount of labeled data, which is difficult to obtain for ancient languages and scripts. Often, a trade-off has to be made between ground truth quantity and quality, as is the case for the recently introduced Bullinger database. It contains an impressive amount of over a hundred thousand labeled text line images of mostly premodern German and Latin texts that were obtained by automatically aligning existing page-level transcriptions with text line images. However, the alignment process introduces systematic errors, such as wrongly hyphenated words. In this paper, we investigate the impact of such errors on training and evaluation and suggest means to detect and correct typical alignment errors.
Authors: Jinghong Li, Wen Gu, Koichi Ota, Shinobu Hasegawa
With the rapid development of the internet in the past decade, it has become increasingly important to extract valuable information from vast resources efficiently, which is crucial for establishing a comprehensive digital ecosystem, particularly in the context of research surveys and comprehension. The foundation of these tasks focuses on accurate extraction and deep mining of data from scientific documents, which are essential for building a robust data infrastructure. However, parsing raw data or extracting data from complex scientific documents have been ongoing challenges. Current data extraction methods for scientific documents typically use rule-based (RB) or machine learning (ML) approaches. However, using rule-based methods can incur high coding costs for articles with intricate typesetting. Conversely, relying solely on machine learning methods necessitates annotation work for complex content types within the scientific document, which can be costly. Additionally, few studies have thoroughly defined and explored the hierarchical layout within scientific documents. The lack of a comprehensive definition of the internal structure and elements of the documents indirectly impacts the accuracy of text classification and object recognition tasks. From the perspective of analyzing the standard layout and typesetting used in the specified publication, we propose a new document layout analysis framework called CTBR(Compartment & Text Blocks Refinement). Firstly, we define scientific documents into hierarchical divisions: base domain, compartment, and text blocks. Next, we conduct an in-depth exploration and classification of the meanings of text blocks. Finally, we utilize the results of text block classification to implement object recognition within scientific documents based on rule-based compartment segmentation.
Authors: Juyeop Kim, Jun-Ho Choi, Soobeom Jang, Jong-Seok Lee
While adversarial perturbation of images to attack deep image classification models pose serious security concerns in practice, this paper suggests a novel paradigm where the concept of image perturbation can benefit classification performance, which we call amicable aid. We show that by taking the opposite search direction of perturbation, an image can be modified to yield higher classification confidence and even a misclassified image can be made correctly classified. This can be also achieved with a large amount of perturbation by which the image is made unrecognizable by human eyes. The mechanism of the amicable aid is explained in the viewpoint of the underlying natural image manifold. Furthermore, we investigate the universal amicable aid, i.e., a fixed perturbation can be applied to multiple images to improve their classification results. While it is challenging to find such perturbations, we show that making the decision boundary as perpendicular to the image manifold as possible via training with modified data is effective to obtain a model for which universal amicable perturbations are more easily found.
Authors: Jared Edward Reser
This article provides an analytical framework for how to simulate human-like thought processes within a computer. It describes how attention and memory should be structured, updated, and utilized to search for associative additions to the stream of thought. The focus is on replicating the dynamics of the mammalian working memory system, which features two forms of persistent activity: sustained firing (preserving information on the order of seconds) and synaptic potentiation (preserving information from minutes to hours). The article uses a series of over 40 original figures to systematically demonstrate how the iterative updating of these working memory stores provides functional structure to behavior, cognition, and consciousness.
In an AI implementation, these two memory stores should be updated continuously and in an iterative fashion, meaning each state should preserve a proportion of the coactive representations from the state before it. Thus, the set of concepts in working memory will evolve gradually and incrementally over time. This makes each state a revised iteration of the preceding state and causes successive states to overlap and blend with respect to the information they contain. Transitions between states happen as persistent activity spreads activation energy throughout the hierarchical network searching long-term memory for the most appropriate representation to be added to the global workspace. The result is a chain of associatively linked intermediate states capable of advancing toward a solution or goal. Iterative updating is conceptualized here as an information processing strategy, a model of working memory, a theory of consciousness, and an algorithm for designing and programming artificial general intelligence.
Authors: Jean Prost, Antoine Houdard, Andrés Almansa, Nicolas Papadakis
We investigate the problem of producing diverse solutions to an image super-resolution problem. From a probabilistic perspective, this can be done by sampling from the posterior distribution of an inverse problem, which requires the definition of a prior distribution on the high-resolution images. In this work, we propose to use a pretrained hierarchical variational autoencoder (HVAE) as a prior. We train a lightweight stochastic encoder to encode low-resolution images in the latent space of a pretrained HVAE. At inference, we combine the low-resolution encoder and the pretrained generative model to super-resolve an image. We demonstrate on the task of face super-resolution that our method provides an advantageous trade-off between the computational efficiency of conditional normalizing flows techniques and the sample quality of diffusion based methods.
Authors: Ramya Muthukrishnan, Angelina Heyler, Keshava Katti, Sarthak Pati, Walter Mankowski, Aprupa Alahari, Michael Sanborn, Emily F. Conant, Christopher Scott, Stacey Winham, Celine Vachon, Pratik Chaudhari, Despina Kontos, Spyridon Bakas
In this study, we automate quantitative mammographic breast density estimation with neural networks and show that this tool is a strong use case for federated learning on multi-institutional datasets. Our dataset included bilateral CC-view and MLO-view mammographic images from two separate institutions. Two U-Nets were separately trained on algorithm-generated labels to perform segmentation of the breast and dense tissue from these images and subsequently calculate breast percent density (PD). The networks were trained with federated learning and compared to three non-federated baselines, one trained on each single-institution dataset and one trained on the aggregated multi-institution dataset. We demonstrate that training on multi-institution datasets is critical to algorithm generalizability. We further show that federated learning on multi-institutional datasets improves model generalization to unseen data at nearly the same level as centralized training on multi-institutional datasets, indicating that federated learning can be applied to our method to improve algorithm generalizability while maintaining patient privacy.
Authors: Hammad A. Ayyubi, Christopher Thomas, Lovish Chum, Rahul Lokesh, Long Chen, Yulei Niu, Xudong Lin, Xuande Feng, Jaywon Koo, Sounak Ray, Shih-Fu Chang
Events describe happenings in our world that are of importance. Naturally, understanding events mentioned in multimedia content and how they are related forms an important way of comprehending our world. Existing literature can infer if events across textual and visual (video) domains are identical (via grounding) and thus, on the same semantic level. However, grounding fails to capture the intricate cross-event relations that exist due to the same events being referred to on many semantic levels. For example, in Figure 1, the abstract event of "war" manifests at a lower semantic level through subevents "tanks firing" (in video) and airplane "shot" (in text), leading to a hierarchical, multimodal relationship between the events.
In this paper, we propose the task of extracting event hierarchies from multimodal (video and text) data to capture how the same event manifests itself in different modalities at different semantic levels. This reveals the structure of events and is critical to understanding them. To support research on this task, we introduce the Multimodal Hierarchical Events (MultiHiEve) dataset. Unlike prior video-language datasets, MultiHiEve is composed of news video-article pairs, which makes it rich in event hierarchies. We densely annotate a part of the dataset to construct the test benchmark. We show the limitations of state-of-the-art unimodal and multimodal baselines on this task. Further, we address these limitations via a new weakly supervised model, leveraging only unannotated video-article pairs from MultiHiEve. We perform a thorough evaluation of our proposed method which demonstrates improved performance on this task and highlight opportunities for future research.
Authors: Fawaz Sammani, Boris Joukovsky, Nikos Deligiannis
Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these approaches and understand their inner workings mechanisms. Given that contrastive models are trained with interdependent and interacting inputs and aim to learn invariance through data augmentation, the existing methods for explaining single-image systems (e.g., image classification models) are inadequate as they fail to account for these factors and typically assume independent inputs. Additionally, there is a lack of evaluation metrics designed to assess pairs of explanations, and no analytical studies have been conducted to investigate the effectiveness of different techniques used to explaining contrastive learning. In this work, we design visual explanation methods that contribute towards understanding similarity learning tasks from pairs of images. We further adapt existing metrics, used to evaluate visual explanations of image classification systems, to suit pairs of explanations and evaluate our proposed methods with these metrics. Finally, we present a thorough analysis of visual explainability methods for contrastive learning, establish their correlation with downstream tasks and demonstrate the potential of our approaches to investigate their merits and drawbacks.
Authors: Robbie Holland, Oliver Leingang, Hrvoje Bogunović, Sophie Riedl, Lars Fritsche, Toby Prevost, Hendrik P. N. Scholl, Ursula Schmidt-Erfurth, Sobha Sivaprasad, Andrew J. Lotery, Daniel Rueckert, Martin J. Menten
Deep learning has potential to automate screening, monitoring and grading of disease in medical images. Pretraining with contrastive learning enables models to extract robust and generalisable features from natural image datasets, facilitating label-efficient downstream image analysis. However, the direct application of conventional contrastive methods to medical datasets introduces two domain-specific issues. Firstly, several image transformations which have been shown to be crucial for effective contrastive learning do not translate from the natural image to the medical image domain. Secondly, the assumption made by conventional methods, that any two images are dissimilar, is systematically misleading in medical datasets depicting the same anatomy and disease. This is exacerbated in longitudinal image datasets that repeatedly image the same patient cohort to monitor their disease progression over time. In this paper we tackle these issues by extending conventional contrastive frameworks with a novel metadata-enhanced strategy. Our approach employs widely available patient metadata to approximate the true set of inter-image contrastive relationships. To this end we employ records for patient identity, eye position (i.e. left or right) and time series information. In experiments using two large longitudinal datasets containing 170,427 retinal OCT images of 7,912 patients with age-related macular degeneration (AMD), we evaluate the utility of using metadata to incorporate the temporal dynamics of disease progression into pretraining. Our metadata-enhanced approach outperforms both standard contrastive methods and a retinal image foundation model in five out of six image-level downstream tasks related to AMD. Due to its modularity, our method can be quickly and cost-effectively tested to establish the potential benefits of including available metadata in contrastive pretraining.
Authors: Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers, Stefan Roth
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain fixed at test time. In this work, we challenge this premise with a self-adaptive approach for semantic segmentation that adjusts the inference process to each input sample. Self-adaptation operates on two levels. First, it fine-tunes the parameters of convolutional layers to the input image using consistency regularization. Second, in Batch Normalization layers, self-adaptation interpolates between the training and the reference distribution derived from a single test sample. Despite both techniques being well known in the literature, their combination sets new state-of-the-art accuracy on synthetic-to-real generalization benchmarks. Our empirical study suggests that self-adaptation may complement the established practice of model regularization at training time for improving deep network generalization to out-of-domain data. Our code and pre-trained models are available at https://github.com/visinf/self-adaptive.
Authors: Jing Wu, Munawar Hayat, Mingyi Zhou, Mehrtash Harandi
Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to model inversion attacks, where adversaries reconstruct users private data via eavesdropping on the shared gradient information. We hypothesize that a key factor in the success of such attacks is the low entanglement among gradients per data within the batch during stochastic optimization. This creates a vulnerability that an adversary can exploit to reconstruct the sensitive data. Building upon this insight, we present a simple, yet effective defense strategy that obfuscates the gradients of the sensitive data with concealed samples. To achieve this, we propose synthesizing concealed samples to mimic the sensitive data at the gradient level while ensuring their visual dissimilarity from the actual sensitive data. Compared to the previous art, our empirical evaluations suggest that the proposed technique provides the strongest protection while simultaneously maintaining the FL performance.
Authors: Juyeop Kim, Junha Park, Songkuk Kim, Jong-Seok Lee
Neural networks with self-attention (a.k.a. Transformers) like ViT and Swin have emerged as a better alternative to traditional convolutional neural networks (CNNs). However, our understanding of how the new architecture works is still limited. In this paper, we focus on the phenomenon that Transformers show higher robustness against corruptions than CNNs, while not being overconfident. This is contrary to the intuition that robustness increases with confidence. We resolve this contradiction by empirically investigating how the output of the penultimate layer moves in the representation space as the input data moves linearly within a small area. In particular, we show the following. (1) While CNNs exhibit fairly linear relationship between the input and output movements, Transformers show nonlinear relationship for some data. For those data, the output of Transformers moves in a curved trajectory as the input moves linearly. (2) When a data is located in a curved region, it is hard to move it out of the decision region since the output moves along a curved trajectory instead of a straight line to the decision boundary, resulting in high robustness of Transformers. (3) If a data is slightly modified to jump out of the curved region, the movements afterwards become linear and the output goes to the decision boundary directly. In other words, there does exist a decision boundary near the data, which is hard to find only because of the curved representation space. This explains the underconfident prediction of Transformers. Also, we examine mathematical properties of the attention operation that induce nonlinear response to linear perturbation. Finally, we share our additional findings, regarding what contributes to the curved representation space of Transformers, and how the curvedness evolves during training.
Authors: Evangelos Ververas, Polydefkis Gkagkos, Jiankang Deng, Michail Christos Doukas, Jia Guo, Stefanos Zafeiriou
Developing gaze estimation models that generalize well to unseen domains and in-the-wild conditions remains a challenge with no known best solution. This is mostly due to the difficulty of acquiring ground truth data that cover the distribution of faces, head poses, and environments that exist in the real world. Most recent methods attempt to close the gap between specific source and target domains using domain adaptation. In this work, we propose to train general gaze estimation models which can be directly employed in novel environments without adaptation. To do so, we leverage the observation that head, body, and hand pose estimation benefit from revising them as dense 3D coordinate prediction, and similarly express gaze estimation as regression of dense 3D eye meshes. To close the gap between image domains, we create a large-scale dataset of diverse faces with gaze pseudo-annotations, which we extract based on the 3D geometry of the scene, and design a multi-view supervision framework to balance their effect during training. We test our method in the task of gaze generalization, in which we demonstrate improvement of up to 30% compared to state-of-the-art when no ground truth data are available, and up to 10% when they are. The project material are available for research purposes at https://github.com/Vagver/3DGazeNet.
Authors: Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao
In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model dubbed ViTPose. Specifically, ViTPose employs the plain and non-hierarchical vision transformer as an encoder to encode features and a lightweight decoder to decode body keypoints in either a top-down or a bottom-up manner. It can be scaled up from about 20M to 1B parameters by taking advantage of the scalable model capacity and high parallelism of the vision transformer, setting a new Pareto front for throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, and pre-training and fine-tuning strategy. Based on the flexibility, a novel ViTPose+ model is proposed to deal with heterogeneous body keypoint categories in different types of body pose estimation tasks via knowledge factorization, i.e., adopting task-agnostic and task-specific feed-forward networks in the transformer. We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Experimental results show that our ViTPose model outperforms representative methods on the challenging MS COCO Human Keypoint Detection benchmark at both top-down and bottom-up settings. Furthermore, our ViTPose+ model achieves state-of-the-art performance simultaneously on a series of body pose estimation tasks, including MS COCO, AI Challenger, OCHuman, MPII for human keypoint detection, COCO-Wholebody for whole-body keypoint detection, as well as AP-10K and APT-36K for animal keypoint detection, without sacrificing inference speed.
Authors: Lemeng Wu, Dilin Wang, Meng Li, Yunyang Xiong, Raghuraman Krishnamoorthi, Qiang Liu, Vikas Chandra
Fusing 3D LiDAR features with 2D camera features is a promising technique for enhancing the accuracy of 3D detection, thanks to their complementary physical properties. While most of the existing methods focus on directly fusing camera features with raw LiDAR point clouds or shallow-level 3D features, it is observed that directly combining 2D and 3D features in deeper layers actually leads to a decrease in accuracy due to feature misalignment. The misalignment, which stems from the aggregation of features learned from large receptive fields, becomes increasingly more severe as we delve into deeper layers. In this paper, we propose PathFusion as a solution to enable the alignment of semantically coherent LiDAR-camera deep feature fusion. PathFusion introduces a path consistency loss at multiple stages within the network, encouraging the 2D backbone and its fusion path to transform 2D features in a way that aligns semantically with the transformation of the 3D backbone. This ensures semantic consistency between 2D and 3D features, even in deeper layers, and amplifies the usage of the network's learning capacity. We apply PathFusion to improve a prior-art fusion baseline, Focals Conv, and observe an improvement of over 1.6% in mAP on the nuScenes test split consistently with and without testing-time data augmentations, and moreover, PathFusion also improves KITTI $\text{AP}_{\text{3D}}$ (R11) by about 0.6% on the moderate level.
Authors: Karol Gotkowski, Shuvam Gupta, Jose R. A. Godinho, Camila G. S. Tochtrop, Klaus H. Maier-Hein, Fabian Isensee
Minerals, metals, and plastics are indispensable for a functioning modern society. Yet, their supply is limited causing a need for optimizing ore extraction and recuperation from recyclable materials.Typically, those processes must be meticulously adapted to the precise properties of the processed materials. Advancing our understanding of these materials is thus vital and can be achieved by crushing them into particles of micrometer size followed by their characterization. Current imaging approaches perform this analysis based on segmentation and characterization of particles imaged with computed tomography (CT), and rely on rudimentary postprocessing techniques to separate touching particles. However, their inability to reliably perform this separation as well as the need to retrain methods for each new image, these approaches leave untapped potential to be leveraged. Here, we propose ParticleSeg3D, an instance segmentation method able to extract individual particles from large CT images of particle samples containing different materials. Our approach is based on the powerful nnU-Net framework, introduces a particle size normalization, uses a border-core representation to enable instance segmentation, and is trained with a large dataset containing particles of numerous different sizes, shapes, and compositions of various materials. We demonstrate that ParticleSeg3D can be applied out-of-the-box to a large variety of particle types, including materials and appearances that have not been part of the training set. Thus, no further manual annotations and retraining are required when applying the method to new particle samples, enabling substantially higher scalability of experiments than existing methods. Our code and dataset are made publicly available.
Authors: Zhou Yu, Xuecheng Ouyang, Zhenwei Shao, Meng Wang, Jun Yu
Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question. Early studies retrieve required knowledge from explicit knowledge bases (KBs), which often introduces irrelevant information to the question, hence restricting the performance of their models. Recent works have resorted to using a powerful large language model (LLM) as an implicit knowledge engine to acquire the necessary knowledge for answering. Despite the encouraging results achieved by these methods, we argue that they have not fully activated the capacity of the blind LLM as the provided textual input is insufficient to depict the required visual information to answer the question. In this paper, we present Prophet -- a conceptually simple, flexible, and general framework designed to prompt LLM with answer heuristics for knowledge-based VQA. Specifically, we first train a vanilla VQA model on a specific knowledge-based VQA dataset without external knowledge. After that, we extract two types of complementary answer heuristics from the VQA model: answer candidates and answer-aware examples. Finally, the two types of answer heuristics are jointly encoded into a formatted prompt to facilitate the LLM's understanding of both the image and question, thus generating a more accurate answer. By incorporating the state-of-the-art LLM GPT-3, Prophet significantly outperforms existing state-of-the-art methods on four challenging knowledge-based VQA datasets. To demonstrate the generality of our approach, we instantiate Prophet with the combinations of different VQA models (i.e., both discriminative and generative ones) and different LLMs (i.e., both commercial and open-source ones).
Authors: Zhonghua Wu, Yicheng Wu, Guosheng Lin, Jianfei Cai
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://github.com/wu-zhonghua/RAC-Net.
Authors: Marc Windsheimer, Fabian Brand, André Kaup
Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of the encoding transform. This issue can be resolved by using invertible latent variable models, which allow a perfect reconstruction if no quantization is performed. Furthermore, many traditional image and video coders apply dynamic block partitioning to vary the compression of certain image regions depending on their content. Inspired by this approach, hierarchical latent spaces have been applied to learning-based compression networks. In this paper, we present a novel concept, which adapts the hierarchical latent space for augmented normalizing flows, an invertible latent variable model. Our best performing model achieved average rate savings of more than 7% over comparable single-scale models.
Authors: Jialin Yuan, Ye Yu, Gaurav Mittal, Matthew Hall, Sandra Sajeev, Mei Chen
There is a rapidly growing need for multimodal content moderation (CM) as more and more content on social media is multimodal in nature. Existing unimodal CM systems may fail to catch harmful content that crosses modalities (e.g., memes or videos), which may lead to severe consequences. In this paper, we present a novel CM model, Asymmetric Mixed-Modal Moderation (AM3), to target multimodal and unimodal CM tasks. Specifically, to address the asymmetry in semantics between vision and language, AM3 has a novel asymmetric fusion architecture that is designed to not only fuse the common knowledge in both modalities but also to exploit the unique information in each modality. Unlike previous works that focus on representing the two modalities into a similar feature space while overlooking the intrinsic difference between the information conveyed in multimodality and in unimodality (asymmetry in modalities), we propose a novel cross-modality contrastive loss to learn the unique knowledge that only appears in multimodality. This is critical as some harmful intent may only be conveyed through the intersection of both modalities. With extensive experiments, we show that AM3 outperforms all existing state-of-the-art methods on both multimodal and unimodal CM benchmarks.
Authors: Ruichen Wang, Zekang Chen, Chen Chen, Jian Ma, Haonan Lu, Xiaodong Lin
Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending on the predicted boxes, a unique mask control is applied to the cross- and self-attention maps. Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image. In addition, the proposed method is straightforward and effective and can be readily integrated into existing cross-attention-based T2I generators. We compare our approach to competing methods and demonstrate that it can faithfully convey the semantics of the original text to the generated content and achieve high availability as a ready-to-use plugin. Please refer to https://github.com/OPPOMente-Lab/attention-mask-control.
Authors: Shitian He, Huanxin Zou, Yingqian Wang, Boyang Li, Xu Cao, Ning Jing
Pointly Supervised Object Detection (PSOD) has attracted considerable interests due to its lower labeling cost as compared to box-level supervised object detection. However, the complex scenes, densely packed and dynamic-scale objects in Remote Sensing (RS) images hinder the development of PSOD methods in RS field. In this paper, we make the first attempt to achieve RS object detection with single point supervision, and propose a PSOD method tailored for RS images. Specifically, we design a point label upgrader (PLUG) to generate pseudo box labels from single point labels, and then use the pseudo boxes to supervise the optimization of existing detectors. Moreover, to handle the challenge of the densely packed objects in RS images, we propose a sparse feature guided semantic prediction module which can generate high-quality semantic maps by fully exploiting informative cues from sparse objects. Extensive ablation studies on the DOTA dataset have validated the effectiveness of our method. Our method can achieve significantly better performance as compared to state-of-the-art image-level and point-level supervised detection methods, and reduce the performance gap between PSOD and box-level supervised object detection. Code is available at https://github.com/heshitian/PLUG.
Authors: Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Todd Zickler, Pratul P. Srinivasan
Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This problem is especially challenging for diffuse objects: it is ill-conditioned because diffuse materials severely blur incoming light, and it is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination -- even from diffuse objects -- by exploiting unintended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatially-varying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who inadvertently cast shadows upon it.
Authors: Kun Zhou, Wenbo Li, Nianjuan Jiang, Xiaoguang Han, Jiangbo Lu
Neural radiance fields (NeRF) have shown great success in novel view synthesis. However, recovering high-quality details from real-world scenes is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation inaccuracy. Even with high-quality training frames, the synthetic novel views produced by NeRF models still suffer from notable rendering artifacts, such as noise and blur. To address this, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm that learns a degradation-driven inter-viewpoint mixer. Specially, we design a NeRF-style degradation modeling approach and construct large-scale training data, enabling the possibility of effectively removing NeRF-native rendering artifacts for deep neural networks. Moreover, beyond the degradation removal, we propose an inter-viewpoint aggregation framework that fuses highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views. Based on this paradigm, we further present NeRFLiX++ with a stronger two-stage NeRF degradation simulator and a faster inter-viewpoint mixer, achieving superior performance with significantly improved computational efficiency. Notably, NeRFLiX++ is capable of restoring photo-realistic ultra-high-resolution outputs from noisy low-resolution NeRF-rendered views. Extensive experiments demonstrate the excellent restoration ability of NeRFLiX++ on various novel view synthesis benchmarks.
Authors: Mengke Li, Zhikai Hu, Yang Lu, Weichao Lan, Yiu-ming Cheung, Hui Huang
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://github.com/Keke921/H2T.
Authors: Ilija Radosavovic, Baifeng Shi, Letian Fu, Ken Goldberg, Trevor Darrell, Jitendra Malik
We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive robot states, and actions, we encode the sequence into tokens, mask out a subset, and train a model to predict the missing content from the rest. We hypothesize that if a robot can predict the masked-out content it will have acquired a good model of the physical world that can enable it to act. RPT is designed to operate on latent visual representations which makes prediction tractable, enables scaling to larger models, and allows fast inference on a real robot. To evaluate our approach, we collected a dataset of 20,000 real-world trajectories over 9 months using a combination of motion planning and grasping algorithms. We find that sensorimotor pre-training consistently outperforms training from scratch, has favorable scaling properties, and enables transfer across different tasks, environments, and robots.
Authors: Qirui Yang, Yihao Liu, Qihua Chen, Jingyu Yang
Denoising and high dynamic range (HDR) imaging are significant yet challenging problems due to the small aperture and sensor size of generic image sensors. Current methods predominantly generate HDR images from a set of bracketed exposure sRGB images. However, they overlook the computational and memory inefficiencies of the Image Signal Processor (ISP) when processing a set of sRGB images with different exposures. Furthermore, the absence of large-scale raw-based HDR datasets limits the research on HDR imaging. Unlike existing methods, the core idea of this work is to utilize the difference between short- and long-exposure images of signal-to-noise ratios to generate HDR images and denoising. To this end, we propose a model tailor-made for double-exposure HDR sensors, leveraging the unique features of the raw data to facilitate raw-to-HDR mapping and raw denoising. Our key insights are threefold: (1) a new computational raw LDR-HDR pair formation pipeline is designed to construct a real-world raw HDR dataset called RealRaw-HDR; (2) a lightweight-efficient HDR model, RepUNet, is developed using the structural reparameterization technique; (3) a plug-and-play alignment-free and motion-aware short-exposure-first selection loss and a colorfulness loss are proposed to mitigate ghost artifacts and color cast. Our empirical evaluation validates the effectiveness of the proposed LDR-HDR formation pipeline, as well as experiments show that our method achieves comparable performance to the state-of-the-art methods with less computational cost.
Authors: Luozhou Wang, Guibao Shen, Wenhang Ge, Guangyong Chen, Yijun Li, Ying-cong Chen
Text-to-image diffusion models have advanced towards more controllable generation via supporting various additional conditions (e.g., depth map, bounding box) beyond text. However, these models are learned based on the premise of perfect alignment between the text and extra conditions. If this alignment is not satisfied, the final output could be either dominated by one condition, or ambiguity may arise, failing to meet user expectations.To address this issue, we present a training-free approach called ``Decompose and Realign'' to further improve the controllability of existing models when provided with partially aligned conditions. The ``Decompose'' phase separates conditions based on pair relationships, computing the result individually for each pair. This ensures that each pair no longer has conflicting conditions. The ``Realign'' phase aligns these independently calculated results via a cross-attention mechanism to avoid new conflicts when combining them back. Both qualitative and quantitative results demonstrate the effectiveness of our approach in handling unaligned conditions, which performs favorably against recent methods and more importantly adds flexibility to the controllable image generation process. Our code will be available at: https://github.com/EnVision-Research/Decompose-and-Realign.
Authors: Ziqing Wang, Qidong Zhao, Jinku Cui, Xu Liu, Dongkuan Xu
Spiking Transformers have gained considerable attention because they achieve both the energy efficiency of Spiking Neural Networks (SNNs) and the high capacity of Transformers. However, the existing Spiking Transformer architectures, derived from Artificial Neural Networks (ANNs), exhibit a notable architectural gap, resulting in suboptimal performance compared to their ANN counterparts. Manually discovering optimal architectures is time-consuming. To address these limitations, we introduce AutoST, a training-free NAS method for Spiking Transformers, to rapidly identify high-performance Spiking Transformer architectures. Unlike existing training-free NAS methods, which struggle with the non-differentiability and high sparsity inherent in SNNs, we propose to utilize Floating-Point Operations (FLOPs) as a performance metric, which is independent of model computations and training dynamics, leading to a stronger correlation with performance. Our extensive experiments show that AutoST models outperform state-of-the-art manually or automatically designed SNN architectures on static and neuromorphic datasets. Full code, model, and data are released for reproduction.
Authors: Shengyi Gao, Zhe Chen, Guo Chen, Wenhai Wang, Tong Lu
The combination of audio and vision has long been a topic of interest in the multi-modal community. Recently, a new audio-visual segmentation (AVS) task has been introduced, aiming to locate and segment the sounding objects in a given video. This task demands audio-driven pixel-level scene understanding for the first time, posing significant challenges. In this paper, we propose AVSegFormer, a novel framework for AVS tasks that leverages the transformer architecture. Specifically, we introduce audio queries and learnable queries into the transformer decoder, enabling the network to selectively attend to interested visual features. Besides, we present an audio-visual mixer, which can dynamically adjust visual features by amplifying relevant and suppressing irrelevant spatial channels. Additionally, we devise an intermediate mask loss to enhance the supervision of the decoder, encouraging the network to produce more accurate intermediate predictions. Extensive experiments demonstrate that AVSegFormer achieves state-of-the-art results on the AVS benchmark. The code is available at https://github.com/vvvb-github/AVSegFormer.
Authors: Yuxiang Zhang, Hongwen Zhang, Liangxiao Hu, Jiajun Zhang, Hongwei Yi, Shengping Zhang, Yebin Liu
Learning-based approaches to monocular motion capture have recently shown promising results by learning to regress in a data-driven manner. However, due to the challenges in data collection and network designs, it remains challenging for existing solutions to achieve real-time full-body capture while being accurate in world space. In this work, we introduce ProxyCap, a human-centric proxy-to-motion learning scheme to learn world-space motions from a proxy dataset of 2D skeleton sequences and 3D rotational motions. Such proxy data enables us to build a learning-based network with accurate world-space supervision while also mitigating the generalization issues. For more accurate and physically plausible predictions in world space, our network is designed to learn human motions from a human-centric perspective, which enables the understanding of the same motion captured with different camera trajectories. Moreover, a contact-aware neural motion descent module is proposed in our network so that it can be aware of foot-ground contact and motion misalignment with the proxy observations. With the proposed learning-based solution, we demonstrate the first real-time monocular full-body capture system with plausible foot-ground contact in world space even using hand-held moving cameras.
Authors: Maxime Di Folco, Cosmin Bercea, Julia A. Schnabel
Deep generative models have emerged as influential instruments for data generation and manipulation. Enhancing the controllability of these models by selectively modifying data attributes has been a recent focus. Variational Autoencoders (VAEs) have shown promise in capturing hidden attributes but often produce blurry reconstructions. Controlling these attributes through different imaging domains is difficult in medical imaging. Recently, Soft Introspective VAE leverage the benefits of both VAEs and Generative Adversarial Networks (GANs), which have demonstrated impressive image synthesis capabilities, by incorporating an adversarial loss into VAE training. In this work, we propose the Attributed Soft Introspective VAE (Attri-SIVAE) by incorporating an attribute regularized loss, into the Soft-Intro VAE framework. We evaluate experimentally the proposed method on cardiac MRI data from different domains, such as various scanner vendors and acquisition centers. The proposed method achieves similar performance in terms of reconstruction and regularization compared to the state-of-the-art Attributed regularized VAE but additionally also succeeds in keeping the same regularization level when tested on a different dataset, unlike the compared method.
Authors: Ping Hu, Ximeng Sun, Stan Sclaroff, Kate Saenko
Multi-label image recognition in the low-label regime is a task of great challenge and practical significance. Previous works have focused on learning the alignment between textual and visual spaces to compensate for limited image labels, yet may suffer from reduced accuracy due to the scarcity of high-quality multi-label annotations. In this research, we leverage the powerful alignment between textual and visual features pretrained with millions of auxiliary image-text pairs. We introduce an efficient and effective framework called Evidence-guided Dual Context Optimization (DualCoOp++), which serves as a unified approach for addressing partial-label and zero-shot multi-label recognition. In DualCoOp++ we separately encode evidential, positive, and negative contexts for target classes as parametric components of the linguistic input (i.e., prompts). The evidential context aims to discover all the related visual content for the target class, and serves as guidance to aggregate positive and negative contexts from the spatial domain of the image, enabling better distinguishment between similar categories. Additionally, we introduce a Winner-Take-All module that promotes inter-class interaction during training, while avoiding the need for extra parameters and costs. As DualCoOp++ imposes minimal additional learnable overhead on the pretrained vision-language framework, it enables rapid adaptation to multi-label recognition tasks with limited annotations and even unseen classes. Experiments on standard multi-label recognition benchmarks across two challenging low-label settings demonstrate the superior performance of our approach compared to state-of-the-art methods.
Authors: Tariq Berrada, Camille Couprie, Karteek Alahari, Jakob Verbeek
Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain. To alleviate this reliance, and boost results, semi-supervised approaches leverage unlabeled data as an additional training signal that limits overfitting to the labeled samples. In this context, we present novel design choices to significantly improve teacher-student distillation models. In particular, we (i) improve the distillation approach by introducing a novel "guided burn-in" stage, and (ii) evaluate different instance segmentation architectures, as well as backbone networks and pre-training strategies. Contrary to previous work which uses only supervised data for the burn-in period of the student model, we also use guidance of the teacher model to exploit unlabeled data in the burn-in period. Our improved distillation approach leads to substantial improvements over previous state-of-the-art results. For example, on the Cityscapes dataset we improve mask-AP from 23.7 to 33.9 when using labels for 10\% of images, and on the COCO dataset we improve mask-AP from 18.3 to 34.1 when using labels for only 1\% of the training data.
Authors: Xuefeng Hu, Ke Zhang, Lu Xia, Albert Chen, Jiajia Luo, Yuyin Sun, Ken Wang, Nan Qiao, Xiao Zeng, Min Sun, Cheng-Hao Kuo, Ram Nevatia
Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data. However, while applying CLIP to a downstream target domain, the presence of visual and text domain gaps and cross-modality misalignment can greatly impact the model performance. To address such challenges, we propose ReCLIP, the first source-free domain adaptation method for vision-language models, which does not require any source data or target labeled data. ReCLIP first learns a projection space to mitigate the misaligned visual-text embeddings and learns pseudo labels, and then deploys cross-modality self-training with the pseudo labels, to update visual and text encoders, refine labels and reduce domain gaps and misalignments iteratively. With extensive experiments, we demonstrate ReCLIP reduces the average error rate of CLIP from 30.17% to 25.06% on 22 image classification benchmarks. Code available at https://github.com/michiganleon/ReCLIP_WACV.
Authors: Heng Wang, Jianbo Ma, Santiago Pascual, Richard Cartwright, Weidong Cai
Building artificial intelligence (AI) systems on top of a set of foundation models (FMs) is becoming a new paradigm in AI research. Their representative and generative abilities learnt from vast amounts of data can be easily adapted and transferred to a wide range of downstream tasks without extra training from scratch. However, leveraging FMs in cross-modal generation remains under-researched when audio modality is involved. On the other hand, automatically generating semantically-relevant sound from visual input is an important problem in cross-modal generation studies. To solve this vision-to-audio (V2A) generation problem, existing methods tend to design and build complex systems from scratch using modestly sized datasets. In this paper, we propose a lightweight solution to this problem by leveraging foundation models, specifically CLIP, CLAP, and AudioLDM. We first investigate the domain gap between the latent space of the visual CLIP and the auditory CLAP models. Then we propose a simple yet effective mapper mechanism (V2A-Mapper) to bridge the domain gap by translating the visual input between CLIP and CLAP spaces. Conditioned on the translated CLAP embedding, pretrained audio generative FM AudioLDM is adopted to produce high-fidelity and visually-aligned sound. Compared to previous approaches, our method only requires a quick training of the V2A-Mapper. We further analyze and conduct extensive experiments on the choice of the V2A-Mapper and show that a generative mapper is better at fidelity and variability (FD) while a regression mapper is slightly better at relevance (CS). Both objective and subjective evaluation on two V2A datasets demonstrate the superiority of our proposed method compared to current state-of-the-art approaches - trained with 86% fewer parameters but achieving 53% and 19% improvement in FD and CS, respectively.
Authors: Yubin Hu, Sheng Ye, Wang Zhao, Matthieu Lin, Yuze He, Yu-Hui Wen, Ying He, Yong-Jin Liu
Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propose a novel framework, empowered by a 2D diffusion-based in-painting model, to reconstruct complete surfaces for the hidden parts of objects. Specifically, we utilize a pre-trained diffusion model to fill in the hidden areas of 2D images. Then we use these in-painted images to optimize a neural implicit surface representation for each instance for 3D reconstruction. Since creating the in-painting masks needed for this process is tricky, we adopt a human-in-the-loop strategy that involves very little human engagement to generate high-quality masks. Moreover, some parts of objects can be totally hidden because the videos are usually shot from limited perspectives. To ensure recovering these invisible areas, we develop a cascaded network architecture for predicting signed distance field, making use of different frequency bands of positional encoding and maintaining overall smoothness. Besides the commonly used rendering loss, Eikonal loss, and silhouette loss, we adopt a CLIP-based semantic consistency loss to guide the surface from unseen camera angles. Experiments on ScanNet scenes show that our proposed framework achieves state-of-the-art accuracy and completeness in object-level reconstruction from scene-level RGB-D videos. Code: https://github.com/THU-LYJ-Lab/O2-Recon.
Authors: Xin Ding, Yongwei Wang, Zuheng Xu
Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can produce subpar fake images due to limited training data. Although Negative Data Augmentation (NDA) effectively enhances unconditional and class-conditional GANs by introducing anomalies into real training images, guiding the GANs away from low-quality outputs, its impact on CcGANs is limited, as it fails to replicate negative samples that may occur during the CcGAN sampling. We present a novel NDA approach called Dual-NDA specifically tailored for CcGANs to address this problem. Dual-NDA employs two types of negative samples: visually unrealistic images generated from a pre-trained CcGAN and label-inconsistent images created by manipulating real images' labels. Leveraging these negative samples, we introduce a novel discriminator objective alongside a modified CcGAN training algorithm. Empirical analysis on UTKFace and Steering Angle reveals that Dual-NDA consistently enhances the visual fidelity and label consistency of fake images generated by CcGANs, exhibiting a substantial performance gain over the vanilla NDA. Moreover, by applying Dual-NDA, CcGANs demonstrate a remarkable advancement beyond the capabilities of state-of-the-art conditional GANs and diffusion models, establishing a new pinnacle of performance. Our codes can be found at https://github.com/UBCDingXin/Dual-NDA.
Authors: Yifei Su, Dong An, Yuan Xu, Kehan Chen, Yan Huang
This report details the methods of the winning entry of the AVDN Challenge in ICCV CLVL 2023. The competition addresses the Aerial Navigation from Dialog History (ANDH) task, which requires a drone agent to associate dialog history with aerial observations to reach the destination. For better cross-modal grounding abilities of the drone agent, we propose a Target-Grounded Graph-Aware Transformer (TG-GAT) framework. Concretely, TG-GAT first leverages a graph-aware transformer to capture spatiotemporal dependency, which benefits navigation state tracking and robust action planning. In addition,an auxiliary visual grounding task is devised to boost the agent's awareness of referred landmarks. Moreover, a hybrid augmentation strategy based on large language models is utilized to mitigate data scarcity limitations. Our TG-GAT framework won the AVDN Challenge, with 2.2% and 3.0% absolute improvements over the baseline on SPL and SR metrics, respectively. The code is available at https://github.com/yifeisu/TG-GAT.
Authors: Jingchun Zhou, Zongxin He, Kin-Man Lam, Yudong Wang, Weishi Zhang, ChunLe Guo, Chongyi Li
In this paper, we present a novel Amplitude-Modulated Stochastic Perturbation and Vortex Convolutional Network, AMSP-UOD, designed for underwater object detection. AMSP-UOD specifically addresses the impact of non-ideal imaging factors on detection accuracy in complex underwater environments. To mitigate the influence of noise on object detection performance, we propose AMSP Vortex Convolution (AMSP-VConv) to disrupt the noise distribution, enhance feature extraction capabilities, effectively reduce parameters, and improve network robustness. We design the Feature Association Decoupling Cross Stage Partial (FAD-CSP) module, which strengthens the association of long and short range features, improving the network performance in complex underwater environments. Additionally, our sophisticated post-processing method, based on Non-Maximum Suppression (NMS) with aspect-ratio similarity thresholds, optimizes detection in dense scenes, such as waterweed and schools of fish, improving object detection accuracy. Extensive experiments on the URPC and RUOD datasets demonstrate that our method outperforms existing state-of-the-art methods in terms of accuracy and noise immunity. AMSP-UOD proposes an innovative solution with the potential for real-world applications. Our code is available at https://github.com/zhoujingchun03/AMSP-UOD.
Authors: Dehuan Zhang, Jingchun Zhou, ChunLe Guo, Weishi Zhang, Chongyi Li
Visually restoring underwater scenes primarily involves mitigating interference from underwater media. Existing methods ignore the inherent scale-related characteristics in underwater scenes. Therefore, we present the synergistic multi-scale detail refinement via intrinsic supervision (SMDR-IS) for enhancing underwater scene details, which contain multi-stages. The low-degradation stage from the original images furnishes the original stage with multi-scale details, achieved through feature propagation using the Adaptive Selective Intrinsic Supervised Feature (ASISF) module. By using intrinsic supervision, the ASISF module can precisely control and guide feature transmission across multi-degradation stages, enhancing multi-scale detail refinement and minimizing the interference from irrelevant information in the low-degradation stage. In multi-degradation encoder-decoder framework of SMDR-IS, we introduce the Bifocal Intrinsic-Context Attention Module (BICA). Based on the intrinsic supervision principles, BICA efficiently exploits multi-scale scene information in images. BICA directs higher-resolution spaces by tapping into the insights of lower-resolution ones, underscoring the pivotal role of spatial contextual relationships in underwater image restoration. Throughout training, the inclusion of a multi-degradation loss function can enhance the network, allowing it to adeptly extract information across diverse scales. When benchmarked against state-of-the-art methods, SMDR-IS consistently showcases superior performance. The code is publicly available at: https://github.com/zhoujingchun03/SMDR-IS.
Authors: Huaxin Zhang, Xiang Wang, Xiaohao Xu, Zhiwu Qing, Changxin Gao, Nong Sang
Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully supervised methods. Code will be available at https://github.com/pipixin321/HR-Pro.
Authors: Shuning Xu, Binbin Song, Xiangyu Chen, Jiantao Zhou
Moire patterns occur when capturing images or videos on screens, severely degrading the quality of the captured images or videos. Despite the recent progresses, existing video demoireing methods neglect the physical characteristics and formation process of moire patterns, significantly limiting the effectiveness of video recovery. This paper presents a unified framework, DTNet, a direction-aware and temporal-guided bilateral learning network for video demoireing. DTNet effectively incorporates the process of moire pattern removal, alignment, color correction, and detail refinement. Our proposed DTNet comprises two primary stages: Frame-level Direction-aware Demoireing and Alignment (FDDA) and Tone and Detail Refinement (TDR). In FDDA, we employ multiple directional DCT modes to perform the moire pattern removal process in the frequency domain, effectively detecting the prominent moire edges. Then, the coarse and fine-grained alignment is applied on the demoired features for facilitating the utilization of neighboring information. In TDR, we propose a temporal-guided bilateral learning pipeline to mitigate the degradation of color and details caused by the moire patterns while preserving the restored frequency information in FDDA. Guided by the aligned temporal features from FDDA, the affine transformations for the recovery of the ultimate clean frames are learned in TDR. Extensive experiments demonstrate that our video demoireing method outperforms state-of-the-art approaches by 2.3 dB in PSNR, and also delivers a superior visual experience. Our code is available at https://github.com/rebeccaeexu/DTNet.
Authors: Shengji Tang, Peng Ye, Baopu Li, Weihao Lin, Tao Chen, Tong He, Chong Yu, Wanli Ouyang
Recent research understands the residual networks from a new perspective of the implicit ensemble model. From this view, previous methods such as stochastic depth and stimulative training have further improved the performance of the residual network by sampling and training of its subnets. However, they both use the same supervision for all subnets of different capacities and neglect the valuable knowledge generated by subnets during training. In this manuscript, we mitigate the significant knowledge distillation gap caused by using the same kind of supervision and advocate leveraging the subnets to provide diverse knowledge. Based on this motivation, we propose a group knowledge based training framework for boosting the performance of residual networks. Specifically, we implicitly divide all subnets into hierarchical groups by subnet-in-subnet sampling, aggregate the knowledge of different subnets in each group during training, and exploit upper-level group knowledge to supervise lower-level subnet groups. Meanwhile, We also develop a subnet sampling strategy that naturally samples larger subnets, which are found to be more helpful than smaller subnets in boosting performance for hierarchical groups. Compared with typical subnet training and other methods, our method achieves the best efficiency and performance trade-offs on multiple datasets and network structures. The code is at https://github.com/tsj-001/AAAI24-GKT.
Authors: Yang Liu, Cheng Yu, Lei Shang, Yongyi He, Ziheng Wu, Xingjun Wang, Chao Xu, Haoyu Xie, Weida Wang, Yuze Zhao, Lin Zhu, Chen Cheng, Weitao Chen, Yuan Yao, Wenmeng Zhou, Jiaqi Xu, Qiang Wang, Yingda Chen, Xuansong Xie, Baigui Sun
Recent advancement in personalized image generation have unveiled the intriguing capability of pre-trained text-to-image models on learning identity information from a collection of portrait images. However, existing solutions are vulnerable in producing truthful details, and usually suffer from several defects such as (i) The generated face exhibit its own unique characteristics, \ie facial shape and facial feature positioning may not resemble key characteristics of the input, and (ii) The synthesized face may contain warped, blurred or corrupted regions. In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input. Concretely, we inject several SOTA face models into the generation procedure, achieving a more efficient label-tagging, data-processing, and model post-processing compared to previous solutions, such as DreamBooth ~\cite{ruiz2023dreambooth} , InstantBooth ~\cite{shi2023instantbooth} , or other LoRA-only approaches ~\cite{hu2021lora} . Besides, based on FaceChain, we further develop several applications to build a broader playground for better showing its value, including virtual try on and 2D talking head. We hope it can grow to serve the burgeoning needs from the communities. Note that this is an ongoing work that will be consistently refined and improved upon. FaceChain is open-sourced under Apache-2.0 license at \url{https://github.com/modelscope/facechain}.
Authors: Xuyang Liu, Siteng Huang, Yachen Kang, Honggang Chen, Donglin Wang
Large-scale text-to-image diffusion models have shown impressive capabilities for generative tasks by leveraging strong vision-language alignment from pre-training. However, most vision-language discriminative tasks require extensive fine-tuning on carefully-labeled datasets to acquire such alignment, with great cost in time and computing resources. In this work, we explore directly applying a pre-trained generative diffusion model to the challenging discriminative task of visual grounding without any fine-tuning and additional training dataset. Specifically, we propose VGDiffZero, a simple yet effective zero-shot visual grounding framework based on text-to-image diffusion models. We also design a comprehensive region-scoring method considering both global and local contexts of each isolated proposal. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg show that VGDiffZero achieves strong performance on zero-shot visual grounding. Our code is available at https://github.com/xuyang-liu16/VGDiffZero.
Authors: Ting Liu, Yue Hu, Wansen Wu, Youkai Wang, Kai Xu, Quanjun Yin
Pretrained visual-language models have extensive world knowledge and are widely used in visual and language navigation (VLN). However, they are not sensitive to indoor scenarios for VLN tasks. Another challenge for VLN is how the agent understands the contextual relations between actions on a path and performs cross-modal alignment sequentially. In this paper, we propose a novel Prompt-bAsed coNtext- and inDoor-Aware (PANDA) pretraining framework to address these problems. It performs prompting in two stages. In the indoor-aware stage, we apply an efficient tuning paradigm to learn deep visual prompts from an indoor dataset, in order to augment pretrained models with inductive biases towards indoor environments. This can enable more sample-efficient adaptation for VLN agents. Furthermore, in the context-aware stage, we design a set of hard context prompts to capture the sequence-level semantics in the instruction. They enable further tuning of the pretrained models via contrastive learning. Experimental results on both R2R and REVERIE show the superiority of PANDA compared to existing state-of-the-art methods.
Authors: Xin Wang, Ziwei Luo, Jing Hu, Chengming Feng, Shu Hu, Bin Zhu, Xi Wu, Siwei Lyu
Most existing Image-to-Image Translation (I2IT) methods generate images in a single run of a deep learning (DL) model. However, designing such a single-step model is always challenging, requiring a huge number of parameters and easily falling into bad global minimums and overfitting. In this work, we reformulate I2IT as a step-wise decision-making problem via deep reinforcement learning (DRL) and propose a novel framework that performs RL-based I2IT (RL-I2IT). The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image. Considering that it is challenging to handle high dimensional continuous state and action spaces in the conventional RL framework, we introduce meta policy with a new concept Plan to the standard Actor-Critic model, which is of a lower dimension than the original image and can facilitate the actor to generate a tractable high dimensional action. In the RL-I2IT framework, we also employ a task-specific auxiliary learning strategy to stabilize the training process and improve the performance of the corresponding task. Experiments on several I2IT tasks demonstrate the effectiveness and robustness of the proposed method when facing high-dimensional continuous action space problems.
Authors: Pan Zhang, Xiaoyi Dong, Bin Wang, Yuhang Cao, Chao Xu, Linke Ouyang, Zhiyuan Zhao, Haodong Duan, Songyang Zhang, Shuangrui Ding, Wenwei Zhang, Hang Yan, Xinyue Zhang, Wei Li, Jingwen Li, Kai Chen, Conghui He, Xingcheng Zhang, Yu Qiao, Dahua Lin, Jiaqi Wang
We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition. The innovative nature of our model is highlighted by three appealing properties: 1) Interleaved Text-Image Composition: InternLM-XComposer can effortlessly generate coherent and contextual articles that seamlessly integrate images, providing a more engaging and immersive reading experience. Simply provide a writing instruction, and our system will generate the corresponding manuscript. It can intelligently identify the areas in the text where images would enhance the content and automatically insert the most appropriate visual candidates. 2) Comprehension with Rich Multilingual Knowledge: The text-image comprehension is empowered by training on an extensive multi-modal multilingual database with carefully crafted strategies, resulting in a deep understanding of visual content. 3) State-of-the-art Performance: Our model consistently achieves state-of-the-art results across various mainstream benchmarks for vision-language foundational models, including MME Benchmark, MMBench, MMBench-CN, Seed-Bench, CCBench (Chinese Cultural Benchmark), QBench and Tiny LVLM. Owing to the absence of established metrics for quantitatively assessing text-image composition, we have devised a robust evaluation procedure that comprises both human and GPT4-Vision (GPT4-V) to ensure reliability. Notably, our InternLM-XComposer achieves competitive text-image composition scores compared to public solutions, including GPT4-V and GPT3.5. Collectively, InternLM-XComposer seamlessly blends advanced text-image comprehension and composition, revolutionizing vision-language interaction and offering new insights and opportunities. The InternLM-XComposer model series are publicly available at https://github.com/InternLM/InternLM-XComposer.
Authors: Athanasios Masouris, Jan van Gemert
Chess recognition is the task of extracting the chess piece configuration from a chessboard image. Current approaches use a pipeline of separate, independent, modules such as chessboard detection, square localization, and piece classification. Instead, we follow the deep learning philosophy and explore an end-to-end approach to directly predict the configuration from the image, thus avoiding the error accumulation of the sequential approaches and eliminating the need for intermediate annotations. Furthermore, we introduce a new dataset, Chess Recognition Dataset (ChessReD), that consists of 10,800 real photographs and their corresponding annotations. In contrast to existing datasets that are synthetically rendered and have only limited angles, ChessReD has photographs captured from various angles using smartphone cameras; a sensor choice made to ensure real-world applicability. Our approach in chess recognition on the introduced challenging benchmark dataset outperforms related approaches, successfully recognizing the chess pieces' configuration in 15.26% of ChessReD's test images. This accuracy may seem low, but it is ~7x better than the current state-of-the-art and reflects the difficulty of the problem. The code and data are available through: https://github.com/ThanosM97/end-to-end-chess-recognition.
Authors: Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, Tianshu Yu
Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (e.g., language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved. To alleviate this, we present Adaptive Language-guided Multimodal Transformer (ALMT), which incorporates an Adaptive Hyper-modality Learning (AHL) module to learn an irrelevance/conflict-suppressing representation from visual and audio features under the guidance of language features at different scales. With the obtained hyper-modality representation, the model can obtain a complementary and joint representation through multimodal fusion for effective MSA. In practice, ALMT achieves state-of-the-art performance on several popular datasets (e.g., MOSI, MOSEI and CH-SIMS) and an abundance of ablation demonstrates the validity and necessity of our irrelevance/conflict suppression mechanism.
Authors: Lukas Struppek, Martin B. Hentschel, Clifton Poth, Dominik Hintersdorf, Kristian Kersting
Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to inconspicuous behavior. However, once a specific trigger pattern appears in the input data, the backdoor activates, causing the model to execute its concealed function. Detecting such poisoned samples within vast datasets is virtually impossible through manual inspection. To address this challenge, we propose a novel approach that enables model training on potentially poisoned datasets by utilizing the power of recent diffusion models. Specifically, we create synthetic variations of all training samples, leveraging the inherent resilience of diffusion models to potential trigger patterns in the data. By combining this generative approach with knowledge distillation, we produce student models that maintain their general performance on the task while exhibiting robust resistance to backdoor triggers.
Authors: Hongbin Xu, Yamei Xia, Shuai Zhao, Bo Cheng
Query-based methods have garnered significant attention in object detection since the advent of DETR, the pioneering query-based detector. However, these methods face challenges like slow convergence and suboptimal performance. Notably, self-attention in object detection often hampers convergence due to its global focus. To address these issues, we propose FoLR, a transformer-like architecture with only decoders. We improve the self-attention by isolating connections between irrelevant objects that makes it focus on local regions but not global regions. We also design the adaptive sampling method to extract effective features based on queries' local regions from feature maps. Additionally, we employ a look-back strategy for decoders to retain previous information, followed by the Feature Mixer module to fuse features and queries. Experimental results demonstrate FoLR's state-of-the-art performance in query-based detectors, excelling in convergence speed and computational efficiency.
Index Terms: Local regions, Attention mechanism, Object detection
Authors: Xidong Peng, Runnan Chen, Feng Qiao, Lingdong Kong, Youquan Liu, Tai Wang, Xinge Zhu, Yuexin Ma
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes obvious across varying capture scenes, fluctuating weather conditions, and the diverse array of LiDAR devices in use. While previous UDA methodologies have often sought to mitigate this gap by aligning features between source and target domains, this approach falls short when applied to 3D segmentation due to the substantial domain variations. Inspired by the remarkable generalization capabilities exhibited by the vision foundation model, SAM, in the realm of image segmentation, our approach leverages the wealth of general knowledge embedded within SAM to unify feature representations across diverse 3D domains and further solves the 3D domain adaptation problem. Specifically, we harness the corresponding images associated with point clouds to facilitate knowledge transfer and propose an innovative hybrid feature augmentation methodology, which significantly enhances the alignment between the 3D feature space and SAM's feature space, operating at both the scene and instance levels. Our method is evaluated on many widely-recognized datasets and achieves state-of-the-art performance.
Authors: Sergio Calvo-Ordonez, Jiahao Huang, Lipei Zhang, Guang Yang, Carola-Bibiane Schonlieb, Angelica I Aviles-Rivero
Diffusion models are a family of generative models that yield record-breaking performance in tasks such as image synthesis, video generation, and molecule design. Despite their capabilities, their efficiency, especially in the reverse denoising process, remains a challenge due to slow convergence rates and high computational costs. In this work, we introduce an approach that leverages continuous dynamical systems to design a novel denoising network for diffusion models that is more parameter-efficient, exhibits faster convergence, and demonstrates increased noise robustness. Experimenting with denoising probabilistic diffusion models, our framework operates with approximately a quarter of the parameters and $\sim 30\%$ of the Floating Point Operations (FLOPs) compared to standard U-Nets in Denoising Diffusion Probabilistic Models (DDPMs). Furthermore, our model is faster in inference than the baseline models when measured in equal conditions while converging to better quality solutions.
Authors: Zhouqiang Jiang, Bowen Wang, Tong Xiang, Zhaofeng Niu, Hong Tang, Guangshun Li, Liangzhi Li
Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning. For the input sequence of video frames, CatMAE keeps the initial frame unchanged while applying substantial masking (95%) to subsequent frames. The encoder in CatMAE is responsible for encoding visible patches for each frame individually; subsequently, for each masked frame, the decoder leverages visible patches from both previous and current frames to reconstruct the original image. Our proposed method enables the model to estimate the motion information between visible patches, match the correspondences between preceding and succeeding frames, and ultimately learn the evolution of scenes. Furthermore, we propose a new data augmentation strategy, Video-Reverse (ViRe), which uses reversed video frames as the model's reconstruction targets. This further encourages the model to utilize continuous motion details and correspondences to complete the reconstruction, thereby enhancing the model's capabilities. Compared to the most advanced pre-training methods, CatMAE achieves a leading level in video segmentation tasks and action recognition tasks.
Authors: Holly Dinkel, Julia Di, Jamie Santos, Keenan Albee, Paulo Borges, Marina Moreira, Oleg Alexandrov, Brian Coltin, Trey Smith
Assistive free-flyer robots autonomously caring for future crewed outposts -- such as NASA's Astrobee robots on the International Space Station (ISS) -- must be able to detect day-to-day interior changes to track inventory, detect and diagnose faults, and monitor the outpost status. This work presents a framework for multi-agent cooperative mapping and change detection to enable robotic maintenance of space outposts. One agent is used to reconstruct a 3D model of the environment from sequences of images and corresponding depth information. Another agent is used to periodically scan the environment for inconsistencies against the 3D model. Change detection is validated after completing the surveys using real image and pose data collected by Astrobee robots in a ground testing environment and from microgravity aboard the ISS. This work outlines the objectives, requirements, and algorithmic modules for the multi-agent reconstruction system, including recommendations for its use by assistive free-flyers aboard future microgravity outposts.
*Denotes Equal Contribution
Authors: Neng Dong, Shuanglin Yan, Hao Tang, Jinhui Tang, Liyan Zhang
Occluded person re-identification (re-ID) presents a challenging task due to occlusion perturbations. Although great efforts have been made to prevent the model from being disturbed by occlusion noise, most current solutions only capture information from a single image, disregarding the rich complementary information available in multiple images depicting the same pedestrian. In this paper, we propose a novel framework called Multi-view Information Integration and Propagation (MVI$^{2}$P). Specifically, realizing the potential of multi-view images in effectively characterizing the occluded target pedestrian, we integrate feature maps of which to create a comprehensive representation. During this process, to avoid introducing occlusion noise, we develop a CAMs-aware Localization module that selectively integrates information contributing to the identification. Additionally, considering the divergence in the discriminative nature of different images, we design a probability-aware Quantification module to emphatically integrate highly reliable information. Moreover, as multiple images with the same identity are not accessible in the testing stage, we devise an Information Propagation (IP) mechanism to distill knowledge from the comprehensive representation to that of a single occluded image. Extensive experiments and analyses have unequivocally demonstrated the effectiveness and superiority of the proposed MVI$^{2}$P. The code will be released at \url{https://github.com/nengdong96/MVIIP}.
Authors: Yingjie Niu, Ming Ding, Keisuke Fujii, Kento Ohtani, Alexander Carballo, Kazuya Takeda
Traffic accidents frequently lead to fatal injuries, contributing to over 50 million deaths until 2023. To mitigate driving hazards and ensure personal safety, it is crucial to assist vehicles in anticipating important objects during travel. Previous research on important object detection primarily assessed the importance of individual participants, treating them as independent entities and frequently overlooking the connections between these participants. Unfortunately, this approach has proven less effective in detecting important objects in complex scenarios. In response, we introduce Driving scene Relationship self-Understanding transformer (DRUformer), designed to enhance the important object detection task. The DRUformer is a transformer-based multi-modal important object detection model that takes into account the relationships between all the participants in the driving scenario. Recognizing that driving intention also significantly affects the detection of important objects during driving, we have incorporated a module for embedding driving intention. To assess the performance of our approach, we conducted a comparative experiment on the DRAMA dataset, pitting our model against other state-of-the-art (SOTA) models. The results demonstrated a noteworthy 16.2\% improvement in mIoU and a substantial 12.3\% boost in ACC compared to SOTA methods. Furthermore, we conducted a qualitative analysis of our model's ability to detect important objects across different road scenarios and classes, highlighting its effectiveness in diverse contexts. Finally, we conducted various ablation studies to assess the efficiency of the proposed modules in our DRUformer model.
Authors: Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan
Vision transformers (ViTs) have recently been used for visual matching beyond object detection and segmentation. However, the original grid dividing strategy of ViTs neglects the spatial information of the keypoints, limiting the sensitivity to local information. Therefore, we propose QueryTrans (Query Transformer), which adopts a cross-attention module and keypoints-based center crop strategy for better spatial information extraction. We further integrate the graph attention module and devise a transformer-based graph matching approach GMTR (Graph Matching TRansformers) whereby the combinatorial nature of GM is addressed by a graph transformer neural GM solver. On standard GM benchmarks, GMTR shows competitive performance against the SOTA frameworks. Specifically, on Pascal VOC, GMTR achieves $\mathbf{83.6\%}$ accuracy, $\mathbf{0.9\%}$ higher than the SOTA framework. On Spair-71k, GMTR shows great potential and outperforms most of the previous works. Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80.1\%$ to $\mathbf{83.3\%}$, and BBGM from $79.0\%$ to $\mathbf{84.5\%}$. On Spair-71k, QueryTrans improves NGMv2 from $80.6\%$ to $\mathbf{82.5\%}$, and BBGM from $82.1\%$ to $\mathbf{83.9\%}$. Source code will be made publicly available.
Authors: Vojtěch Čermák, Lukas Picek, Lukáš Adam, Kostas Papafitsoros
In this paper, we present WildlifeDatasets (https://github.com/WildlifeDatasets/wildlife-datasets) - an open-source toolkit intended primarily for ecologists and computer-vision / machine-learning researchers. The WildlifeDatasets is written in Python, allows straightforward access to publicly available wildlife datasets, and provides a wide variety of methods for dataset pre-processing, performance analysis, and model fine-tuning. We showcase the toolkit in various scenarios and baseline experiments, including, to the best of our knowledge, the most comprehensive experimental comparison of datasets and methods for wildlife re-identification, including both local descriptors and deep learning approaches. Furthermore, we provide the first-ever foundation model for individual re-identification within a wide range of species - MegaDescriptor - that provides state-of-the-art performance on animal re-identification datasets and outperforms other pre-trained models such as CLIP and DINOv2 by a significant margin. To make the model available to the general public and to allow easy integration with any existing wildlife monitoring applications, we provide multiple MegaDescriptor flavors (i.e., Small, Medium, and Large) through the HuggingFace hub (https://huggingface.co/BVRA).
Authors: Peiang Zhao, Han Li, Ruiyang Jin, S. Kevin Zhou
Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in accurately conveying fine-grained spatial compositions. In this paper, we propose LoCo, a training-free approach for layout-to-image synthesis that excels in producing high-quality images aligned with both textual prompts and spatial layouts. Our method introduces a Localized Attention Constraint to refine cross-attention for individual objects, ensuring their precise placement in designated regions. We further propose a Padding Token Constraint to leverage the semantic information embedded in previously neglected padding tokens, thereby preventing the undesired fusion of synthesized objects. LoCo seamlessly integrates into existing text-to-image and layout-to-image models, significantly amplifying their performance and effectively addressing semantic failures observed in prior methods. Through extensive experiments, we showcase the superiority of our approach, surpassing existing state-of-the-art training-free layout-to-image methods both qualitatively and quantitatively across multiple benchmarks.
Authors: Yifan Yang, Yixian Zhang, Daoyang Li, Shuju Sun, Junhong Duan, Junzhou He, Qingyang Wu, Hao Liu
Geographic privacy or geo-privacy refers to the keeping private of one's geographic location, especially the restriction of geographical data maintained by personal electronic equipment. Geo-privacy is a crucial aspect of personal security, however often goes unnoticed in daily activities. With the surge in the use of Large Multimodal Models (LMM), such as GPT-4, for Open Source Intelligence (OSINT), the potential risks associated with geo-privacy breaches have intensified. This study develops a location-integrated GPT-4 based model named GeoLocator and designed four-dimensional experiments to demonstrate its capability in inferring and identifying the locational information of input imageries and/or social media contents. Our experiments reveal that GeoLocator generates specific geographic details with high accuracy and consequently embeds the risk of the model users exposing geospatial information to the public unintentionally, highlighting the thread of online data sharing, information gathering technologies and LLM on geo-privacy. We conclude with the broader implications of GeoLocator and our findings for individuals and the community at large, by emphasizing the urgency for enhanced awareness and protective measures against geo-privacy leakage in the era of advanced AI and widespread social media usage.
Keywords: geoprivacy, GPT-4, image comprehension, Large Multimodal Model (LMM), Open Source Intelligence (OSINT)
Authors: Cuifeng Shen, Yulu Gan, Chen Chen, Xiongwei Zhu, Lele Cheng, Tingting Gao, Jinzhi Wang
The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i.e., one image and text.The previous cI2V generation methods conventionally perform in RGB pixel space, with limitations in modeling motion consistency and visual continuity. Additionally, the efficiency of generating videos in pixel space is quite low.In this paper, we propose a novel approach to address these challenges by disentangling the target RGB pixels into two distinct components: spatial content and temporal motions. Specifically, we predict temporal motions which include motion vector and residual based on a 3D-UNet diffusion model. By explicitly modeling temporal motions and warping them to the starting image, we improve the temporal consistency of generated videos. This results in a reduction of spatial redundancy, emphasizing temporal details. Our proposed method achieves performance improvements by disentangling content and motion, all without introducing new structural complexities to the model. Extensive experiments on various datasets confirm our approach's superior performance over the majority of state-of-the-art methods in both effectiveness and efficiency.
Authors: Xiangyu Xiong, Yue Sun, Xiaohong Liu, Chan-Tong Lam, Tong Tong, Hao Chen, Qinquan Gao, Wei Ke, Tao Tan
Although current data augmentation methods are successful to alleviate the data insufficiency, conventional augmentation are primarily intra-domain while advanced generative adversarial networks (GANs) generate images remaining uncertain, particularly in small-scale datasets. In this paper, we propose a parameterized GAN (ParaGAN) that effectively controls the changes of synthetic samples among domains and highlights the attention regions for downstream classification. Specifically, ParaGAN incorporates projection distance parameters in cyclic projection and projects the source images to the decision boundary to obtain the class-difference maps. Our experiments show that ParaGAN can consistently outperform the existing augmentation methods with explainable classification on two small-scale medical datasets.
Authors: Zhongyi Shui, Yunlong Zhang, Kai Yao, Chenglu Zhu, Yuxuan Sun, Lin Yang
Nuclear instance segmentation in histology images is crucial for a broad spectrum of clinical applications. Current prevailing nuclear instance segmentation algorithms rely on regression of nuclei contours, distance maps, watershed markers or a proxy nuclear representation of star-convex polygons. Consequently, these methods necessitate sophisticated post-processing operations to distinguish nuclei instances, which are commonly acknowledged to be error-prone and parameter-sensitive. Recently, the segment anything model (SAM) has earned attracted huge attention within the domain of medical image segmentation due to its impressive generalization ability and promptable property. Nevertheless, its potential on nuclear instance segmentation remains largely underexplored. In this paper, we present a novel prompt-driven framework that consists of a point prompter and a SAM for automatic nuclei instance segmentation. Specifically, the prompter learns to generate a unique point prompt for each nucleus while the SAM is fine tuned to output the corresponding mask of the cued nucleus. Furthermore, we propose to add adjacent nuclei as negative prompts to promote the model's ability to recognize overlapping nuclei. Without bells and whistles, our proposed method sets a new state-of-the-art performance on three challenging benchmarks. Our code is available at \url{https://github.com/windygoo/PromptNucSeg}.
Authors: Wenjie Zhao, Jia Li, Xin Dong, Yu Xiang, Yunhui Guo
Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detecting these OoD objects is crucial for safety-critical applications. Existing methods rely on anomaly scores, but choosing a suitable threshold for generating masks presents difficulties and can lead to fragmentation and inaccuracy. This paper introduces a method to convert anomaly \textbf{S}core \textbf{T}o segmentation \textbf{M}ask, called S2M, a simple and effective framework for OoD detection in semantic segmentation. Unlike assigning anomaly scores to pixels, S2M directly segments the entire OoD object. By transforming anomaly scores into prompts for a promptable segmentation model, S2M eliminates the need for threshold selection. Extensive experiments demonstrate that S2M outperforms the state-of-the-art by approximately 10% in IoU and 30% in mean F1 score, on average, across various benchmarks including Fishyscapes, Segment-Me-If-You-Can, and RoadAnomaly datasets.
Authors: Weilin Wan, Zhiyang Dou, Taku Komura, Wenping Wang, Dinesh Jayaraman, Lingjie Liu
Controllable human motion synthesis is essential for applications in AR/VR, gaming, movies, and embodied AI. Existing methods often focus solely on either language or full trajectory control, lacking precision in synthesizing motions aligned with user-specified trajectories, especially for multi-joint control. To address these issues, we present TLControl, a new method for realistic human motion synthesis, incorporating both low-level trajectory and high-level language semantics controls. Specifically, we first train a VQ-VAE to learn a compact latent motion space organized by body parts. We then propose a Masked Trajectories Transformer to make coarse initial predictions of full trajectories of joints based on the learned latent motion space, with user-specified partial trajectories and text descriptions as conditioning. Finally, we introduce an efficient test-time optimization to refine these coarse predictions for accurate trajectory control. Experiments demonstrate that TLControl outperforms the state-of-the-art in trajectory accuracy and time efficiency, making it practical for interactive and high-quality animation generation.
Authors: Yijun Yang, Ruiyuan Gao, Xiaosen Wang, Tsung-Yi Ho, Nan Xu, Qiang Xu
In recent years, Text-to-Image (T2I) models have seen remarkable advancements, gaining widespread adoption. However, this progress has inadvertently opened avenues for potential misuse, particularly in generating inappropriate or Not-Safe-For-Work (NSFW) content. Our work introduces MMA-Diffusion, a framework that presents a significant and realistic threat to the security of T2I models by effectively circumventing current defensive measures in both open-source models and commercial online services. Unlike previous approaches, MMA-Diffusion leverages both textual and visual modalities to bypass safeguards like prompt filters and post-hoc safety checkers, thus exposing and highlighting the vulnerabilities in existing defense mechanisms.
Authors: Gustav Bredell, Marcel Fischer, Przemyslaw Szostak, Samaneh Abbasi-Sureshjani, Alvaro Gomariz
Digital pathology has significantly advanced disease detection and pathologist efficiency through the analysis of gigapixel whole-slide images (WSI). In this process, WSIs are first divided into patches, for which a feature extractor model is applied to obtain feature vectors, which are subsequently processed by an aggregation model to predict the respective WSI label. With the rapid evolution of representation learning, numerous new feature extractor models, often termed foundational models, have emerged. Traditional evaluation methods, however, rely on fixed aggregation model hyperparameters, a framework we identify as potentially biasing the results. Our study uncovers a co-dependence between feature extractor models and aggregation model hyperparameters, indicating that performance comparability can be skewed based on the chosen hyperparameters. By accounting for this co-dependency, we find that the performance of many current feature extractor models is notably similar. We support this insight by evaluating seven feature extractor models across three different datasets with 162 different aggregation model configurations. This comprehensive approach provides a more nuanced understanding of the relationship between feature extractors and aggregation models, leading to a fairer and more accurate assessment of feature extractor models in digital pathology.
Authors: Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, Vijay Baiyya, Siddhant Bansal, Bikram Boote, Eugene Byrne, Zach Chavis, Joya Chen, Feng Cheng, Fu-Jen Chu, Sean Crane, Avijit Dasgupta, Jing Dong, Maria Escobar, Cristhian Forigua, Abrham Gebreselasie, Sanjay Haresh, Jing Huang, Md Mohaiminul Islam, Suyog Jain, Rawal Khirodkar, Devansh Kukreja, Kevin J Liang, Jia-Wei Liu, Sagnik Majumder, Yongsen Mao, Miguel Martin, Effrosyni Mavroudi, Tushar Nagarajan, Francesco Ragusa, Santhosh Kumar Ramakrishnan, Luigi Seminara, Arjun Somayazulu, Yale Song, Shan Su, Zihui Xue, Edward Zhang, Jinxu Zhang, Angela Castillo, Changan Chen, Xinzhu Fu, Ryosuke Furuta, Cristina Gonzalez, Prince Gupta, Jiabo Hu, Yifei Huang, Yiming Huang, Weslie Khoo, et al. (48 additional authors not shown)
We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). More than 800 participants from 13 cities worldwide performed these activities in 131 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,422 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources will be open sourced to fuel new research in the community.
Authors: Shuchao Duan, Amirhossein Dadashzadeh, Alan Whone, Majid Mirmehdi
Facial expression recognition (FER) methods have made great inroads in categorising moods and feelings in humans. Beyond FER, pain estimation methods assess levels of intensity in pain expressions, however assessing the quality of all facial expressions is of critical value in health-related applications. In this work, we address the quality of five different facial expressions in patients affected by Parkinson's disease. We propose a novel landmark-guided approach, QAFE-Net, that combines temporal landmark heatmaps with RGB data to capture small facial muscle movements that are encoded and mapped to severity scores. The proposed approach is evaluated on a new Parkinson's Disease Facial Expression dataset (PFED5), as well as on the pain estimation benchmark, the UNBC-McMaster Shoulder Pain Expression Archive Database. Our comparative experiments demonstrate that the proposed method outperforms SOTA action quality assessment works on PFED5 and achieves lower mean absolute error than the SOTA pain estimation methods on UNBC-McMaster. Our code and the new PFED5 dataset are available at https://github.com/shuchaoduan/QAFE-Net.
Authors: Walid Bousselham, Felix Petersen, Vittorio Ferrari, Hilde Kuehne
Vision-language foundation models have shown remarkable performance in various zero-shot settings such as image retrieval, classification, or captioning. But so far, those models seem to fall behind when it comes to zero-shot localization of referential expressions and objects in images. As a result, they need to be fine-tuned for this task. In this paper, we show that pretrained vision-language (VL) models allow for zero-shot open-vocabulary object localization without any fine-tuning. To leverage those capabilities, we propose a Grounding Everything Module (GEM) that generalizes the idea of value-value attention introduced by CLIPSurgery to a self-self attention path. We show that the concept of self-self attention corresponds to clustering, thus enforcing groups of tokens arising from the same object to be similar while preserving the alignment with the language space. To further guide the group formation, we propose a set of regularizations that allows the model to finally generalize across datasets and backbones. We evaluate the proposed GEM framework on various benchmark tasks and datasets for semantic segmentation. It shows that GEM not only outperforms other training-free open-vocabulary localization methods, but also achieves state-of-the-art results on the recently proposed OpenImagesV7 large-scale segmentation benchmark.
Authors: Can Jin, Tianjin Huang, Yihua Zhang, Mykola Pechenizkiy, Sijia Liu, Shiwei Liu, Tianlong Chen
The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have demonstrated numerous favorable benefits like low complexity, undamaged generalization, etc. Most of the prominent pruning strategies are invented from a model-centric perspective, focusing on searching and preserving crucial weights by analyzing network topologies. However, the role of data and its interplay with model-centric pruning has remained relatively unexplored. In this research, we introduce a novel data-model co-design perspective: to promote superior weight sparsity by learning important model topology and adequate input data in a synergetic manner. Specifically, customized Visual Prompts are mounted to upgrade neural Network sparsification in our proposed VPNs framework. As a pioneering effort, this paper conducts systematic investigations about the impact of different visual prompts on model pruning and suggests an effective joint optimization approach. Extensive experiments with 3 network architectures and 8 datasets evidence the substantial performance improvements from VPNs over existing start-of-the-art pruning algorithms. Furthermore, we find that subnetworks discovered by VPNs from pre-trained models enjoy better transferability across diverse downstream scenarios. These insights shed light on new promising possibilities of data-model co-designs for vision model sparsification.
Authors: Xiaoqian Shen, Mohamed Elhoseiny
Recent generative models have demonstrated impressive capabilities in generating realistic and visually pleasing images grounded on textual prompts. Nevertheless, a significant challenge remains in applying these models for the more intricate task of story visualization. Since it requires resolving pronouns (he, she, they) in the frame descriptions, i.e., anaphora resolution, and ensuring consistent characters and background synthesis across frames. Yet, the emerging Large Language Model (LLM) showcases robust reasoning abilities to navigate through ambiguous references and process extensive sequences. Therefore, we introduce \textbf{StoryGPT-V}, which leverages the merits of the latent diffusion (LDM) and LLM to produce images with consistent and high-quality characters grounded on given story descriptions. First, we train a character-aware LDM, which takes character-augmented semantic embedding as input and includes the supervision of the cross-attention map using character segmentation masks, aiming to enhance character generation accuracy and faithfulness. In the second stage, we enable an alignment between the output of LLM and the character-augmented embedding residing in the input space of the first-stage model. This harnesses the reasoning ability of LLM to address ambiguous references and the comprehension capability to memorize the context. We conduct comprehensive experiments on two visual story visualization benchmarks. Our model reports superior quantitative results and consistently generates accurate characters of remarkable quality with low memory consumption. Our code will be made publicly available.
Authors: Zeyi Sun, Ye Fang, Tong Wu, Pan Zhang, Yuhang Zang, Shu Kong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang
Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the details, even those irrelevant to specific tasks. However, for a finer understanding and controlled editing of images, it becomes crucial to focus on specific regions of interest, which can be indicated as points, masks, or boxes by humans or perception models. To fulfill the requirements, we introduce Alpha-CLIP, an enhanced version of CLIP with an auxiliary alpha channel to suggest attentive regions and fine-tuned with constructed millions of RGBA region-text pairs. Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents. It demonstrates effectiveness in various tasks, including but not limited to open-world recognition, multimodal large language models, and conditional 2D / 3D generation. It has a strong potential to serve as a versatile tool for image-related tasks.
Authors: Zhixiang Wei, Lin Chen, Yi Jin, Xiaoxiao Ma, Tianle Liu, Pengyang Lin, Ben Wang, Huaian Chen, Jinjin Zheng
In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely Rein, to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 68.1% on the Cityscapes, without accessing any real urban-scene datasets.Code is available at https://github.com/w1oves/Rein.git.
Authors: Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang
The formidable model size and demanding computational requirements of Segment Anything Model (SAM) have rendered it cumbersome for deployment on resource-constrained devices. Existing approaches for SAM compression typically involve training a new network from scratch, posing a challenging trade-off between compression costs and model performance. To address this issue, this paper introduces SlimSAM, a novel SAM compression method that achieves superior performance with remarkably low training costs. This is achieved by the efficient reuse of pre-trained SAMs through a unified pruning-distillation framework. To enhance knowledge inheritance from the original SAM, we employ an innovative alternate slimming strategy that partitions the compression process into a progressive procedure. Diverging from prior pruning techniques, we meticulously prune and distill decoupled model structures in an alternating fashion. Furthermore, a novel label-free pruning criterion is also proposed to align the pruning objective with the optimization target, thereby boosting the post-distillation after pruning. SlimSAM yields significant performance improvements while demanding over 10 times less training costs than any other existing methods. Even when compared to the original SAM-H, SlimSAM achieves approaching performance while reducing parameter counts to merely 0.9% (5.7M), MACs to 0.8% (21G), and requiring only 0.1% (10k) of the SAM training data. Code is available at url{this http URL}.
Authors: Zijian Chen, Wei Sun, Haoning Wu, Zicheng Zhang, Jun Jia, Xiongkuo Min, Guangtao Zhai, Wenjun Zhang
The proliferation of Artificial Intelligence-Generated Images (AGIs) has greatly expanded the Image Naturalness Assessment (INA) problem. Different from early definitions that mainly focus on tone-mapped images with limited distortions (e.g., exposure, contrast, and color reproduction), INA on AI-generated images is especially challenging as it has more diverse contents and could be affected by factors from multiple perspectives, including low-level technical distortions and high-level rationality distortions. In this paper, we take the first step to benchmark and assess the visual naturalness of AI-generated images. First, we construct the AI-Generated Image Naturalness (AGIN) database by conducting a large-scale subjective study to collect human opinions on the overall naturalness as well as perceptions from technical and rationality perspectives. AGIN verifies that naturalness is universally and disparately affected by both technical and rationality distortions. Second, we propose the Joint Objective Image Naturalness evaluaTor (JOINT), to automatically learn the naturalness of AGIs that aligns human ratings. Specifically, JOINT imitates human reasoning in naturalness evaluation by jointly learning both technical and rationality perspectives. Experimental results show our proposed JOINT significantly surpasses baselines for providing more subjectively consistent results on naturalness assessment. Our database and code will be released in https://github.com/zijianchen98/AGIN.
Authors: Fangxun Shu, Lei Zhang, Hao Jiang, Cihang Xie
This paper presents Audio-Visual LLM, a Multimodal Large Language Model that takes both visual and auditory inputs for holistic video understanding. A key design is the modality-augmented training, which involves the integration of modality-specific tokens engineered to activate the appropriate visual and/or auditory encoder selectively. This mechanism is pivotal in enabling end-to-end joint training with video data at different modalities, including visual-only, audio-only, and audio-visual formats. Moreover, we introduce a high-quality video instruction dataset, derived from GPT-4. This dataset allows Audio-Visual LLM to adeptly process a variety of task-oriented video instructions, ranging from multi-turn conversations and audio-visual narratives to complex reasoning tasks. Extensive experiments demonstrate that Audio-Visual LLM impressively achieves strong zero-shot results across a range of video understanding tasks. For example, Audio-Visual LLM achieves an accuracy of 53.7% on MSRVTT-QA, outperforming non-LLM-based InterVideo by 6.6% and LLM-based Valley by 4.4%, respectively. Additionally, our Audio-Visual LLM also achieves competitive performance on audio tasks (e.g., AudioCaps).
Authors: Qirui Yang, Qihua Cheng, Huanjing Yue, Le Zhang, Yihao Liu, Jingyu Yang
Raw low light image enhancement (LLIE) has achieved much better performance than the sRGB domain enhancement methods due to the merits of raw data. However, the ambiguity between noisy to clean and raw to sRGB mappings may mislead the single-stage enhancement networks. The two-stage networks avoid ambiguity by decoupling the two mappings but usually have large computing complexity. To solve this problem, we propose a single-stage network empowered by Feature Domain Adaptation (FDA) to decouple the denoising and color mapping tasks in raw LLIE. The denoising encoder is supervised by the clean raw image, and then the denoised features are adapted for the color mapping task by an FDA module. We propose a Lineformer to serve as the FDA, which can well explore the global and local correlations with fewer line buffers (friendly to the line-based imaging process). During inference, the raw supervision branch is removed. In this way, our network combines the advantage of a two-stage enhancement process with the efficiency of single-stage inference. Experiments on four benchmark datasets demonstrate that our method achieves state-of-the-art performance with fewer computing costs (60% FLOPs of the two-stage method DNF). Our codes will be released after the acceptance of this work.
Authors: Lei Zhang, Fangxun Shu, Sucheng Ren, Bingchen Zhao, Hao Jiang, Cihang Xie
The massive growth of image-text data through web crawling inherently presents the challenge of variability in data quality. This paper introduces a novel algorithm, rooted in human knowledge, to compress this vast corpus of web-crawled image-text datasets to a compact and high-quality form. Our method unfolds in three major steps. First, we collect an image-text dataset, wherein each image is associated with multiple captions sourced from diverse origins. Then, to systemically capture human preferences regarding the best caption paired with each image, we establish a comprehensive set of both subjective and objective criteria for critically guiding the alignment assessment from labelers. Lastly, we train a reward model on the annotated dataset to internalize the nuanced human understanding of image-text alignment. The resulting reward model thus can act as a human-like referee to filter misaligned/low-quality image-text pairs. Extensive experiments demonstrate that we are able to secure (or even improve) model performance by compressing the image-text datasets up to ~90%. An impressive example is that, by aggressively reducing the total training sample from 130M to 15.5M (e.g., ~9x smaller), our BLIP-B/16 models still consistently show superior performance compared with the full-size-dataset counterpart on image-text retrieval (Flickr30K, COCO) by ~2.5% in Recall@1, and on image-captioning (Nocaps, COCO) by ~10.0% in CIDEr and ~2.7% in SPICE.
Authors: Bin Yang, Patrick Pfreundschuh, Roland Siegwart, Marco Hutter, Peyman Moghadam, Vaishakh Patil
LiDAR Upsampling is a challenging task for the perception systems of robots and autonomous vehicles, due to the sparse and irregular structure of large-scale scene contexts. Recent works propose to solve this problem by converting LiDAR data from 3D Euclidean space into an image super-resolution problem in 2D image space. Although their methods can generate high-resolution range images with fine-grained details, the resulting 3D point clouds often blur out details and predict invalid points. In this paper, we propose TULIP, a new method to reconstruct high-resolution LiDAR point clouds from low-resolution LiDAR input. We also follow a range image-based approach but specifically modify the patch and window geometries of a Swin-Transformer-based network to better fit the characteristics of range images. We conducted several experiments on three different public real-world and simulated datasets. TULIP outperforms state-of-the-art methods in all relevant metrics and generates robust and more realistic point clouds than prior works.
Authors: Guangfeng Jiang, Jun Liu, Yuzhi Wu, Wenlong Liao, Tao He, Pai Peng
Instance segmentation is a fundamental research in computer vision, especially in autonomous driving. However, manual mask annotation for instance segmentation is quite time-consuming and costly. To address this problem, some prior works attempt to apply weakly supervised manner by exploring 2D or 3D boxes. However, no one has ever successfully segmented 2D and 3D instances simultaneously by only using 2D box annotations, which could further reduce the annotation cost by an order of magnitude. Thus, we propose a novel framework called Multimodal Weakly Supervised Instance Segmentation (MWSIS), which incorporates various fine-grained label generation and correction modules for both 2D and 3D modalities to improve the quality of pseudo labels, along with a new multimodal cross-supervision approach, named Consistency Sparse Cross-modal Supervision (CSCS), to reduce the inconsistency of multimodal predictions by response distillation. Particularly, transferring the 3D backbone to downstream tasks not only improves the performance of the 3D detectors, but also outperforms fully supervised instance segmentation with only 5% fully supervised annotations. On the Waymo dataset, the proposed framework demonstrates significant improvements over the baseline, especially achieving 2.59% mAP and 12.75% mAP increases for 2D and 3D instance segmentation tasks, respectively. The code is available at https://github.com/jiangxb98/mwsis-plugin.
Authors: Guanxing Lu, Ziwei Wang, Changliu Liu, Jiwen Lu, Yansong Tang
Embodied Instruction Following (EIF) requires agents to complete human instruction by interacting objects in complicated surrounding environments. Conventional methods directly consider the sparse human instruction to generate action plans for agents, which usually fail to achieve human goals because of the instruction incoherence in action descriptions. On the contrary, we propose ThinkBot that reasons the thought chain in human instruction to recover the missing action descriptions, so that the agent can successfully complete human goals by following the coherent instruction. Specifically, we first design an instruction completer based on large language models to recover the missing actions with interacted objects between consecutive human instruction, where the perceived surrounding environments and the completed sub-goals are considered for instruction completion. Based on the partially observed scene semantic maps, we present an object localizer to infer the position of interacted objects for agents to achieve complex human goals. Extensive experiments in the simulated environment show that our ThinkBot outperforms the state-of-the-art EIF methods by a sizable margin in both success rate and execution efficiency.
Authors: Ri Cheng, Ruian He, Xuhao Jiang, Shili Zhou, Weimin Tan, Bo Yan
Existing recurrent optical flow estimation networks are computationally expensive since they use a fixed large number of iterations to update the flow field for each sample. An efficient network should skip iterations when the flow improvement is limited. In this paper, we develop a Context-Aware Iteration Policy Network for efficient optical flow estimation, which determines the optimal number of iterations per sample. The policy network achieves this by learning contextual information to realize whether flow improvement is bottlenecked or minimal. On the one hand, we use iteration embedding and historical hidden cell, which include previous iterations information, to convey how flow has changed from previous iterations. On the other hand, we use the incremental loss to make the policy network implicitly perceive the magnitude of optical flow improvement in the subsequent iteration. Furthermore, the computational complexity in our dynamic network is controllable, allowing us to satisfy various resource preferences with a single trained model. Our policy network can be easily integrated into state-of-the-art optical flow networks. Extensive experiments show that our method maintains performance while reducing FLOPs by about 40%/20% for the Sintel/KITTI datasets.
Authors: Zihao Zhao, Yuxiao Liu, Han Wu, Yonghao Li, Sheng Wang, Lin Teng, Disheng Liu, Zhiming Cui, Qian Wang, Dinggang Shen
Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks, attributable to its generalizability and interpretability. The use of CLIP has recently gained increasing interest in the medical imaging domain, serving both as a pre-training paradigm for aligning medical vision and language, and as a critical component in diverse clinical tasks. With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP paradigm within the domain of medical imaging, regarding both refined CLIP pre-training and CLIP-driven applications. In this study, We (1) start with a brief introduction to the fundamentals of CLIP methodology. (2) Then, we investigate the adaptation of CLIP pre-training in the medical domain, focusing on how to optimize CLIP given characteristics of medical images and reports. (3) Furthermore, we explore the practical utilization of CLIP pre-trained models in various tasks, including classification, dense prediction, and cross-modal tasks. (4) Finally, we discuss existing limitations of CLIP in the context of medical imaging and propose forward-looking directions to address the demands of medical imaging domain. We expect that this comprehensive survey will provide researchers in the field of medical image analysis with a holistic understanding of the CLIP paradigm and its potential implications. The project page can be found on https://github.com/zhaozh10/Awesome-CLIP-in-Medical-Imaging.
Authors: Jian Hu, Jiayi Lin, Weitong Cai, Shaogang Gong
Camouflaged object detection (COD) approaches heavily rely on pixel-level annotated datasets. Weakly-supervised COD (WSCOD) approaches use sparse annotations like scribbles or points to reduce annotation effort, but this can lead to decreased accuracy. The Segment Anything Model (SAM) shows remarkable segmentation ability with sparse prompts like points. However, manual prompt is not always feasible, as it may not be accessible in real-world application. Additionally, it only provides localization information instead of semantic one, which can intrinsically cause ambiguity in interpreting the targets. In this work, we aim to eliminate the need for manual prompt. The key idea is to employ Cross-modal Chains of Thought Prompting (CCTP) to reason visual prompts using the semantic information given by a generic text prompt. To that end, we introduce a test-time adaptation per-instance mechanism called Generalizable SAM (GenSAM) to automatically enerate and optimize visual prompts the generic task prompt for WSCOD. In particular, CCTP maps a single generic text prompt onto image-specific consensus foreground and background heatmaps using vision-language models, acquiring reliable visual prompts. Moreover, to test-time adapt the visual prompts, we further propose Progressive Mask Generation (PMG) to iteratively reweight the input image, guiding the model to focus on the targets in a coarse-to-fine manner. Crucially, all network parameters are fixed, avoiding the need for additional training. Experiments demonstrate the superiority of GenSAM. Experiments on three benchmarks demonstrate that GenSAM outperforms point supervision approaches and achieves comparable results to scribble supervision ones, solely relying on general task descriptions as prompts. our codes is in: https://lwpyh.github.io/GenSAM/.
Authors: Ji Lin, Hongxu Yin, Wei Ping, Yao Lu, Pavlo Molchanov, Andrew Tao, Huizi Mao, Jan Kautz, Mohammad Shoeybi, Song Han
Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM with visual inputs, but lacks an in-depth study of the visual language pre-training process, where the model learns to perform joint modeling on both modalities. In this work, we examine the design options for VLM pre-training by augmenting LLM towards VLM through step-by-step controllable comparisons. We introduce three main findings: (1) freezing LLMs during pre-training can achieve decent zero-shot performance, but lack in-context learning capability, which requires unfreezing the LLM; (2) interleaved pre-training data is beneficial whereas image-text pairs alone are not optimal; (3) re-blending text-only instruction data to image-text data during instruction fine-tuning not only remedies the degradation of text-only tasks, but also boosts VLM task accuracy. With an enhanced pre-training recipe we build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models, e.g., LLaVA-1.5, across main benchmarks without bells and whistles. Multi-modal pre-training also helps unveil appealing properties of VILA, including multi-image reasoning, enhanced in-context learning, and better world knowledge.
Authors: Liuxiang Qiu, Si Chen, Yan Yan, Jing-Hao Xue, Da-Han Wang, Shunzhi Zhu
Visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same persons captured by visible (VIS) and infrared (IR) cameras. Existing VI-ReID methods ignore high-order structure information of features while being relatively difficult to learn a reasonable common feature space due to the large modality discrepancy between VIS and IR images. To address the above problems, we propose a novel high-order structure based middle-feature learning network (HOS-Net) for effective VI-ReID. Specifically, we first leverage a short- and long-range feature extraction (SLE) module to effectively exploit both short-range and long-range features. Then, we propose a high-order structure learning (HSL) module to successfully model the high-order relationship across different local features of each person image based on a whitened hypergraph network.This greatly alleviates model collapse and enhances feature representations. Finally, we develop a common feature space learning (CFL) module to learn a discriminative and reasonable common feature space based on middle features generated by aligning features from different modalities and ranges. In particular, a modality-range identity-center contrastive (MRIC) loss is proposed to reduce the distances between the VIS, IR, and middle features, smoothing the training process. Extensive experiments on the SYSU-MM01, RegDB, and LLCM datasets show that our HOS-Net achieves superior state-of-the-art performance. Our code is available at \url{https://github.com/Jaulaucoeng/HOS-Net}.
Authors: Yanzuo Lu, Meng Shen, Andy J Ma, Xiaohua Xie, Jian-Huang Lai
Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer. Existing UniDA methods may suffer from the problems of overlooking intra-domain variations in the target domain and difficulty in separating between the similar known and unknown class. To address these issues, we propose a novel Mutual Learning Network (MLNet) with neighborhood invariance for UniDA. In our method, confidence-guided invariant feature learning with self-adaptive neighbor selection is designed to reduce the intra-domain variations for more generalizable feature representation. By using the cross-domain mixup scheme for better unknown-class identification, the proposed method compensates for the misidentified known-class errors by mutual learning between the closed-set and open-set classifiers. Extensive experiments on three publicly available benchmarks demonstrate that our method achieves the best results compared to the state-of-the-arts in most cases and significantly outperforms the baseline across all the four settings in UniDA. Code is available at https://github.com/YanzuoLu/MLNet.
Authors: T. Kim, H. Jeon, Y. Lim
Recently, as many studies of autonomous vehicles have been achieved for levels 4 and 5, there has been also increasing interest in the advancement of perception, decision, and control technologies, which are the three major aspects of autonomous vehicles. As for the perception technologies achieving reliable maneuvering of autonomous vehicles, object detection by using diverse sensors (e.g., LiDAR, radar, and camera) should be prioritized. These sensors require to detect objects accurately and quickly in diverse weather conditions, but they tend to have challenges to consistently detect objects in bad weather conditions with rain, snow, or fog. Thus, in this study, based on the experimentally obtained raindrop data from precipitation conditions, we constructed a novel dataset that could test diverse network model in various precipitation conditions through the CARLA simulator. Consequently, based on our novel dataset, YOLO series, a one-stage-detector, was used to quantitatively verify how much object detection performance could be decreased under various precipitation conditions from normal to extreme heavy rain situations.
Authors: Kewei Wang, Yizheng Wu, Zhiyu Pan, Xingyi Li, Ke Xian, Zhe Wang, Zhiguo Cao, Guosheng Lin
Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and re-generates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://github.com/kwwcv/SSMP.
Authors: Xu-Lu Zhang, Xiao-Yong Wei, Jin-Lin Wu, Tian-Yi Zhang, Zhaoxiang Zhang, Zhen Lei, Qing Li
Inversion methods, such as Textual Inversion, generate personalized images by incorporating concepts of interest provided by user images. However, existing methods often suffer from overfitting issues, where the dominant presence of inverted concepts leads to the absence of other desired concepts. It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space. To address this issue, we propose a method that guides the inversion process towards the core distribution for compositional embeddings. Additionally, we introduce a spatial regularization approach to balance the attention on the concepts being composed. Our method is designed as a post-training approach and can be seamlessly integrated with other inversion methods. Experimental results demonstrate the effectiveness of our proposed approach in mitigating the overfitting problem and generating more diverse and balanced compositions of concepts in the synthesized images. The source code is available at https://github.com/zhangxulu1996/Compositional-Inversion.
Authors: Wenting Chen, Xiang Li, Linlin Shen, Yixuan Yuan
To address these issues, we propose a novel Adaptive patch-word Matching (AdaMatch) model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explainability for the generation process. AdaMatch exploits the fine-grained relation between adaptive patches and words to provide explanations of specific image regions with corresponding words. To capture the abnormal regions of varying sizes and positions, we introduce the Adaptive Patch extraction (AdaPatch) module to acquire the adaptive patches for these regions adaptively. In order to provide explicit explainability for CXR-report generation task, we propose an AdaMatch-based bidirectional large language model for Cyclic CXR-report generation (AdaMatch-Cyclic). It employs the AdaMatch to obtain the keywords for CXR images and `keypatches' for medical reports as hints to guide CXR-report generation. Extensive experiments on two publicly available CXR datasets prove the effectiveness of our method and its superior performance to existing methods.