Authors: Prakash Chandra Chhipa, Kanjar De, Meenakshi Subhash Chippa, Rajkumar Saini, Marcus Liwicki
Abstract: The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Open-vocabulary object detection extends the capabilities of traditional object detection frameworks to recognize and classify objects beyond predefined categories. Investigating OOD robustness in open-vocabulary object detection is essential to increase the trustworthiness of these models. This study presents a comprehensive robustness comparison of zero-shot capabilities of three recent open-vocabulary foundation object detection models, namely OWL-ViT, YOLO World, and Grounding DINO. Experiments carried out on the COCO-O and COCO-C benchmarks encompassing distribution shifts highlight the challenges of the models' robustness. Source code shall be made available to the research community on GitHub.
Authors: Ibne Farabi Shihab, Benjir Islam Alvee, Sudesh Ramesh Bhagat, Anuj Sharma
Abstract: This study aims to compare the effectiveness of a robust ensemble model with the state-of-the-art ONE-PEACE Large Language Model (LLM) for accurate detection of sidewalks. Accurate sidewalk detection is crucial in improving road safety and urban planning. The study evaluated the model's performance on Cityscapes, Ade20k, and the Boston Dataset. The results showed that the ensemble model performed better than the individual models, achieving mean Intersection Over Union (mIOU) scores of 93.1\%, 90.3\%, and 90.6\% on these datasets under ideal conditions. Additionally, the ensemble model maintained a consistent level of performance even in challenging conditions such as Salt-and-Pepper and Speckle noise, with only a gradual decrease in efficiency observed. On the other hand, the ONE-PEACE LLM performed slightly better than the ensemble model in ideal scenarios but experienced a significant decline in performance under noisy conditions. These findings demonstrate the robustness and reliability of the ensemble model, making it a valuable asset for improving urban infrastructure related to road safety and curb space management. This study contributes positively to the broader context of urban health and mobility.
Authors: Joel Sol, Amir M. Soufi Enayati, Homayoun Najjaran
Abstract: This paper addresses the challenge of geometric quality assurance in manufacturing, particularly when human assessment is required. It proposes using Blender, an open-source simulation tool, to create synthetic datasets for machine learning (ML) models. The process involves translating expert information into shape key parameters to simulate deformations, generating images for both deformed and non-deformed objects. The study explores the impact of discrepancies between real and simulated environments on ML model performance and investigates the effect of different simulation backgrounds on model sensitivity. Additionally, the study aims to enhance the model's robustness to camera positioning by generating datasets with a variety of randomized viewpoints. The entire process, from data synthesis to model training and testing, is implemented using a Python API interfacing with Blender. An experiment with a soda can object validates the accuracy of the proposed pipeline.
Authors: Ouassine Younes (LISI, Computer Science Department), Zahir Jihad (LISI, Computer Science Department), Conruyt No\"el (LIM), Kayal Mohsen (ENTROPIE), A. Martin Philippe (LIM), Chenin Eric (UMMISCO), Bigot Lionel (ENTROPIE), Vignes Lebbe Regine (ISYEB)
Abstract: Coral reefs are vital ecosystems that are under increasing threat due to local human impacts and climate change. Efficient and accurate monitoring of coral reefs is crucial for their conservation and management. In this paper, we present an automatic coral detection system utilizing the You Only Look Once (YOLO) deep learning model, which is specifically tailored for underwater imagery analysis. To train and evaluate our system, we employ a dataset consisting of 400 original underwater images. We increased the number of annotated images to 580 through image manipulation using data augmentation techniques, which can improve the model's performance by providing more diverse examples for training. The dataset is carefully collected from underwater videos that capture various coral reef environments, species, and lighting conditions. Our system leverages the YOLOv5 algorithm's real-time object detection capabilities, enabling efficient and accurate coral detection. We used YOLOv5 to extract discriminating features from the annotated dataset, enabling the system to generalize, including previously unseen underwater images. The successful implementation of the automatic coral detection system with YOLOv5 on our original image dataset highlights the potential of advanced computer vision techniques for coral reef research and conservation. Further research will focus on refining the algorithm to handle challenging underwater image conditions, and expanding the dataset to incorporate a wider range of coral species and spatio-temporal variations.
Authors: Xu Pan, Aaron Philip, Ziqian Xie, Odelia Schwartz
Abstract: Self-attention in vision transformers has been thought to perform perceptual grouping where tokens attend to other tokens with similar embeddings, which could correspond to semantically similar features in an image. However, contextualization is also an important and necessary computation for processing signals. Contextualization potentially requires tokens to attend to dissimilar tokens such as those corresponding to backgrounds or different objects, but this effect has not been reported in previous studies. In this study, we investigate whether self-attention in vision transformers exhibits a preference for attending to similar tokens or dissimilar tokens, providing evidence of perceptual grouping and contextualization, respectively. To study this question, we propose the use of singular value decomposition on the query-key matrix ${\textbf{W}_q}^T\textbf{W}_k$. Naturally, the left and right singular vectors are feature directions of the self-attention layer and can be analyzed in pairs to interpret the interaction between tokens. We find that early layers attend more to similar tokens, while late layers show increased attention to dissimilar tokens. Moreover, many of these interactions between features represented by singular vectors are interpretable. We present a novel perspective on interpreting the attention mechanism, which may contribute to understanding how transformer models utilize context and salient features when processing images.
Authors: Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood, Karthik Nandakumar
Abstract: Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an augmented image. Such methods may not only omit important portions of the input images but also introduce label ambiguities by mixing images across labels resulting in misleading supervisory signals. To address these limitations, we propose DiffuseMix, a novel data augmentation technique that leverages a diffusion model to reshape training images, supervised by our bespoke conditional prompts. First, concatenation of a partial natural image and its generated counterpart is obtained which helps in avoiding the generation of unrealistic images or label ambiguities. Then, to enhance resilience against adversarial attacks and improves safety measures, a randomly selected structural pattern from a set of fractal images is blended into the concatenated image to form the final augmented image for training. Our empirical results on seven different datasets reveal that DiffuseMix achieves superior performance compared to existing state-of the-art methods on tasks including general classification,fine-grained classification, fine-tuning, data scarcity, and adversarial robustness. Augmented datasets and codes are available here: https://diffusemix.github.io/
Authors: Yurii Piadyk, Giancarlo Pereira, Claudio Silva, Daniele Panozzo
Abstract: We introduce a novel calibration and reconstruction procedure for structured light scanning that foregoes explicit point triangulation in favor of a data-driven lookup procedure. The key idea is to sweep a calibration checkerboard over the entire scanning volume with a linear stage and acquire a dense stack of images to build a per-pixel lookup table from colors to depths. Imperfections in the setup, lens distortion, and sensor defects are baked into the calibration data, leading to a more reliable and accurate reconstruction. Existing structured light scanners can be reused without modifications while enjoying the superior precision and resilience that our calibration and reconstruction algorithms offer. Our algorithm shines when paired with a custom-designed analog projector, which enables 1-megapixel high-speed 3D scanning at up to 500 fps. We describe our algorithm and hardware prototype for high-speed 3D scanning and compare them with commercial and open-source structured light scanning methods.
Authors: Roberta Iuliana Luca, Alexandra Baicoianu, Ioana Cristina Plajer
Abstract: Multispectral and hyperspectral images are increasingly popular in different research fields, such as remote sensing, astronomical imaging, or precision agriculture. However, the amount of free data available to perform machine learning tasks is relatively small. Moreover, artificial intelligence models developed in the area of spectral imaging require input images with a fixed spectral signature, expecting the data to have the same number of spectral bands or the same spectral resolution. This requirement significantly reduces the number of usable sources that can be used for a given model. The scope of this study is to introduce a methodology for spectral image data fusion, in order to allow machine learning models to be trained and/or used on data from a larger number of sources, thus providing better generalization. For this purpose, we propose different interpolation techniques, in order to make multisource spectral data compatible with each other. The interpolation outcomes are evaluated through various approaches. This includes direct assessments using surface plots and metrics such as a Custom Mean Squared Error (CMSE) and the Normalized Difference Vegetation Index (NDVI). Additionally, indirect evaluation is done by estimating their impact on machine learning model training, particularly for semantic segmentation.
Authors: Jiaxu Wang, Junhao He, Ziyi Zhang, Mingyuan Sun, Jingkai Sun, Renjing Xu
Abstract: Event cameras offer promising advantages such as high dynamic range and low latency, making them well-suited for challenging lighting conditions and fast-moving scenarios. However, reconstructing 3D scenes from raw event streams is difficult because event data is sparse and does not carry absolute color information. To release its potential in 3D reconstruction, we propose the first event-based generalizable 3D reconstruction framework, called EvGGS, which reconstructs scenes as 3D Gaussians from only event input in a feedforward manner and can generalize to unseen cases without any retraining. This framework includes a depth estimation module, an intensity reconstruction module, and a Gaussian regression module. These submodules connect in a cascading manner, and we collaboratively train them with a designed joint loss to make them mutually promote. To facilitate related studies, we build a novel event-based 3D dataset with various material objects and calibrated labels of grayscale images, depth maps, camera poses, and silhouettes. Experiments show models that have jointly trained significantly outperform those trained individually. Our approach performs better than all baselines in reconstruction quality, and depth/intensity predictions with satisfactory rendering speed.
Authors: Chi Hong, Jiyue Huang, Robert Birke, Dick Epema, Stefanie Roos, Lydia Y. Chen
Abstract: While diffusion models effectively generate remarkable synthetic images, a key limitation is the inference inefficiency, requiring numerous sampling steps. To accelerate inference and maintain high-quality synthesis, teacher-student distillation is applied to compress the diffusion models in a progressive and binary manner by retraining, e.g., reducing the 1024-step model to a 128-step model in 3 folds. In this paper, we propose a single-fold distillation algorithm, SFDDM, which can flexibly compress the teacher diffusion model into a student model of any desired step, based on reparameterization of the intermediate inputs from the teacher model. To train the student diffusion, we minimize not only the output distance but also the distribution of the hidden variables between the teacher and student model. Extensive experiments on four datasets demonstrate that our student model trained by the proposed SFDDM is able to sample high-quality data with steps reduced to as little as approximately 1%, thus, trading off inference time. Our remarkable performance highlights that SFDDM effectively transfers knowledge in single-fold distillation, achieving semantic consistency and meaningful image interpolation.
Authors: Henry Hengyuan Zhao, Pan Zhou, Difei Gao, Mike Zheng Shou
Abstract: Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. However, current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. In this study, we introduce LOVA3, an innovative framework named ``Learning tO Visual Question Answering, Asking and Assessment,'' designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming at fostering the skills of asking and assessing questions in the context of images. To develop the questioning ability, we compile a comprehensive set of multimodal foundational tasks. For assessment, we introduce a new benchmark called EvalQABench, comprising 64,000 training samples (split evenly between positive and negative samples) and 5,000 testing samples. We posit that enhancing MLLMs with the capabilities to answer, ask, and assess questions will improve their multimodal comprehension and lead to better performance. We validate our hypothesis by training an MLLM using the LOVA3 framework and testing it on 10 multimodal benchmarks. The results demonstrate consistent performance improvements, thereby confirming the efficacy of our approach.
Authors: Mario D\"obler, Robert A. Marsden, Tobias Raichle, Bin Yang
Abstract: In the realm of deep learning, maintaining model robustness against distribution shifts is critical. This paper investigates test-time adaptation strategies for vision-language models, with a specific focus on CLIP and its variants. Through a systematic exploration of prompt-based techniques and existing test-time adaptation methods, the study aims to enhance the adaptability and robustness of vision-language models in diverse real-world scenarios. The investigation includes an analysis of prompt engineering strategies, such as hand-crafted prompts, prompt ensembles, and prompt learning techniques. We introduce a vision-text-space ensemble that significantly boosts the average performance compared to a text-space-only ensemble. Additionally, our comparative study delves into leveraging existing test-time adaptation methods originally designed for image classification tasks. Experimental evaluations conducted across various datasets and model architectures demonstrate the efficacy of different adaptation strategies. We further give insights into the importance of updating the vision encoder and whether it is beneficial to update the text encoder. Code is available at https://github.com/mariodoebler/test-time-adaptation
Authors: Amin Ahmadi Kasani, Hedieh Sajedi
Abstract: Estimating the Bone Age of children is very important for diagnosing growth defects, and related diseases, and estimating the final height that children reach after maturity. For this reason, it is widely used in different countries. Traditional methods for estimating bone age are performed by comparing atlas images and radiographic images of the left hand, which is time-consuming and error-prone. To estimate bone age using deep neural network models, a lot of research has been done, our effort has been to improve the accuracy and speed of this process by using the introduced approach. After creating and analyzing our initial model, we focused on preprocessing and made the inputs smaller, and increased their quality. we selected small regions of hand radiographs and estimated the age of the bone only according to these regions. by doing this we improved bone age estimation accuracy even further than what was achieved in related works, without increasing the required computational resource. We reached a Mean Absolute Error (MAE) of 3.90 months in the range of 0-20 years and an MAE of 3.84 months in the range of 1-18 years on the RSNA test set.
Authors: Zander W. Blasingame, Chen Liu
Abstract: The optimization of the latents and parameters of diffusion models with respect to some differentiable metric defined on the output of the model is a challenging and complex problem. The sampling for diffusion models is done by solving either the probability flow ODE or diffusion SDE wherein a neural network approximates the score function or related quantity, allowing a numerical ODE/SDE solver to be used. However, na\"ive backpropagation techniques are memory intensive, requiring the storage of all intermediate states, and face additional complexity in handling the injected noise from the diffusion term of the diffusion SDE. We propose a novel method based on the stochastic adjoint sensitivity method to calculate the gradientwith respect to the initial noise, conditional information, and model parameters by solving an additional SDE whose solution is the gradient of the diffusion SDE. We exploit the unique construction of diffusion SDEs to further simplify the formulation of the adjoint diffusion SDE and use a change-of-variables to simplify the solution to an exponentially weighted integral. Using this formulation we derive a custom solver for the adjoint SDE as well as the simpler adjoint ODE. The proposed adjoint diffusion solvers can efficiently compute the gradients for both the probability flow ODE and diffusion SDE for latents and parameters of the model. Lastly, we demonstrate the effectiveness of the adjoint diffusion solvers onthe face morphing problem.
Authors: Manav Prabhakar, Jwalandhar Girnar, Arpan Kusari
Abstract: While there has been extensive work on generating physics-based adversarial samples recently, an overlooked class of such samples come from physical failures in the camera. Camera failures can occur as a result of an external physical process, i.e. breakdown of a component due to stress, or an internal component failure. In this work, we develop a simulated physical process for generating broken lens as a class of physics-based adversarial samples. We create a stress-based physical simulation by generating particles constrained in a mesh and apply stress at a random point and at a random angle. We perform stress propagation through the mesh and the end result of the mesh is a corresponding image which simulates the broken lens pattern. We also develop a neural emulator which learns the non-linear mapping between the mesh as a graph and the stress propagation using constrained propagation setup. We can then statistically compare the difference between the generated adversarial samples with real, simulated and emulated adversarial examples using the detection failure rate of the different classes and in between the samples using the Frechet Inception distance. Our goal through this work is to provide a robust physics based process for generating adversarial samples.
Authors: Xuanyu Zhang, Jiarui Meng, Runyi Li, Zhipei Xu, Yongbing Zhang, Jian Zhang
Abstract: 3D Gaussian Splatting (3DGS) has already become the emerging research focus in the fields of 3D scene reconstruction and novel view synthesis. Given that training a 3DGS requires a significant amount of time and computational cost, it is crucial to protect the copyright, integrity, and privacy of such 3D assets. Steganography, as a crucial technique for encrypted transmission and copyright protection, has been extensively studied. However, it still lacks profound exploration targeted at 3DGS. Unlike its predecessor NeRF, 3DGS possesses two distinct features: 1) explicit 3D representation; and 2) real-time rendering speeds. These characteristics result in the 3DGS point cloud files being public and transparent, with each Gaussian point having a clear physical significance. Therefore, ensuring the security and fidelity of the original 3D scene while embedding information into the 3DGS point cloud files is an extremely challenging task. To solve the above-mentioned issue, we first propose a steganography framework for 3DGS, dubbed GS-Hider, which can embed 3D scenes and images into original GS point clouds in an invisible manner and accurately extract the hidden messages. Specifically, we design a coupled secured feature attribute to replace the original 3DGS's spherical harmonics coefficients and then use a scene decoder and a message decoder to disentangle the original RGB scene and the hidden message. Extensive experiments demonstrated that the proposed GS-Hider can effectively conceal multimodal messages without compromising rendering quality and possesses exceptional security, robustness, capacity, and flexibility. Our project is available at: https://xuanyuzhang21.github.io/project/gshider.
Authors: Yuanhao Cai, Zihao Xiao, Yixun Liang, Yulun Zhang, Xiaokang Yang, Yaoyao Liu, Alan Yuille
Abstract: High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques. The rendered HDR images capture a wider range of brightness levels containing more details of the scene than normal low dynamic range (LDR) images. Existing HDR NVS methods are mainly based on NeRF. They suffer from long training time and slow inference speed. In this paper, we propose a new framework, High Dynamic Range Gaussian Splatting (HDR-GS), which can efficiently render novel HDR views and reconstruct LDR images with a user input exposure time. Specifically, we design a Dual Dynamic Range (DDR) Gaussian point cloud model that uses spherical harmonics to fit HDR color and employs an MLP-based tone-mapper to render LDR color. The HDR and LDR colors are then fed into two Parallel Differentiable Rasterization (PDR) processes to reconstruct HDR and LDR views. To establish the data foundation for the research of 3D Gaussian splatting-based methods in HDR NVS, we recalibrate the camera parameters and compute the initial positions for Gaussian point clouds. Experiments demonstrate that our HDR-GS surpasses the state-of-the-art NeRF-based method by 3.84 and 1.91 dB on LDR and HDR NVS while enjoying 1000x inference speed and only requiring 6.3% training time.
Authors: Pratyusha Musunuru, Yuchao Li, Jamison Weber, Dimitri Bertsekas
Abstract: In this work, we consider data association problems involving multi-object tracking (MOT). In particular, we address the challenges arising from object occlusions. We propose a framework called approximate dynamic programming track (ADPTrack), which applies dynamic programming principles to improve an existing method called the base heuristic. Given a set of tracks and the next target frame, the base heuristic extends the tracks by matching them to the objects of this target frame directly. In contrast, ADPTrack first processes a few subsequent frames and applies the base heuristic starting from the next target frame to obtain tentative tracks. It then leverages the tentative tracks to match the objects of the target frame. This tends to reduce the occlusion-based errors and leads to an improvement over the base heuristic. When tested on the MOT17 video dataset, the proposed method demonstrates a 0.7% improvement in the association accuracy (IDF1 metric) over a state-of-the-art method that is used as the base heuristic. It also obtains improvements with respect to all the other standard metrics. Empirically, we found that the improvements are particularly pronounced in scenarios where the video data is obtained by fixed-position cameras.
Authors: Lizhi Bai, Chunqi Tian, Jun Yang, Siyu Zhang, Weijian Liang
Abstract: Neural implicit representations have recently demonstrated considerable potential in the field of visual simultaneous localization and mapping (SLAM). This is due to their inherent advantages, including low storage overhead and representation continuity. However, these methods necessitate the size of the scene as input, which is impractical for unknown scenes. Consequently, we propose NeB-SLAM, a neural block-based scalable RGB-D SLAM for unknown scenes. Specifically, we first propose a divide-and-conquer mapping strategy that represents the entire unknown scene as a set of sub-maps. These sub-maps are a set of neural blocks of fixed size. Then, we introduce an adaptive map growth strategy to achieve adaptive allocation of neural blocks during camera tracking and gradually cover the whole unknown scene. Finally, extensive evaluations on various datasets demonstrate that our method is competitive in both mapping and tracking when targeting unknown environments.
Authors: Leyuan Wang, Liuyu Xiang, Yujie Wei, Yunlong Wang, Zhaofeng He
Abstract: Online Lifelong Learning (OLL) addresses the challenge of learning from continuous and non-stationary data streams. Existing online lifelong learning methods based on image classification models often require preset conditions such as the total number of classes or maximum memory capacity, which hinders the realization of real never-ending learning and renders them impractical for real-world scenarios. In this work, we propose that vision-language models, such as Contrastive Language-Image Pretraining (CLIP), are more suitable candidates for online lifelong learning. We discover that maintaining symmetry between image and text is crucial during Parameter-Efficient Tuning (PET) for CLIP model in online lifelong learning. To this end, we introduce the Symmetric Image-Text (SIT) tuning strategy. We conduct extensive experiments on multiple lifelong learning benchmark datasets and elucidate the effectiveness of SIT through gradient analysis. Additionally, we assess the impact of lifelong learning on generalizability of CLIP and found that tuning the image encoder is beneficial for lifelong learning, while tuning the text encoder aids in zero-shot learning.
Authors: Leyuan Wang, Liuyu Xiang, Yunlong Wang, Huijia Wu, Zhaofeng He
Abstract: Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argue that the imbalance between old task and new task data contributes to forgetting of the old tasks. Moreover, the increasing imbalance ratio during incremental learning further aggravates the problem. To address the dynamic imbalance issue, we propose Uniform Prototype Contrastive Learning (UPCL), where uniform and compact features are learned. Specifically, we generate a set of non-learnable uniform prototypes before each task starts. Then we assign these uniform prototypes to each class and guide the feature learning through prototype contrastive learning. We also dynamically adjust the relative margin between old and new classes so that the feature distribution will be maintained balanced and compact. Finally, we demonstrate through extensive experiments that the proposed method achieves state-of-the-art performance on several benchmark datasets including CIFAR100, ImageNet100 and TinyImageNet.
Authors: Sucheng Ren, Hongru Zhu, Chen Wei, Yijiang Li, Alan Yuille, Cihang Xie
Abstract: This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two key designs are included. First, we organize autoregressive video tokens into clusters that span both spatially and temporally, thereby enabling a richer aggregation of contextual information compared to the standard spatial-only or temporal-only clusters. Second, we adopt a randomized spatiotemporal prediction order to facilitate learning from multi-dimensional data, addressing the limitations of a handcrafted spatial-first or temporal-first sequence order. Extensive experiments establish ARVideo as an effective paradigm for self-supervised video representation learning. For example, when trained with the ViT-B backbone, ARVideo competitively attains 81.2% on Kinetics-400 and 70.9% on Something-Something V2, which are on par with the strong benchmark set by VideoMAE. Importantly, ARVideo also demonstrates higher training efficiency, i.e., it trains 14% faster and requires 58% less GPU memory compared to VideoMAE.
Authors: Weize Li, Zhicheng Zhao, Haochen Bai, Fei Su
Abstract: Referring Expression Segmentation (RES) has attracted rising attention, aiming to identify and segment objects based on natural language expressions. While substantial progress has been made in RES, the emergence of Generalized Referring Expression Segmentation (GRES) introduces new challenges by allowing expressions to describe multiple objects or lack specific object references. Existing RES methods, usually rely on sophisticated encoder-decoder and feature fusion modules, and are difficult to generate class prototypes that match each instance individually when confronted with the complex referent and binary labels of GRES. In this paper, reevaluating the differences between RES and GRES, we propose a novel Model with Adaptive Binding Prototypes (MABP) that adaptively binds queries to object features in the corresponding region. It enables different query vectors to match instances of different categories or different parts of the same instance, significantly expanding the decoder's flexibility, dispersing global pressure across all queries, and easing the demands on the encoder. Experimental results demonstrate that MABP significantly outperforms state-of-the-art methods in all three splits on gRefCOCO dataset. Meanwhile, MABP also surpasses state-of-the-art methods on RefCOCO+ and G-Ref datasets, and achieves very competitive results on RefCOCO. Code is available at https://github.com/buptLwz/MABP
Authors: Song Wang, Jiawei Yu, Wentong Li, Hao Shi, Kailun Yang, Junbo Chen, Jianke Zhu
Abstract: Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving. Prior endeavors concentrate on constructing the network or benchmark in a fully supervised manner. While the dense occupancy grids need point-wise semantic annotations, which incur expensive and tedious labeling costs. In this paper, we build a new label-efficient benchmark, named ScribbleSC, where the sparse scribble-based semantic labels are combined with dense geometric labels for semantic scene completion. In particular, we propose a simple yet effective approach called Scribble2Scene, which bridges the gap between the sparse scribble annotations and fully-supervision. Our method consists of geometric-aware auto-labelers construction and online model training with an offline-to-online distillation module to enhance the performance. Experiments on SemanticKITTI demonstrate that Scribble2Scene achieves competitive performance against the fully-supervised counterparts, showing 99% performance of the fully-supervised models with only 13.5% voxels labeled. Both annotations of ScribbleSC and our full implementation are available at https://github.com/songw-zju/Scribble2Scene.
Authors: Xinan He, Yue Zhou, Wei Ye, Feng Ding
Abstract: Prior DeepFake detection methods have faced a core challenge in preserving generalizability and fairness effectively. In this paper, we proposed an approach akin to decoupling and sublimating forgery semantics, named astray-learning. The primary objective of the proposed method is to blend hybrid forgery semantics derived from high-frequency components into authentic imagery, named aberrations. The ambiguity of aberrations is beneficial to reducing the model's bias towards specific semantics. Consequently, it can enhance the model's generalization ability and maintain the detection fairness. All codes for astray-learning are publicly available at https://anonymous.4open.science/r/astray-learning-C49B .
URLs: https://anonymous.4open.science/r/astray-learning-C49B
Authors: Pan Liao, Feng Yang, Di Wu, Liu Bo
Abstract: Monocular vision-based 3D object detection is crucial in various sectors, yet existing methods face significant challenges in terms of accuracy and computational efficiency. Building on the successful strategies in 2D detection and depth estimation, we propose MonoDETRNext, which seeks to optimally balance precision and processing speed. Our methodology includes the development of an efficient hybrid visual encoder, enhancement of depth prediction mechanisms, and introduction of an innovative query generation strategy, augmented by an advanced depth predictor. Building on MonoDETR, MonoDETRNext introduces two variants: MonoDETRNext-F, which emphasizes speed, and MonoDETRNext-A, which focuses on precision. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 4.60% improvement in the AP3D metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-F showed a 2.21% increase. Additionally, the computational efficiency of MonoDETRNext-F slightly exceeds that of its predecessor.
Authors: Bingchen Yang, Haiyong Jiang, Hao Pan, Peter Wonka, Jun Xiao, Guosheng Lin
Abstract: Reverse engineering CAD models from raw geometry is a classic but challenging research problem. In particular, reconstructing the CAD modeling sequence from point clouds provides great interpretability and convenience for editing. To improve upon this problem, we introduce geometric guidance into the reconstruction network. Our proposed model, PS-CAD, reconstructs the CAD modeling sequence one step at a time. At each step, we provide two forms of geometric guidance. First, we provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. This helps the framework to focus on regions that still need work. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces where a CAD extrusion step could be started. Our framework has three major components. Geometric guidance computation extracts the two types of geometric guidance. Single-step reconstruction computes a single candidate CAD modeling step for each provided prompt. Single-step selection selects among the candidate CAD modeling steps. The process continues until the reconstruction is completed. Our quantitative results show a significant improvement across all metrics. For example, on the dataset DeepCAD, PS-CAD improves upon the best published SOTA method by reducing the geometry errors (CD and HD) by 10%, and the structural error (ECD metric) by about 15%.
Authors: Haoxuan Qu, Zhuoling Li, Hossein Rahmani, Yujun Cai, Jun Liu
Abstract: Recently, Gaussian Splatting, a method that represents a 3D scene as a collection of Gaussian distributions, has gained significant attention in addressing the task of novel view synthesis. In this paper, we highlight a fundamental limitation of Gaussian Splatting: its inability to accurately render discontinuities and boundaries in images due to the continuous nature of Gaussian distributions. To address this issue, we propose a novel framework enabling Gaussian Splatting to perform discontinuity-aware image rendering. Additionally, we introduce a B\'ezier-boundary gradient approximation strategy within our framework to keep the ``differentiability'' of the proposed discontinuity-aware rendering process. Extensive experiments demonstrate the efficacy of our framework.
Authors: Jingyuan Zhu, Shiyu Li, Yuxuan Liu, Ping Huang, Jiulong Shan, Huimin Ma, Jian Yuan
Abstract: Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation quality and the controllability for complex scenes containing multi-class objects and dense objects with occlusions remain limited. This paper presents ODGEN, a novel method to generate high-quality images conditioned on bounding boxes, thereby facilitating data synthesis for object detection. Given a domain-specific object detection dataset, we first fine-tune a pre-trained diffusion model on both cropped foreground objects and entire images to fit target distributions. Then we propose to control the diffusion model using synthesized visual prompts with spatial constraints and object-wise textual descriptions. ODGEN exhibits robustness in handling complex scenes and specific domains. Further, we design a dataset synthesis pipeline to evaluate ODGEN on 7 domain-specific benchmarks to demonstrate its effectiveness. Adding training data generated by ODGEN improves up to 25.3% mAP@.50:.95 with object detectors like YOLOv5 and YOLOv7, outperforming prior controllable generative methods. In addition, we design an evaluation protocol based on COCO-2014 to validate ODGEN in general domains and observe an advantage up to 5.6% in mAP@.50:.95 against existing methods.
Authors: Hyungtae Lee, Yan Zhang, Yi-Ting Shen, Heesung Kwon, Shuvra S. Bhattacharyya
Abstract: Aerial-view human detection has a large demand for large-scale data to capture more diverse human appearances compared to ground-view human detection. Therefore, synthetic data can be a good resource to expand data, but the domain gap with real-world data is the biggest obstacle to its use in training. As a common solution to deal with the domain gap, the sim2real transformation is used, and its quality is affected by three factors: i) the real data serving as a reference when calculating the domain gap, ii) the synthetic data chosen to avoid the transformation quality degradation, and iii) the synthetic data pool from which the synthetic data is selected. In this paper, we investigate the impact of these factors on maximizing the effectiveness of synthetic data in training in terms of improving learning performance and acquiring domain generalization ability--two main benefits expected of using synthetic data. As an evaluation metric for the second benefit, we introduce a method for measuring the distribution gap between two datasets, which is derived as the normalized sum of the Mahalanobis distances of all test data. As a result, we have discovered several important findings that have never been investigated or have been used previously without accurate understanding. We expect that these findings can break the current trend of either naively using or being hesitant to use synthetic data in machine learning due to the lack of understanding, leading to more appropriate use in future research.
Authors: Sami Arja, Alexandre Marcireau, Saeed Afshar, Bharath Ramesh, Gregory Cohen
Abstract: Achieving optimal performance with frame-based vision sensors on aerial platforms poses a significant challenge due to the fundamental tradeoffs between bandwidth and latency. Event cameras, which draw inspiration from biological vision systems, present a promising alternative due to their exceptional temporal resolution, superior dynamic range, and minimal power requirements. Due to these properties, they are well-suited for processing and segmenting fast motions that require rapid reactions. However, previous methods for event-based motion segmentation encountered limitations, such as the need for per-scene parameter tuning or manual labelling to achieve satisfactory results. To overcome these issues, our proposed method leverages features from self-supervised transformers on both event data and optical flow information, eliminating the need for human annotations and reducing the parameter tuning problem. In this paper, we use an event camera with HD resolution onboard a highly dynamic aerial platform in an urban setting. We conduct extensive evaluations of our framework across multiple datasets, demonstrating state-of-the-art performance compared to existing works. Our method can effectively handle various types of motion and an arbitrary number of moving objects. Code and dataset are available at: \url{https://samiarja.github.io/evairborne/}
Authors: Qingdong He, Jiangning Zhang, Jinlong Peng, Haoyang He, Yabiao Wang, Chengjie Wang
Abstract: Transformers have revolutionized the point cloud learning task, but the quadratic complexity hinders its extension to long sequence and makes a burden on limited computational resources. The recent advent of RWKV, a fresh breed of deep sequence models, has shown immense potential for sequence modeling in NLP tasks. In this paper, we present PointRWKV, a model of linear complexity derived from the RWKV model in the NLP field with necessary modifications for point cloud learning tasks. Specifically, taking the embedded point patches as input, we first propose to explore the global processing capabilities within PointRWKV blocks using modified multi-headed matrix-valued states and a dynamic attention recurrence mechanism. To extract local geometric features simultaneously, we design a parallel branch to encode the point cloud efficiently in a fixed radius near-neighbors graph with a graph stabilizer. Furthermore, we design PointRWKV as a multi-scale framework for hierarchical feature learning of 3D point clouds, facilitating various downstream tasks. Extensive experiments on different point cloud learning tasks show our proposed PointRWKV outperforms the transformer- and mamba-based counterparts, while significantly saving about 46\% FLOPs, demonstrating the potential option for constructing foundational 3D models.
Authors: Vikas Thamizharasan, Difan Liu, Matthew Fisher, Nanxuan Zhao, Evangelos Kalogerakis, Michal Lukac
Abstract: The success of denoising diffusion models in representing rich data distributions over 2D raster images has prompted research on extending them to other data representations, such as vector graphics. Unfortunately due to their variable structure and scarcity of vector training data, directly applying diffusion models on this domain remains a challenging problem. Using workarounds like optimization via Score Distillation Sampling (SDS) is also fraught with difficulty, as vector representations are non trivial to directly optimize and tend to result in implausible geometries such as redundant or self-intersecting shapes. NIVeL addresses these challenges by reinterpreting the problem on an alternative, intermediate domain which preserves the desirable properties of vector graphics -- mainly sparsity of representation and resolution-independence. This alternative domain is based on neural implicit fields expressed in a set of decomposable, editable layers. Based on our experiments, NIVeL produces text-to-vector graphics results of significantly better quality than the state-of-the-art.
Authors: Yanwei Zheng, Changrui Li, Chuanlin Lan, Yaling Li, Xiao Zhang, Yifei Zou, Dongxiao Yu, Zhipeng Cai
Abstract: Zero-shot object navigation (ZSON) addresses situation where an agent navigates to an unseen object that does not present in the training set. Previous works mainly train agent using seen objects with known labels, and ignore the seen objects without labels. In this paper, we introduce seen objects without labels, herein termed as ``unknown objects'', into training procedure to enrich the agent's knowledge base with distinguishable but previously overlooked information. Furthermore, we propose the label-wise meta-correlation module (LWMCM) to harness relationships among objects with and without labels, and obtain enhanced objects information. Specially, we propose target feature generator (TFG) to generate the features representation of the unlabeled target objects. Subsequently, the unlabeled object identifier (UOI) module assesses whether the unlabeled target object appears in the current observation frame captured by the camera and produces an adapted target features representation specific to the observed context. In meta contrastive feature modifier (MCFM), the target features is modified via approaching the features of objects within the observation frame while distancing itself from features of unobserved objects. Finally, the meta object-graph learner (MOGL) module is utilized to calculate the relationships among objects based on the features. Experiments conducted on AI2THOR and RoboTHOR platforms demonstrate the effectiveness of our proposed method.
Authors: Jialong Wu, Shaofeng Yin, Ningya Feng, Xu He, Dong Li, Jianye Hao, Mingsheng Long
Abstract: World models empower model-based agents to interactively explore, reason, and plan within imagined environments for real-world decision-making. However, the high demand for interactivity poses challenges in harnessing recent advancements in video generative models for developing world models at scale. This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction. iVideoGPT features a novel compressive tokenization technique that efficiently discretizes high-dimensional visual observations. Leveraging its scalable architecture, we are able to pre-train iVideoGPT on millions of human and robotic manipulation trajectories, establishing a versatile foundation that is adaptable to serve as interactive world models for a wide range of downstream tasks. These include action-conditioned video prediction, visual planning, and model-based reinforcement learning, where iVideoGPT achieves competitive performance compared with state-of-the-art methods. Our work advances the development of interactive general world models, bridging the gap between generative video models and practical model-based reinforcement learning applications.
Authors: Yajing Liu, Shijun Zhou, Xiyao Liu, Chunhui Hao, Baojie Fan, Jiandong Tian
Abstract: Single-source domain generalization (SDG) for object detection is a challenging yet essential task as the distribution bias of the unseen domain degrades the algorithm performance significantly. However, existing methods attempt to extract domain-invariant features, neglecting that the biased data leads the network to learn biased features that are non-causal and poorly generalizable. To this end, we propose an Unbiased Faster R-CNN (UFR) for generalizable feature learning. Specifically, we formulate SDG in object detection from a causal perspective and construct a Structural Causal Model (SCM) to analyze the data bias and feature bias in the task, which are caused by scene confounders and object attribute confounders. Based on the SCM, we design a Global-Local Transformation module for data augmentation, which effectively simulates domain diversity and mitigates the data bias. Additionally, we introduce a Causal Attention Learning module that incorporates a designed attention invariance loss to learn image-level features that are robust to scene confounders. Moreover, we develop a Causal Prototype Learning module with an explicit instance constraint and an implicit prototype constraint, which further alleviates the negative impact of object attribute confounders. Experimental results on five scenes demonstrate the prominent generalization ability of our method, with an improvement of 3.9% mAP on the Night-Clear scene.
Authors: Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Xiaobo Xia, Tongliang Liu, Min Yang, Binyuan Hui
Abstract: The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs). While LMMs have achieved tremendous success by promoting the synergy between multimodal comprehension and creation, they often face challenges when confronted with out-of-distribution data. This is primarily due to their reliance on image encoders trained to encode images into task-relevant features, which may lead them to disregard irrelevant details. Delving into the modeling capabilities of diffusion models for images naturally prompts the question: Can diffusion models serve as the eyes of large language models for image perception? In this paper, we propose DEEM, a simple and effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. This addresses the drawbacks of previous methods that solely relied on image encoders like ViT, thereby enhancing the model's resilience against out-of-distribution samples and reducing visual hallucinations. Importantly, this is achieved without requiring additional training modules and with fewer training parameters. We extensively evaluated DEEM on both our newly constructed RobustVQA benchmark and another well-known benchmark, POPE, for object hallucination. Compared to the state-of-the-art interleaved content generation models, DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data (10%), and a smaller base model size.
Authors: Yimeng Zhang, Xin Chen, Jinghan Jia, Yihua Zhang, Chongyu Fan, Jiancheng Liu, Mingyi Hong, Ke Ding, Sijia Liu
Abstract: Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also known as concept erasing, have been developed to address these risks. However, these techniques remain vulnerable to adversarial prompt attacks, which can prompt DMs post-unlearning to regenerate undesired images containing concepts (such as nudity) meant to be erased. This work aims to enhance the robustness of concept erasing by integrating the principle of adversarial training (AT) into machine unlearning, resulting in the robust unlearning framework referred to as AdvUnlearn. However, achieving this effectively and efficiently is highly nontrivial. First, we find that a straightforward implementation of AT compromises DMs' image generation quality post-unlearning. To address this, we develop a utility-retaining regularization on an additional retain set, optimizing the trade-off between concept erasure robustness and model utility in AdvUnlearn. Moreover, we identify the text encoder as a more suitable module for robustification compared to UNet, ensuring unlearning effectiveness. And the acquired text encoder can serve as a plug-and-play robust unlearner for various DM types. Empirically, we perform extensive experiments to demonstrate the robustness advantage of AdvUnlearn across various DM unlearning scenarios, including the erasure of nudity, objects, and style concepts. In addition to robustness, AdvUnlearn also achieves a balanced tradeoff with model utility. To our knowledge, this is the first work to systematically explore robust DM unlearning through AT, setting it apart from existing methods that overlook robustness in concept erasing. Codes are available at: https://github.com/OPTML-Group/AdvUnlearn
Authors: Li Zhang, Yuankun Yang, Ziyang Xie, Zhiyuan Yuan, Jianfeng Feng, Xiatian Zhu, Yu-Gang Jiang
Abstract: Understanding the hidden mechanisms behind human's visual perception is a fundamental quest in neuroscience, underpins a wide variety of critical applications, e.g. clinical diagnosis. To that end, investigating into the neural responses of human mind activities, such as functional Magnetic Resonance Imaging (fMRI), has been a significant research vehicle. However, analyzing fMRI signals is challenging, costly, daunting, and demanding for professional training. Despite remarkable progress in artificial intelligence (AI) based fMRI analysis, existing solutions are limited and far away from being clinically meaningful. In this context, we leap forward to demonstrate how AI can go beyond the current state of the art by decoding fMRI into visually plausible 3D visuals, enabling automatic clinical analysis of fMRI data, even without healthcare professionals. Innovationally, we reformulate the task of analyzing fMRI data as a conditional 3D scene reconstruction problem. We design a novel cross-modal 3D scene representation learning method, Brain3D, that takes as input the fMRI data of a subject who was presented with a 2D object image, and yields as output the corresponding 3D object visuals. Importantly, we show that in simulated scenarios our AI agent captures the distinct functionalities of each region of human vision system as well as their intricate interplay relationships, aligning remarkably with the established discoveries of neuroscience. Non-expert diagnosis indicate that Brain3D can successfully identify the disordered brain regions, such as V1, V2, V3, V4, and the medial temporal lobe (MTL) within the human visual system. We also present results in cross-modal 3D visual construction setting, showcasing the perception quality of our 3D scene generation.
Authors: Neehar Kondapaneni, Markus Marks, Oisin MacAodha, Pietro Perona
Abstract: We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual explanations that are critical for discriminating between classes. This is achieved by simultaneously optimizing three criteria: the explanations should be few, diverse, and human-interpretable. Our approach builds on the recently introduced Concept Relevance Propagation (CRP) explainability method. While CRP is effective at describing individual neuronal activations, it generates too many concepts, which impacts human comprehension. Instead, DCNE selects the few most important explanations. We introduce a new evaluation dataset centered on the challenging task of classifying birds, enabling us to compare the alignment of DCNE's explanations to those of human expert-defined ones. Compared to existing eXplainable Artificial Intelligence (XAI) methods, DCNE has a desirable trade-off between conciseness and completeness when summarizing network explanations. It produces 1/30 of CRP's explanations while only resulting in a slight reduction in explanation quality. DCNE represents a step forward in making neural network decisions accessible and interpretable to humans, providing a valuable tool for both researchers and practitioners in XAI and model alignment.
Authors: Leif Bergerhoff
Abstract: We come up with a novel application for image analysis methods in the context of direction dependent signal characteristics. For this purpose, we describe an inpainting approach adding benefit to technical signal information which are typically only used for monitoring and control purposes in ground station operations. Recalling the theoretical properties of the employed inpainting technique and appropriate modeling allow us to demonstrate the usefulness of our approach for satellite data reception quality assessment. In our application, we show the advantages of inpainting products over raw data as well as the rich potential of the visualization of technical signal information.
Authors: Saul Fuster, Farbod Khoraminia, Julio Silva-Rodr\'iguez, Umay Kiraz, Geert J. L. H. van Leenders, Trygve Eftest{\o}l, Valery Naranjo, Emiel A. M. Janssen, Tahlita C. M. Zuiverloon, Kjersti Engan
Abstract: We present a pioneering investigation into the application of deep learning techniques to analyze histopathological images for addressing the substantial challenge of automated prognostic prediction. Prognostic prediction poses a unique challenge as the ground truth labels are inherently weak, and the model must anticipate future events that are not directly observable in the image. To address this challenge, we propose a novel three-part framework comprising of a convolutional network based tissue segmentation algorithm for region of interest delineation, a contrastive learning module for feature extraction, and a nested multiple instance learning classification module. Our study explores the significance of various regions of interest within the histopathological slides and exploits diverse learning scenarios. The pipeline is initially validated on artificially generated data and a simpler diagnostic task. Transitioning to prognostic prediction, tasks become more challenging. Employing bladder cancer as use case, our best models yield an AUC of 0.721 and 0.678 for recurrence and treatment outcome prediction respectively.
Authors: Jiayi Chen, Rong Quan, Jie Qin
Abstract: Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in addressing CD-FSS. However, they completely rely on support images for feature transformation, and repeatedly utilizing a few support images for each class may easily lead to overfitting and overlooking intra-class appearance differences. In this paper, we propose a Doubly Matching Transformation-based Network (DMTNet) to solve the above issue. Instead of completely relying on support images, we propose Self-Matching Transformation (SMT) to construct query-specific transformation matrices based on query images themselves to transform domain-specific query features into domain-agnostic ones. Calculating query-specific transformation matrices can prevent overfitting, especially for the meta-testing stage where only one or several images are used as support images to segment hundreds or thousands of images. After obtaining domain-agnostic features, we exploit a Dual Hypercorrelation Construction (DHC) module to explore the hypercorrelations between the query image with the foreground and background of the support image, based on which foreground and background prediction maps are generated and supervised, respectively, to enhance the segmentation result. In addition, we propose a Test-time Self-Finetuning (TSF) strategy to more accurately self-tune the query prediction in unseen domains. Extensive experiments on four popular datasets show that DMTNet achieves superior performance over state-of-the-art approaches. Code is available at https://github.com/ChenJiayi68/DMTNet.
Authors: Haoxuan Qu, Zhaoyang He, Zeyu Hu, Yujun Cai, Jun Liu
Abstract: To facilitate the application of motion prediction in practice, recently, the few-shot motion prediction task has attracted increasing research attention. Yet, in existing few-shot motion prediction works, a specific model that is dedicatedly trained over human motions is generally required. In this work, rather than tackling this task through training a specific human motion prediction model, we instead propose a novel FMP-OC framework. In FMP-OC, in a totally training-free manner, we enable Few-shot Motion Prediction, which is a non-language task, to be performed directly via utilizing the Off-the-shelf language model ChatGPT. Specifically, to lead ChatGPT as a language model to become an accurate motion predictor, in FMP-OC, we first introduce several novel designs to facilitate extracting implicit knowledge from ChatGPT. Moreover, we also incorporate our framework with a motion-in-context learning mechanism. Extensive experiments demonstrate the efficacy of our proposed framework.
Authors: Yuwei Niu, Shuo He, Qi Wei, Feng Liu, Lei Feng
Abstract: Multimodal contrastive learning methods (e.g., CLIP) have shown impressive zero-shot classification performance due to their strong ability to joint representation learning for visual and textual modalities. However, recent research revealed that multimodal contrastive learning on poisoned pre-training data with a small proportion of maliciously backdoored data can induce backdoored CLIP that could be attacked by inserted triggers in downstream tasks with a high success rate. To defend against backdoor attacks on CLIP, existing defense methods focus on either the pre-training stage or the fine-tuning stage, which would unfortunately cause high computational costs due to numerous parameter updates. In this paper, we provide the first attempt at a computationally efficient backdoor detection method to defend against backdoored CLIP in the inference stage. We empirically find that the visual representations of backdoored images are insensitive to both benign and malignant changes in class description texts. Motivated by this observation, we propose BDetCLIP, a novel test-time backdoor detection method based on contrastive prompting. Specifically, we first prompt the language model (e.g., GPT-4) to produce class-related description texts (benign) and class-perturbed random texts (malignant) by specially designed instructions. Then, the distribution difference in cosine similarity between images and the two types of class description texts can be used as the criterion to detect backdoor samples. Extensive experiments validate that our proposed BDetCLIP is superior to state-of-the-art backdoor detection methods, in terms of both effectiveness and efficiency.
Authors: Yuhang Liu, Boyi Sun, Guixu Zheng, Yishuo Wang, Jing Wang, Fei-Yue Wang
Abstract: LiDAR sensors play a crucial role in various applications, especially in autonomous driving. Current research primarily focuses on optimizing perceptual models with point cloud data as input, while the exploration of deeper cognitive intelligence remains relatively limited. To address this challenge, parallel LiDARs have emerged as a novel theoretical framework for the next-generation intelligent LiDAR systems, which tightly integrate physical, digital, and social systems. To endow LiDAR systems with cognitive capabilities, we introduce the 3D visual grounding task into parallel LiDARs and present a novel human-computer interaction paradigm for LiDAR systems. We propose Talk2LiDAR, a large-scale benchmark dataset tailored for 3D visual grounding in autonomous driving. Additionally, we present a two-stage baseline approach and an efficient one-stage method named BEVGrounding, which significantly improves grounding accuracy by fusing coarse-grained sentence and fine-grained word embeddings with visual features. Our experiments on Talk2Car-3D and Talk2LiDAR datasets demonstrate the superior performance of BEVGrounding, laying a foundation for further research in this domain.
Authors: Shuai Jiang, Zhu Meng, Delong Liu, Haiwen Li, Fei Su, Zhicheng Zhao
Abstract: Brain decoding, which aims at reconstructing visual stimuli from brain signals, primarily utilizing functional magnetic resonance imaging (fMRI), has recently made positive progress. However, it is impeded by significant challenges such as the difficulty of acquiring fMRI-image pairs and the variability of individuals, etc. Most methods have to adopt the per-subject-per-model paradigm, greatly limiting their applications. To alleviate this problem, we introduce a new and meaningful task, few-shot brain decoding, while it will face two inherent difficulties: 1) the scarcity of fMRI-image pairs and the noisy signals can easily lead to overfitting; 2) the inadequate guidance complicates the training of a robust encoder. Therefore, a novel framework named MindShot, is proposed to achieve effective few-shot brain decoding by leveraging cross-subject prior knowledge. Firstly, inspired by the hemodynamic response function (HRF), the HRF adapter is applied to eliminate unexplainable cognitive differences between subjects with small trainable parameters. Secondly, a Fourier-based cross-subject supervision method is presented to extract additional high-level and low-level biological guidance information from signals of other subjects. Under the MindShot, new subjects and pretrained individuals only need to view images of the same semantic class, significantly expanding the model's applicability. Experimental results demonstrate MindShot's ability of reconstructing semantically faithful images in few-shot scenarios and outperforms methods based on the per-subject-per-model paradigm. The promising results of the proposed method not only validate the feasibility of few-shot brain decoding but also provide the possibility for the learning of large models under the condition of reducing data dependence.
Authors: Chengming Xu, Chen Liu, Yikai Wang, Yanwei Fu
Abstract: Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query sample. The fundamental problem in VICL is how to select the best prompt to activate its power as much as possible, which is equivalent to the ranking problem to test the in-context behavior of each candidate in the alternative set and select the best one. To utilize more appropriate ranking metric and leverage more comprehensive information among the alternative set, we propose a novel in-context example selection framework to approximately identify the global optimal prompt, i.e. choosing the best performing in-context examples from all alternatives for each query sample. Our method, dubbed Partial2Global, adopts a transformer-based list-wise ranker to provide a more comprehensive comparison within several alternatives, and a consistency-aware ranking aggregator to generate globally consistent ranking. The effectiveness of Partial2Global is validated through experiments on foreground segmentation, single object detection and image colorization, demonstrating that Partial2Global selects consistently better in-context examples compared with other methods, and thus establish the new state-of-the-arts.
Authors: Boyi Sun, Yuhang Liu, Xingxia Wang, Bin Tian, Long Chen, Fei-Yue Wang
Abstract: Point cloud data labeling is considered a time-consuming and expensive task in autonomous driving, whereas unsupervised learning can avoid it by learning point cloud representations from unannotated data. In this paper, we propose UOV, a novel 3D Unsupervised framework assisted by 2D Open-Vocabulary segmentation models. It consists of two stages: In the first stage, we innovatively integrate high-quality textual and image features of 2D open-vocabulary models and propose the Tri-Modal contrastive Pre-training (TMP). In the second stage, spatial mapping between point clouds and images is utilized to generate pseudo-labels, enabling cross-modal knowledge distillation. Besides, we introduce the Approximate Flat Interaction (AFI) to address the noise during alignment and label confusion. To validate the superiority of UOV, extensive experiments are conducted on multiple related datasets. We achieved a record-breaking 47.73% mIoU on the annotation-free point cloud segmentation task in nuScenes, surpassing the previous best model by 10.70% mIoU. Meanwhile, the performance of fine-tuning with 1% data on nuScenes and SemanticKITTI reached a remarkable 51.75% mIoU and 48.14% mIoU, outperforming all previous pre-trained models.
Authors: Chengming Xu, Kai Hu, Donghao Luo, Jiangning Zhang, Wei Li, Yanhao Ge, Chengjie Wang
Abstract: Stylized Text-to-Image Generation (STIG) aims to generate images based on text prompts and style reference images. We in this paper propose a novel framework dubbed as StyleMaster for this task by leveraging pretrained Stable Diffusion (SD), which tries to solve the previous problems such as insufficient style and inconsistent semantics. The enhancement lies in two novel module, namely multi-source style embedder and dynamic attention adapter. In order to provide SD with better style embeddings, we propose the multi-source style embedder considers both global and local level visual information along with textual one, which provide both complementary style-related and semantic-related knowledge. Additionally, aiming for better balance between the adaptor capacity and semantic control, the proposed dynamic attention adapter is applied to the diffusion UNet in which adaptation weights are dynamically calculated based on the style embeddings. Two objective functions are introduced to optimize the model together with denoising loss, which can further enhance semantic and style consistency. Extensive experiments demonstrate the superiority of StyleMaster over existing methods, rendering images with variable target styles while successfully maintaining the semantic information from the text prompts.
Authors: Zeen Song, Siyu Zhao, Xingyu Zhang, Jiangmeng Li, Changwen Zheng, Wenwen Qiang
Abstract: Pre-trained large-scale models have become a major research focus, but their effectiveness is limited in real-world applications due to diverse data distributions. In contrast, humans excel at decision-making across various domains by learning reusable knowledge that remains invariant despite environmental changes in a complex world. Although CLIP, as a successful vision-language pre-trained model, demonstrates remarkable performance in various visual downstream tasks, our experiments reveal unsatisfactory results in specific domains. Our further analysis with causal inference exposes the current CLIP model's inability to capture the invariant causal mechanisms across domains, attributed to its deficiency in identifying latent factors generating the data. To address this, we propose the Invariant Causal Mechanism of CLIP (CLIP-ICM), an algorithm designed to provably identify invariant latent factors with the aid of interventional data, and perform accurate prediction on various domains. Theoretical analysis demonstrates that our method has a lower generalization bound in out-of-distribution (OOD) scenarios. Experimental results showcase the outstanding performance of CLIP-ICM.
Authors: Yifan Zhou, Wanli Peng, Zhongyu Yang, He Liu, Yi Sun
Abstract: The perception of transparent objects for grasp and manipulation remains a major challenge, because existing robotic grasp methods which heavily rely on depth maps are not suitable for transparent objects due to their unique visual properties. These properties lead to gaps and inaccuracies in the depth maps of the transparent objects captured by depth sensors. To address this issue, we propose an end-to-end network for transparent object depth completion that combines the strengths of single-view RGB-D based depth completion and multi-view depth estimation. Moreover, we introduce a depth refinement module based on confidence estimation to fuse predicted depth maps from single-view and multi-view modules, which further refines the restored depth map. The extensive experiments on the ClearPose and TransCG datasets demonstrate that our method achieves superior accuracy and robustness in complex scenarios with significant occlusion compared to the state-of-the-art methods.
Authors: Yibo Zhang, Lihong Wang, Changqing Zou, Tieru Wu, Rui Ma
Abstract: 3D sketches are widely used for visually representing the 3D shape and structure of objects or scenes. However, the creation of 3D sketch often requires users to possess professional artistic skills. Existing research efforts primarily focus on enhancing the ability of interactive sketch generation in 3D virtual systems. In this work, we propose Diff3DS, a novel differentiable rendering framework for generating view-consistent 3D sketch by optimizing 3D parametric curves under various supervisions. Specifically, we perform perspective projection to render the 3D rational B\'ezier curves into 2D curves, which are subsequently converted to a 2D raster image via our customized differentiable rasterizer. Our framework bridges the domains of 3D sketch and raster image, achieving end-toend optimization of 3D sketch through gradients computed in the 2D image domain. Our Diff3DS can enable a series of novel 3D sketch generation tasks, including textto-3D sketch and image-to-3D sketch, supported by the popular distillation-based supervision, such as Score Distillation Sampling (SDS). Extensive experiments have yielded promising results and demonstrated the potential of our framework.
Authors: Khanh-Binh Nguyen, Chae Jung Park
Abstract: Self-supervised learning (SSL) is gaining attention for its ability to learn effective representations with large amounts of unlabeled data. Lightweight models can be distilled from larger self-supervised pre-trained models using contrastive and consistency constraints. Still, the different sizes of the projection heads make it challenging for students to mimic the teacher's embedding accurately. We propose \textsc{Retro}, which reuses the teacher's projection head for students, and our experimental results demonstrate significant improvements over the state-of-the-art on all lightweight models. For instance, when training EfficientNet-B0 using ResNet-50/101/152 as teachers, our approach improves the linear result on ImageNet to $66.9\%$, $69.3\%$, and $69.8\%$, respectively, with significantly fewer parameters.
Authors: Aoxue Li, Mingyang Yi, Zhenguo Li
Abstract: Recently, text-to-image (T2I) editing has been greatly pushed forward by applying diffusion models. Despite the visual promise of the generated images, inconsistencies with the expected textual prompt remain prevalent. This paper aims to systematically improve the text-guided image editing techniques based on diffusion models, by addressing their limitations. Notably, the common idea in diffusion-based editing firstly reconstructs the source image via inversion techniques e.g., DDIM Inversion. Then following a fusion process that carefully integrates the source intermediate (hidden) states (obtained by inversion) with the ones of the target image. Unfortunately, such a standard pipeline fails in many cases due to the interference of texture retention and the new characters creation in some regions. To mitigate this, we incorporate human annotation as an external knowledge to confine editing within a ``Mask-informed'' region. Then we carefully Fuse the edited image with the source image and a constructed intermediate image within the model's Self-Attention module. Extensive empirical results demonstrate the proposed ``MaSaFusion'' significantly improves the existing T2I editing techniques.
Authors: Guibao Shen, Luozhou Wang, Jiantao Lin, Wenhang Ge, Chaozhe Zhang, Xin Tao, Yuan Zhang, Pengfei Wan, Zhongyuan Wang, Guangyong Chen, Yijun Li, Ying-Cong Chen
Abstract: Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accurate contextualization and structural control. So the generated images do not consistently align with human expectations, especially in complex scenarios involving multiple objects and relationships. In this paper, we introduce the Scene Graph Adapter(SG-Adapter), leveraging the structured representation of scene graphs to rectify inaccuracies in the original text embeddings. The SG-Adapter's explicit and non-fully connected graph representation greatly improves the fully connected, transformer-based text representations. This enhancement is particularly notable in maintaining precise correspondence in scenarios involving multiple relationships. To address the challenges posed by low-quality annotated datasets like Visual Genome, we have manually curated a highly clean, multi-relational scene graph-image paired dataset MultiRels. Furthermore, we design three metrics derived from GPT-4V to effectively and thoroughly measure the correspondence between images and scene graphs. Both qualitative and quantitative results validate the efficacy of our approach in controlling the correspondence in multiple relationships.
Authors: Mingyang Yi, Aoxue Li, Yi Xin, Zhenguo Li
Abstract: Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion image generator. Despite the success of DPM in practice, the mechanism behind it remains to be explored. To fill this blank, we begin by examining the intermediate statuses during the gradual denoising generation process in DPM. The empirical observations indicate, the shape of image is reconstructed after the first few denoising steps, and then the image is filled with details (e.g., texture). The phenomenon is because the low-frequency signal (shape relevant) of the noisy image is not corrupted until the final stage in the forward process (initial stage of generation) of adding noise in DPM. Inspired by the observations, we proceed to explore the influence of each token in the text prompt during the two stages. After a series of experiments of T2I generations conditioned on a set of text prompts. We conclude that in the earlier generation stage, the image is mostly decided by the special token [\texttt{EOS}] in the text prompt, and the information in the text prompt is already conveyed in this stage. After that, the diffusion model completes the details of generated images by information from themselves. Finally, we propose to apply this observation to accelerate the process of T2I generation by properly removing text guidance, which finally accelerates the sampling up to 25\%+.
Authors: Lichuan Ji, Yingqi Lin, Zhenhua Huang, Yan Han, Xiaogang Xu, Jiafei Wu, Chong Wang, Zhe Liu
Abstract: The development of AI-Generated Content (AIGC) has empowered the creation of remarkably realistic AI-generated videos, such as those involving Sora. However, the widespread adoption of these models raises concerns regarding potential misuse, including face video scams and copyright disputes. Addressing these concerns requires the development of robust tools capable of accurately determining video authenticity. The main challenges lie in the dataset and neural classifier for training. Current datasets lack a varied and comprehensive repository of real and generated content for effective discrimination. In this paper, we first introduce an extensive video dataset designed specifically for AI-Generated Video Detection (GenVidDet). It includes over 2.66 M instances of both real and generated videos, varying in categories, frames per second, resolutions, and lengths. The comprehensiveness of GenVidDet enables the training of a generalizable video detector. We also present the Dual-Branch 3D Transformer (DuB3D), an innovative and effective method for distinguishing between real and generated videos, enhanced by incorporating motion information alongside visual appearance. DuB3D utilizes a dual-branch architecture that adaptively leverages and fuses raw spatio-temporal data and optical flow. We systematically explore the critical factors affecting detection performance, achieving the optimal configuration for DuB3D. Trained on GenVidDet, DuB3D can distinguish between real and generated video content with 96.77% accuracy, and strong generalization capability even for unseen types.
Authors: Beitao Chen, Xinyu Lyu, Lianli Gao, Jingkuan Song, Heng Tao Shen
Abstract: Although Large Visual Language Models (LVLMs) have demonstrated exceptional abilities in understanding multimodal data, they invariably suffer from hallucinations, leading to a disconnect between the generated text and the corresponding images. Almost all current visual contrastive decoding methods attempt to mitigate these hallucinations by introducing visual uncertainty information that appropriately widens the contrastive logits gap between hallucinatory and targeted ones. However, due to uncontrollable nature of the global visual uncertainty, they struggle to precisely induce the hallucinatory tokens, which severely limits their effectiveness in mitigating hallucinations and may even lead to the generation of undesired hallucinations. To tackle this issue, we conducted the theoretical analysis to promote the effectiveness of contrast decoding. Building on this insight, we introduce a novel optimization strategy named Hallucination-Induced Optimization (HIO). This strategy seeks to amplify the contrast between hallucinatory and targeted tokens relying on a fine-tuned theoretical preference model (i.e., Contrary Bradley-Terry Model), thereby facilitating efficient contrast decoding to alleviate hallucinations in LVLMs. Extensive experimental research demonstrates that our HIO strategy can effectively reduce hallucinations in LVLMs, outperforming state-of-the-art methods across various benchmarks.
Authors: Meng You, Zhiyu Zhu, Hui Liu, Junhui Hou
Abstract: By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \textit{without} the need for training. NVS-Solver adaptively modulates the diffusion sampling process with the given views to enable the creation of remarkable visual experiences from single or multiple views of static scenes or monocular videos of dynamic scenes. Specifically, built upon our theoretical modeling, we iteratively modulate the score function with the given scene priors represented with warped input views to control the video diffusion process. Moreover, by theoretically exploring the boundary of the estimation error, we achieve the modulation in an adaptive fashion according to the view pose and the number of diffusion steps. Extensive evaluations on both static and dynamic scenes substantiate the significant superiority of our NVS-Solver over state-of-the-art methods both quantitatively and qualitatively. \textit{ Source code in } \href{https://github.com/ZHU-Zhiyu/NVS_Solver}{https://github.com/ZHU-Zhiyu/NVS$\_$Solver}.
URLs: https://github.com/ZHU-Zhiyu/NVS_Solver, https://github.com/ZHU-Zhiyu/NVS$\_$Solver
Authors: Bingyu Li, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li
Abstract: Multimodal semantic segmentation is a pivotal component of computer vision and typically surpasses unimodal methods by utilizing rich information set from various sources.Current models frequently adopt modality-specific frameworks that inherently biases toward certain modalities. Although these biases might be advantageous in specific situations, they generally limit the adaptability of the models across different multimodal contexts, thereby potentially impairing performance. To address this issue, we leverage the inherent capabilities of the model itself to discover the optimal equilibrium in multimodal fusion and introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation. Specifically, this method involves an unbiased integration of multimodal visual data. Additionally, we employ feature fusion at multiple scales to ensure the effective extraction and integration of both global and local features. Experimental results demonstrate that our approach achieves superior performance across multiple datasets, verifing its efficacy in enhancing the robustness and versatility of semantic segmentation in diverse settings. Our code is available at U3M-multimodal-semantic-segmentation.
Authors: Xia Li, Runzhao Yang, Xiangtai Li, Antony Lomax, Ye Zhang, Joachim Buhmann
Abstract: Motion information from 4D medical imaging offers critical insights into dynamic changes in patient anatomy for clinical assessments and radiotherapy planning and, thereby, enhances the capabilities of 3D image analysis. However, inherent physical and technical constraints of imaging hardware often necessitate a compromise between temporal resolution and image quality. Frame interpolation emerges as a pivotal solution to this challenge. Previous methods often suffer from discretion when they estimate the intermediate motion and execute the forward warping. In this study, we draw inspiration from fluid mechanics to propose a novel approach for continuously modeling patient anatomic motion using implicit neural representation. It ensures both spatial and temporal continuity, effectively bridging Eulerian and Lagrangian specifications together to naturally facilitate continuous frame interpolation. Our experiments across multiple datasets underscore the method's superior accuracy and speed. Furthermore, as a case-specific optimization (training-free) approach, it circumvents the need for extensive datasets and addresses model generalization issues.
Authors: Ho\`ang-\^An L\^e, Minh-Tan Pham
Abstract: Partial multi-task learning where training examples are annotated for one of the target tasks is a promising idea in remote sensing as it allows combining datasets annotated for different tasks and predicting more tasks with fewer network parameters. The na\"ive approach to partial multi-task learning is sub-optimal due to the lack of all-task annotations for learning joint representations. This paper proposes using knowledge distillation to replace the need of ground truths for the alternate task and enhance the performance of such approach. Experiments conducted on the public ISPRS 2D Semantic Labeling Contest dataset show the effectiveness of the proposed idea on partial multi-task learning for semantic tasks including object detection and semantic segmentation in aerial images.
Authors: Hyeonjae Gil, Myung-Hwan Jeon, Ayoung Kim
Abstract: Thermal infrared (TIR) cameras are emerging as promising sensors in safety-related fields due to their robustness against external illumination. However, RAW TIR image has 14 bits of pixel depth and needs to be rescaled into 8 bits for general applications. Previous works utilize a global 1D look-up table to compute pixel-wise gain solely based on its intensity, which degrades image quality by failing to consider the local nature of the heat. We propose Fieldscale, a rescaling based on locality-aware 2D fields where both the intensity value and spatial context of each pixel within an image are embedded. It can adaptively determine the pixel gain for each region and produce spatially consistent 8-bit rescaled images with minimal information loss and high visibility. Consistent performance improvement on image quality assessment and two other downstream tasks support the effectiveness and usability of Fieldscale. All the codes are publicly opened to facilitate research advancements in this field. https://github.com/hyeonjaegil/fieldscale
Authors: Bar{\i}\c{s} B\"uy\"ukta\c{s}, Kenneth Weitzel, Sebastian V\"olkers, Felix Zailskas, Beg\"um Demir
Abstract: Federated learning (FL) aims to collaboratively learn deep learning model parameters from decentralized data archives (i.e., clients) without accessing training data on clients. However, the training data across clients might be not independent and identically distributed (non-IID), which may result in difficulty in achieving optimal model convergence. In this work, we investigate the capability of state-of-the-art transformer architectures (which are MLP-Mixer, ConvMixer, PoolFormer) to address the challenges related to non-IID training data across various clients in the context of FL for multi-label classification (MLC) problems in remote sensing (RS). The considered transformer architectures are compared among themselves and with the ResNet-50 architecture in terms of their: 1) robustness to training data heterogeneity; 2) local training complexity; and 3) aggregation complexity under different non-IID levels. The experimental results obtained on the BigEarthNet-S2 benchmark archive demonstrate that the considered architectures increase the generalization ability with the cost of higher local training and aggregation complexities. On the basis of our analysis, some guidelines are derived for a proper selection of transformer architecture in the context of FL for RS MLC. The code of this work is publicly available at https://git.tu-berlin.de/rsim/FL-Transformer.
Authors: Ajay John Alex, Chloe M. Barnes, Pedro Machado, Isibor Ihianle, G\'abor Mark\'o, Martin Bencsik, Jordan J. Bird
Abstract: In an era of rapid climate change and its adverse effects on food production, technological intervention to monitor pollinator conservation is of paramount importance for environmental monitoring and conservation for global food security. The survival of the human species depends on the conservation of pollinators. This article explores the use of Computer Vision and Object Recognition to autonomously track and report bee behaviour from images. A novel dataset of 9664 images containing bees is extracted from video streams and annotated with bounding boxes. With training, validation and testing sets (6722, 1915, and 997 images, respectively), the results of the COCO-based YOLO model fine-tuning approaches show that YOLOv5m is the most effective approach in terms of recognition accuracy. However, YOLOv5s was shown to be the most optimal for real-time bee detection with an average processing and inference time of 5.1ms per video frame at the cost of slightly lower ability. The trained model is then packaged within an explainable AI interface, which converts detection events into timestamped reports and charts, with the aim of facilitating use by non-technical users such as expert stakeholders from the apiculture industry towards informing responsible consumption and production.
Authors: \'Alvaro Becerra, Javier Irigoyen, Roberto Daza, Ruth Cobos, Aythami Morales, Julian Fierrez, Mutlu Cukurova
Abstract: In this article, we explore computer vision approaches to detect abnormal head pose during e-learning sessions and we introduce a study on the effects of mobile phone usage during these sessions. We utilize behavioral data collected from 120 learners monitored while participating in a MOOC learning sessions. Our study focuses on the influence of phone-usage events on behavior and physiological responses, specifically attention, heart rate, and meditation, before, during, and after phone usage. Additionally, we propose an approach for estimating head pose events using images taken by the webcam during the MOOC learning sessions to detect phone-usage events. Our hypothesis suggests that head posture undergoes significant changes when learners interact with a mobile phone, contrasting with the typical behavior seen when learners face a computer during e-learning sessions. We propose an approach designed to detect deviations in head posture from the average observed during a learner's session, operating as a semi-supervised method. This system flags events indicating alterations in head posture for subsequent human review and selection of mobile phone usage occurrences with a sensitivity over 90%.
Authors: Wenquan Dong, Edward T. A. Mitchard, Yuwei Chen, Man Chen, Congfeng Cao, Peilun Hu, Cong Xu, Steven Hancock
Abstract: Large-scale high spatial resolution aboveground biomass (AGB) maps play a crucial role in determining forest carbon stocks and how they are changing, which is instrumental in understanding the global carbon cycle, and implementing policy to mitigate climate change. The advent of the new space-borne LiDAR sensor, NASA's GEDI instrument, provides unparalleled possibilities for the accurate and unbiased estimation of forest AGB at high resolution, particularly in dense and tall forests, where Synthetic Aperture Radar (SAR) and passive optical data exhibit saturation. However, GEDI is a sampling instrument, collecting dispersed footprints, and its data must be combined with that from other continuous cover satellites to create high-resolution maps, using local machine learning methods. In this study, we developed local models to estimate forest AGB from GEDI L2A data, as the models used to create GEDI L4 AGB data incorporated minimal field data from China. We then applied LightGBM and random forest regression to generate wall-to-wall AGB maps at 25 m resolution, using extensive GEDI footprints as well as Sentinel-1 data, ALOS-2 PALSAR-2 and Sentinel-2 optical data. Through a 5-fold cross-validation, LightGBM demonstrated a slightly better performance than Random Forest across two contrasting regions. However, in both regions, the computation speed of LightGBM is substantially faster than that of the random forest model, requiring roughly one-third of the time to compute on the same hardware. Through the validation against field data, the 25 m resolution AGB maps generated using the local models developed in this study exhibited higher accuracy compared to the GEDI L4B AGB data. We found in both regions an increase in error as slope increased. The trained models were tested on nearby but different regions and exhibited good performance.
Authors: Zichen Geng, Caren Han, Zeeshan Hayder, Jian Liu, Mubarak Shah, Ajmal Mian
Abstract: Text-driven human motion generation is an emerging task in animation and humanoid robot design. Existing algorithms directly generate the full sequence which is computationally expensive and prone to errors as it does not pay special attention to key poses, a process that has been the cornerstone of animation for decades. We propose KeyMotion, that generates plausible human motion sequences corresponding to input text by first generating keyframes followed by in-filling. We use a Variational Autoencoder (VAE) with Kullback-Leibler regularization to project the keyframes into a latent space to reduce dimensionality and further accelerate the subsequent diffusion process. For the reverse diffusion, we propose a novel Parallel Skip Transformer that performs cross-modal attention between the keyframe latents and text condition. To complete the motion sequence, we propose a text-guided Transformer designed to perform motion-in-filling, ensuring the preservation of both fidelity and adherence to the physical constraints of human motion. Experiments show that our method achieves state-of-theart results on the HumanML3D dataset outperforming others on all R-precision metrics and MultiModal Distance. KeyMotion also achieves competitive performance on the KIT dataset, achieving the best results on Top3 R-precision, FID, and Diversity metrics.
Authors: Yiming Wu, Hangfei Li, Fangfang Wang, Yilong Zhang, Ronghua Liang
Abstract: In the domain of language-based fashion image retrieval, pinpointing the desired fashion item using both a reference image and its accompanying textual description is an intriguing challenge. Existing approaches lean heavily on static fusion techniques, intertwining image and text. Despite their commendable advancements, these approaches are still limited by a deficiency in flexibility. In response, we propose a Self-distilled Dynamic Fusion Network to compose the multi-granularity features dynamically by considering the consistency of routing path and modality-specific information simultaneously. Two new modules are included in our proposed method: (1) Dynamic Fusion Network with Modality Specific Routers. The dynamic network enables a flexible determination of the routing for each reference image and modification text, taking into account their distinct semantics and distributions. (2) Self Path Distillation Loss. A stable path decision for queries benefits the optimization of feature extraction as well as routing, and we approach this by progressively refine the path decision with previous path information. Extensive experiments demonstrate the effectiveness of our proposed model compared to existing methods.
Authors: Zicheng Wang, Zhenghao Chen, Yiming Wu, Zhen Zhao, Luping Zhou, Dong Xu
Abstract: Point cloud analysis has seen substantial advancements due to deep learning, although previous Transformer-based methods excel at modeling long-range dependencies on this task, their computational demands are substantial. Conversely, the Mamba offers greater efficiency but shows limited potential compared with Transformer-based methods. In this study, we introduce PoinTramba, a pioneering hybrid framework that synergies the analytical power of Transformer with the remarkable computational efficiency of Mamba for enhanced point cloud analysis. Specifically, our approach first segments point clouds into groups, where the Transformer meticulously captures intricate intra-group dependencies and produces group embeddings, whose inter-group relationships will be simultaneously and adeptly captured by efficient Mamba architecture, ensuring comprehensive analysis. Unlike previous Mamba approaches, we introduce a bi-directional importance-aware ordering (BIO) strategy to tackle the challenges of random ordering effects. This innovative strategy intelligently reorders group embeddings based on their calculated importance scores, significantly enhancing Mamba's performance and optimizing the overall analytical process. Our framework achieves a superior balance between computational efficiency and analytical performance by seamlessly integrating these advanced techniques, marking a substantial leap forward in point cloud analysis. Extensive experiments on datasets such as ScanObjectNN, ModelNet40, and ShapeNetPart demonstrate the effectiveness of our approach, establishing a new state-of-the-art analysis benchmark on point cloud recognition. For the first time, this paradigm leverages the combined strengths of both Transformer and Mamba architectures, facilitating a new standard in the field. The code is available at https://github.com/xiaoyao3302/PoinTramba.
Authors: Fan Liu, Liang Yao, Chuanyi Zhang, Ting Wu, Xinlei Zhang, Jun Zhou, Xiruo Jiang
Abstract: Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage inferences. Despite their remarkable detecting accuracies, real-time efficiency is sacrificed, making them less practical to handle real applications. To this end, we propose to improve the single-stage inference accuracy through learning scale-invariant features. Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features. Then an Adversarial Feature Learning scheme is employed to enhance disentanglement. Finally, scale-invariant features are leveraged for robust UAV-based object detection. Furthermore, we construct a multi-modal UAV object detection dataset, State-Air, which incorporates annotated UAV state parameters. We apply our approach to three state-of-the-art lightweight detection frameworks on three benchmark datasets, including State-Air. Extensive experiments demonstrate that our approach can effectively improve model accuracy. Our code and dataset are provided in Supplementary Materials and will be publicly available once the paper is accepted.
Authors: Abhishek Goswami, Aru Ranjan Singh, Francesco Banterle, Kurt Debattista, Thomas Bashford-Rogers
Abstract: The range of real-world scene luminance is larger than the capture capability of many digital camera sensors which leads to details being lost in captured images, most typically in bright regions. Inverse tone mapping attempts to boost these captured Standard Dynamic Range (SDR) images back to High Dynamic Range (HDR) by creating a mapping that linearizes the well exposed values from the SDR image, and provides a luminance boost to the clipped content. However, in most cases, the details in the clipped regions cannot be recovered or estimated. In this paper, we present a novel inverse tone mapping approach for mapping SDR images to HDR that generates lost details in clipped regions through a semantic-aware diffusion based inpainting approach. Our method proposes two major contributions - first, we propose to use a semantic graph to guide SDR diffusion based inpainting in masked regions in a saturated image. Second, drawing inspiration from traditional HDR imaging and bracketing methods, we propose a principled formulation to lift the SDR inpainted regions to HDR that is compatible with generative inpainting methods. Results show that our method demonstrates superior performance across different datasets on objective metrics, and subjective experiments show that the proposed method matches (and in most cases outperforms) state-of-art inverse tone mapping operators in terms of objective metrics and outperforms them for visual fidelity.
Authors: Eduard Zamfir, Zongwei Wu, Nancy Mehta, Danda Dani Paudel, Yulun Zhang, Radu Timofte
Abstract: Reconstructing missing details from degraded low-quality inputs poses a significant challenge. Recent progress in image restoration has demonstrated the efficacy of learning large models capable of addressing various degradations simultaneously. Nonetheless, these approaches introduce considerable computational overhead and complex learning paradigms, limiting their practical utility. In response, we propose \textit{DaAIR}, an efficient All-in-One image restorer employing a Degradation-aware Learner (DaLe) in the low-rank regime to collaboratively mine shared aspects and subtle nuances across diverse degradations, generating a degradation-aware embedding. By dynamically allocating model capacity to input degradations, we realize an efficient restorer integrating holistic and specific learning within a unified model. Furthermore, DaAIR introduces a cost-efficient parameter update mechanism that enhances degradation awareness while maintaining computational efficiency. Extensive comparisons across five image degradations demonstrate that our DaAIR outperforms both state-of-the-art All-in-One models and degradation-specific counterparts, affirming our efficacy and practicality. The source will be publicly made available at \url{https://eduardzamfir.github.io/daair/}
Authors: Panagiotis Agrafiotis, {\L}ukasz Janowski, Dimitrios Skarlatos, Beg\"um Demir
Abstract: Accurate, detailed, and high-frequent bathymetry, coupled with complex semantic content, is crucial for the undermapped shallow seabed areas facing intense climatological and anthropogenic pressures. Current methods exploiting remote sensing images to derive bathymetry or seabed classes mainly exploit non-open data. This lack of openly accessible benchmark archives prevents the wider use of deep learning methods in such applications. To address this issue, in this paper we present the MagicBathyNet, which is a benchmark dataset made up of image patches of Sentinel2, SPOT-6 and aerial imagery, bathymetry in raster format and annotations of seabed classes. MagicBathyNet is then exploited to benchmark state-of-the-art methods in learning-based bathymetry and pixel-based classification. Dataset, pre-trained weights, and code are publicly available at www.magicbathy.eu/magicbathynet.html.
Authors: Jiajun Huang, Hongchuan Yu
Abstract: We present GSDeformer, a method that achieves free-form deformation on 3D Gaussian Splatting(3DGS) without requiring any architectural changes. Our method extends cage-based deformation, a traditional mesh deformation method, to 3DGS. This is done by converting 3DGS into a novel proxy point cloud representation, where its deformation can be used to infer the transformations to apply on the 3D gaussians making up 3DGS. We also propose an automatic cage construction algorithm for 3DGS to minimize manual work. Our method does not modify the underlying architecture of 3DGS. Therefore, any existing trained vanilla 3DGS can be easily edited by our method. We compare the deformation capability of our method against other existing methods, demonstrating the ease of use and comparable quality of our method, despite being more direct and thus easier to integrate with other concurrent developments on 3DGS.
Authors: T. Berriel Martins, Javier Civera
Abstract: 3D Gaussian Splatting has emerged as a very promising scene representation, achieving state-of-the-art quality in novel view synthesis significantly faster than competing alternatives. However, its use of spherical harmonics to represent scene colors limits the expressivity of 3D Gaussians and, as a consequence, the capability of the representation to generalize as we move away from the training views. In this paper, we propose to encode the color information of 3D Gaussians into per-Gaussian feature vectors, which we denote as Feature Splatting (FeatSplat). To synthesize a novel view, Gaussians are first "splatted" into the image plane, then the corresponding feature vectors are alpha-blended, and finally the blended vector is decoded by a small MLP to render the RGB pixel values. To further inform the model, we concatenate a camera embedding to the blended feature vector, to condition the decoding also on the viewpoint information. Our experiments show that these novel model for encoding the radiance considerably improves novel view synthesis for low overlap views that are distant from the training views. Finally, we also show the capacity and convenience of our feature vector representation, demonstrating its capability not only to generate RGB values for novel views, but also their per-pixel semantic labels. We will release the code upon acceptance. Keywords: Gaussian Splatting, Novel View Synthesis, Feature Splatting
Authors: Edward Sanderson, Bogdan J. Matuszewski
Abstract: It has recently been demonstrated that pretraining backbones in a self-supervised manner generally provides better fine-tuned polyp segmentation performance, and that models with ViT-B backbones typically perform better than models with ResNet50 backbones. In this paper, we extend this recent work to consider generalisability. I.e., we assess the performance of models on a different dataset to that used for fine-tuning, accounting for variation in network architecture and pretraining pipeline (algorithm and dataset). This reveals how well models with different pretrained backbones generalise to data of a somewhat different distribution to the training data, which will likely arise in deployment due to different cameras and demographics of patients, amongst other factors. We observe that the previous findings, regarding pretraining pipelines for polyp segmentation, hold true when considering generalisability. However, our results imply that models with ResNet50 backbones typically generalise better, despite being outperformed by models with ViT-B backbones in evaluation on the test set from the same dataset used for fine-tuning.
Authors: Yunyao Mao, Xiaoyang Liu, Wengang Zhou, Zhenbo Lu, Houqiang Li
Abstract: Text-driven human motion generation, as one of the vital tasks in computer-aided content creation, has recently attracted increasing attention. While pioneering research has largely focused on improving numerical performance metrics on given datasets, practical applications reveal a common challenge: existing methods often overfit specific motion expressions in the training data, hindering their ability to generalize to novel descriptions like unseen combinations of motions. This limitation restricts their broader applicability. We argue that the aforementioned problem primarily arises from the scarcity of available motion-text pairs, given the many-to-many nature of text-driven motion generation. To tackle this problem, we formulate text-to-motion generation as a Markov decision process and present \textbf{InstructMotion}, which incorporate the trail and error paradigm in reinforcement learning for generalizable human motion generation. Leveraging contrastive pre-trained text and motion encoders, we delve into optimizing reward design to enable InstructMotion to operate effectively on both paired data, enhancing global semantic level text-motion alignment, and synthetic text-only data, facilitating better generalization to novel prompts without the need for ground-truth motion supervision. Extensive experiments on prevalent benchmarks and also our synthesized unpaired dataset demonstrate that the proposed InstructMotion achieves outstanding performance both quantitatively and qualitatively.
Authors: Hantao Yao, Rui Zhang, Lu Yu, Changsheng Xu
Abstract: Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as they are independent of the pre-trained tokens and fail to capture input-specific knowledge, such as class-aware textual or instance-aware visual knowledge. Leveraging the discriminative and generalization capabilities inherent in pre-trained tokens, we introduce a novel approach named Self-Enhanced Prompt Tuning (SEP). The core principle of SEP involves adapting the learnable prompt tokens at each encoder layer from the corresponding self-pretrained tokens, thereby explicitly incorporating discriminative prior knowledge to enhance both textual-level and visual-level embeddings. Furthermore, SEP's self-enhanced tokens not only boost discrimination but also mitigate domain shifts in unseen domains, enhancing generalization. In practice, SEP selects several representative tokens from all pre-trained tokens for each input data at every layer of the text/visual encoders. Subsequently, a Token Fusion Module (TFM) is introduced to generate a self-enhanced token by merging these representative tokens with the learnable tokens using a cross-attention mechanism. This self-enhanced token is then concatenated with all pre-trained tokens, serving as input for subsequent encoder layers to produce the relevant embeddings. Comprehensive evaluations across various benchmarks and tasks confirm SEP's efficacy in prompt tuning. Code: \href{Code}{https://github.com/htyao89/SEP}.
Authors: Shahid Ismail, Moises Diaz, Cristina Carmona-Duarte, Jose Manuel Vilar, Miguel A. Ferrer
Abstract: Lameness is one of the costliest pathological problems affecting dairy animals. It is usually assessed by trained veterinary clinicians who observe features such as gait symmetry or gait parameters as step counts in real-time. With the development of artificial intelligence, various modular systems have been proposed to minimize subjectivity in lameness assessment. However, the major limitation in their development is the unavailability of a public dataset which is currently either commercial or privately held. To tackle this limitation, we have introduced CowScreeningDB which was created using sensory data. This dataset was sourced from 43 cows at a dairy located in Gran Canaria, Spain. It consists of a multi-sensor dataset built on data collected using an Apple Watch 6 during the normal daily routine of a dairy cow. Thanks to the collection environment, sampling technique, information regarding the sensors, the applications used for data conversion and storage make the dataset a transparent one. This transparency of data can thus be used for further development of techniques for lameness detection for dairy cows which can be objectively compared. Aside from the public sharing of the dataset, we have also shared a machine-learning technique which classifies the caws in healthy and lame by using the raw sensory data. Hence validating the major objective which is to establish the relationship between sensor data and lameness.
Authors: Niloy Sikder, Md. Al-Masrur Khan, Anupam Kumar Bairagi, Mehedi Masud, Jun Jiat Tiang, Abdullah-Al Nahid
Abstract: Viruses are submicroscopic agents that can infect all kinds of lifeforms and use their hosts' living cells to replicate themselves. Despite having some of the simplest genetic structures among all living beings, viruses are highly adaptable, resilient, and given the right conditions, are capable of causing unforeseen complications in their hosts' bodies. Due to their multiple transmission pathways, high contagion rate, and lethality, viruses are the biggest biological threat faced by animal and plant species. It is often challenging to promptly detect the presence of a virus in a possible host's body and accurately determine its type using manual examination techniques; however, it can be done using computer-based automatic diagnosis methods. Most notably, the analysis of Transmission Electron Microscopy (TEM) images has been proven to be quite successful in instant virus identification. Using TEM images collected from a recently published dataset, this article proposes a deep learning-based classification model to identify the type of virus within those images correctly. The methodology of this study includes two coherent image processing techniques to reduce the noise present in the raw microscopy images. Experimental results show that it can differentiate among the 14 types of viruses present in the dataset with a maximum of 97.44% classification accuracy and F1-score, which asserts the effectiveness and reliability of the proposed method. Implementing this scheme will impart a fast and dependable way of virus identification subsidiary to the thorough diagnostic procedures.
Authors: Janan Arslan, Henri Chhoa, Ines Khemir, Romain Valabregue, Kurt K. Benke
Abstract: Summary: Medical researchers obtain knowledge about the prevention and treatment of disability and disease using physical measurements and image data. To assist in this endeavor, feature extraction packages are available that are designed to collect data from the image structure. In this study, we aim to augment current works by adding to the current mix of shape-based features. The significance of shape-based features has been explored extensively in research for several decades, but there is no single package available in which all shape-related features can be extracted easily by the researcher. PyCellMech has been crafted to address this gap. The PyCellMech package extracts three classes of shape features, which are classified as one-dimensional, geometric, and polygonal. Future iterations will be expanded to include other feature classes, such as scale-space. Availability and implementation: PyCellMech is freely available at https://github.com/icm-dac/pycellmech.
Authors: Byung-Kwan Lee, Chae Won Kim, Beomchan Park, Yong Man Ro
Abstract: The rapid development of large language and vision models (LLVMs) has been driven by advances in visual instruction tuning. Recently, open-source LLVMs have curated high-quality visual instruction tuning datasets and utilized additional vision encoders or multiple computer vision models in order to narrow the performance gap with powerful closed-source LLVMs. These advancements are attributed to multifaceted information required for diverse capabilities, including fundamental image understanding, real-world knowledge about common-sense and non-object concepts (e.g., charts, diagrams, symbols, signs, and math problems), and step-by-step procedures for solving complex questions. Drawing from the multifaceted information, we present a new efficient LLVM, Mamba-based traversal of rationales (Meteor), which leverages multifaceted rationale to enhance understanding and answering capabilities. To embed lengthy rationales containing abundant information, we employ the Mamba architecture, capable of processing sequential data with linear time complexity. We introduce a new concept of traversal of rationale that facilitates efficient embedding of rationale. Subsequently, the backbone multimodal language model (MLM) is trained to generate answers with the aid of rationale. Through these steps, Meteor achieves significant improvements in vision language performances across multiple evaluation benchmarks requiring diverse capabilities, without scaling up the model size or employing additional vision encoders and computer vision models.
Authors: Hanchen Tai, Qingdong He, Jiangning Zhang, Yijie Qian, Zhenyu Zhang, Xiaobin Hu, Yabiao Wang, Yong Liu
Abstract: Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent advancements have sought to transfer knowledge embedded in vision language models from the 2D domain to 3D domain. However, these approaches often require learning prior knowledge from specific 3D scene datasets, which limits their applicability in open-world scenarios. The Segment Anything Model (SAM) has demonstrated remarkable zero-shot segmentation capabilities, prompting us to investigate its potential for comprehending 3D scenes without the need for training. In this paper, we introduce OV-SAM3D, a universal framework for open-vocabulary 3D scene understanding. This framework is designed to perform understanding tasks for any 3D scene without requiring prior knowledge of the scene. Specifically, our method is composed of two key sub-modules: First, we initiate the process by generating superpoints as the initial 3D prompts and refine these prompts using segment masks derived from SAM. Moreover, we then integrate a specially designed overlapping score table with open tags from the Recognize Anything Model (RAM) to produce final 3D instances with open-world label. Empirical evaluations conducted on the ScanNet200 and nuScenes datasets demonstrate that our approach surpasses existing open-vocabulary methods in unknown open-world environments.
Authors: Bill Psomas, Ioannis Kakogeorgiou, Nikos Efthymiadis, Giorgos Tolias, Ondrej Chum, Yannis Avrithis, Konstantinos Karantzalos
Abstract: This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descriptive power over unimodal queries, either visual or textual. Various attributes can be modified by the textual part, such as shape, color, or context. A novel method fusing image-to-image and text-to-image similarity is introduced. We demonstrate that a vision-language model possesses sufficient descriptive power and no further learning step or training data are necessary. We present a new evaluation benchmark focused on color, context, density, existence, quantity, and shape modifications. Our work not only sets the state-of-the-art for this task, but also serves as a foundational step in addressing a gap in the field of remote sensing image retrieval. Code at: https://github.com/billpsomas/rscir
Authors: Hafsa El Hafyani, Bastien Pasdeloup, Camille Yver, Pierre Romenteau
Abstract: Multimodal object detection has shown promise in remote sensing. However, multimodal data frequently encounter the problem of low-quality, wherein the modalities lack strict cell-to-cell alignment, leading to mismatch between different modalities. In this paper, we investigate multimodal object detection where only one modality contains the target object and the others provide crucial contextual information. We propose to resolve the alignment problem by converting the contextual binary information into probability maps. We then propose an early fusion architecture that we validate with extensive experiments on the DOTA dataset.
Authors: Xiankang He, Guangkai Xu, Bo Zhang, Hao Chen, Ying Cui, Dongyan Guo
Abstract: Monocular camera calibration is a key precondition for numerous 3D vision applications. Despite considerable advancements, existing methods often hinge on specific assumptions and struggle to generalize across varied real-world scenarios, and the performance is limited by insufficient training data. Recently, diffusion models trained on expansive datasets have been confirmed to maintain the capability to generate diverse, high-quality images. This success suggests a strong potential of the models to effectively understand varied visual information. In this work, we leverage the comprehensive visual knowledge embedded in pre-trained diffusion models to enable more robust and accurate monocular camera intrinsic estimation. Specifically, we reformulate the problem of estimating the four degrees of freedom (4-DoF) of camera intrinsic parameters as a dense incident map generation task. The map details the angle of incidence for each pixel in the RGB image, and its format aligns well with the paradigm of diffusion models. The camera intrinsic then can be derived from the incident map with a simple non-learning RANSAC algorithm during inference. Moreover, to further enhance the performance, we jointly estimate a depth map to provide extra geometric information for the incident map estimation. Extensive experiments on multiple testing datasets demonstrate that our model achieves state-of-the-art performance, gaining up to a 40% reduction in prediction errors. Besides, the experiments also show that the precise camera intrinsic and depth maps estimated by our pipeline can greatly benefit practical applications such as 3D reconstruction from a single in-the-wild image.
Authors: Ruikai Cui, Xibin Song, Weixuan Sun, Senbo Wang, Weizhe Liu, Shenzhou Chen, Taizhang Shang, Yang Li, Nick Barnes, Hongdong Li, Pan Ji
Abstract: Large Reconstruction Models have made significant strides in the realm of automated 3D content generation from single or multiple input images. Despite their success, these models often produce 3D meshes with geometric inaccuracies, stemming from the inherent challenges of deducing 3D shapes solely from image data. In this work, we introduce a novel framework, the Large Image and Point Cloud Alignment Model (LAM3D), which utilizes 3D point cloud data to enhance the fidelity of generated 3D meshes. Our methodology begins with the development of a point-cloud-based network that effectively generates precise and meaningful latent tri-planes, laying the groundwork for accurate 3D mesh reconstruction. Building upon this, our Image-Point-Cloud Feature Alignment technique processes a single input image, aligning to the latent tri-planes to imbue image features with robust 3D information. This process not only enriches the image features but also facilitates the production of high-fidelity 3D meshes without the need for multi-view input, significantly reducing geometric distortions. Our approach achieves state-of-the-art high-fidelity 3D mesh reconstruction from a single image in just 6 seconds, and experiments on various datasets demonstrate its effectiveness.
Authors: Thomas De Min, Massimiliano Mancini, St\'ephane Lathuili\`ere, Subhankar Roy, Elisa Ricci
Abstract: Prompt tuning has emerged as an effective rehearsal-free technique for class-incremental learning (CIL) that learns a tiny set of task-specific parameters (or prompts) to instruct a pre-trained transformer to learn on a sequence of tasks. Albeit effective, prompt tuning methods do not lend well in the multi-label class incremental learning (MLCIL) scenario (where an image contains multiple foreground classes) due to the ambiguity in selecting the correct prompt(s) corresponding to different foreground objects belonging to multiple tasks. To circumvent this issue we propose to eliminate the prompt selection mechanism by maintaining task-specific pathways, which allow us to learn representations that do not interact with the ones from the other tasks. Since independent pathways in truly incremental scenarios will result in an explosion of computation due to the quadratically complex multi-head self-attention (MSA) operation in prompt tuning, we propose to reduce the original patch token embeddings into summarized tokens. Prompt tuning is then applied to these fewer summarized tokens to compute the final representation. Our proposed method Multi-Label class incremental learning via summarising pAtch tokeN Embeddings (MULTI-LANE) enables learning disentangled task-specific representations in MLCIL while ensuring fast inference. We conduct experiments in common benchmarks and demonstrate that our MULTI-LANE achieves a new state-of-the-art in MLCIL. Additionally, we show that MULTI-LANE is also competitive in the CIL setting. Source code available at https://github.com/tdemin16/multi-lane
Authors: Rudolf Herdt, Peter Maass
Abstract: We investigate how generated structures of GANs correlate with their activations in hidden layers, with the purpose of better understanding the inner workings of those models and being able to paint structures with unconditionally trained GANs. This gives us more control over the generated images, allowing to generate them from a semantic segmentation map while not requiring such a segmentation in the training data. To this end we introduce the concept of tileable features, allowing us to identify activations that work well for painting.
Authors: Hongyu Wang, Jiayu Xu, Senwei Xie, Ruiping Wang, Jialin Li, Zhaojie Xie, Bin Zhang, Chuyan Xiong, Xilin Chen
Abstract: Multilingual multimodal reasoning is a core component in achieving human-level intelligence. However, most existing benchmarks for multilingual multimodal reasoning struggle to differentiate between models of varying performance; even language models without visual capabilities can easily achieve high scores. This leaves a comprehensive evaluation of leading multilingual multimodal models largely unexplored. In this work, we introduce M4U, a novel and challenging benchmark for assessing the capability of multi-discipline multilingual multimodal understanding and reasoning. M4U contains 8,931 samples covering 64 disciplines across 16 subfields in Science, Engineering, and Healthcare in Chinese, English, and German. Using M4U, we conduct extensive evaluations of 21 leading Large Multimodal Models (LMMs) and Large Language Models (LLMs) with external tools. The evaluation results show that the state-of-the-art model, GPT-4o, achieves only 47.6% average accuracy on M4U. Additionally, we observe that the leading LMMs exhibit significant language preferences. Our in-depth analysis indicates that leading LMMs, including GPT-4o, suffer performance degradation when prompted with cross-lingual multimodal questions, such as images with key textual information in Chinese while the question is in German. We believe that M4U can serve as a crucial tool for systematically evaluating LMMs based on their multilingual multimodal reasoning capabilities and monitoring their development. The homepage, codes and data are public available.
Authors: Zhuoyan Luo, Yinghao Wu, Yong Liu, Yicheng Xiao, Xiao-Ping Zhang, Yujiu Yang
Abstract: The newly proposed Generalized Referring Expression Segmentation (GRES) amplifies the formulation of classic RES by involving multiple/non-target scenarios. Recent approaches focus on optimizing the last modality-fused feature which is directly utilized for segmentation and object-existence identification. However, the attempt to integrate all-grained information into a single joint representation is impractical in GRES due to the increased complexity of the spatial relationships among instances and deceptive text descriptions. Furthermore, the subsequent binary target justification across all referent scenarios fails to specify their inherent differences, leading to ambiguity in object understanding. To address the weakness, we propose a $\textbf{H}$ierarchical Semantic $\textbf{D}$ecoding with $\textbf{C}$ounting Assistance framework (HDC). It hierarchically transfers complementary modality information across granularities, and then aggregates each well-aligned semantic correspondence for multi-level decoding. Moreover, with complete semantic context modeling, we endow HDC with explicit counting capability to facilitate comprehensive object perception in multiple/single/non-target settings. Experimental results on gRefCOCO, Ref-ZOM, R-RefCOCO, and RefCOCO benchmarks demonstrate the effectiveness and rationality of HDC which outperforms the state-of-the-art GRES methods by a remarkable margin. Code will be available $\href{https://github.com/RobertLuo1/HDC}{here}$.
Authors: Xiaogang Xu, Kun Zhou, Tao Hu, Ruixing Wang, Hujun Bao
Abstract: Low-Light Video Enhancement (LLVE) seeks to restore dynamic and static scenes plagued by severe invisibility and noise. One critical aspect is formulating a consistency constraint specifically for temporal-spatial illumination and appearance enhanced versions, a dimension overlooked in existing methods. In this paper, we present an innovative video Retinex-based decomposition strategy that operates without the need for explicit supervision to delineate illumination and reflectance components. We leverage dynamic cross-frame correspondences for intrinsic appearance and enforce a scene-level continuity constraint on the illumination field to yield satisfactory consistent decomposition results. To further ensure consistent decomposition, we introduce a dual-structure enhancement network featuring a novel cross-frame interaction mechanism. This mechanism can seamlessly integrate with encoder-decoder single-frame networks, incurring minimal additional parameter costs. By supervising different frames simultaneously, this network encourages them to exhibit matching decomposition features, thus achieving the desired temporal propagation. Extensive experiments are conducted on widely recognized LLVE benchmarks, covering diverse scenarios. Our framework consistently outperforms existing methods, establishing a new state-of-the-art (SOTA) performance.
Authors: James Hinns, David Martens
Abstract: The rise of deep learning in image classification has brought unprecedented accuracy but also highlighted a key issue: the use of 'shortcuts' by models. Such shortcuts are easy-to-learn patterns from the training data that fail to generalise to new data. Examples include the use of a copyright watermark to recognise horses, snowy background to recognise huskies, or ink markings to detect malignant skin lesions. The explainable AI (XAI) community has suggested using instance-level explanations to detect shortcuts without external data, but this requires the examination of many explanations to confirm the presence of such shortcuts, making it a labour-intensive process. To address these challenges, we introduce Counterfactual Frequency (CoF) tables, a novel approach that aggregates instance-based explanations into global insights, and exposes shortcuts. The aggregation implies the need for some semantic concepts to be used in the explanations, which we solve by labelling the segments of an image. We demonstrate the utility of CoF tables across several datasets, revealing the shortcuts learned from them.
Authors: Abdelrahman Abdelhamed, Mahmoud Afifi, Alec Go
Abstract: Large language models (LLMs) has been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs. By employing multimodal LLMs, we generate comprehensive textual representations from input images. These textual representations are then utilized to generate fixed-dimensional features in a cross-modal embedding space. Subsequently, these features are fused together to perform zero-shot classification using a linear classifier. Our method does not require prompt engineering for each dataset; instead, we use a single, straightforward, set of prompts across all datasets. We evaluated our method on several datasets, and our results demonstrate its remarkable effectiveness, surpassing benchmark accuracy on multiple datasets. On average over ten benchmarks, our method achieved an accuracy gain of 4.1 percentage points, with an increase of 6.8 percentage points on the ImageNet dataset, compared to prior methods. Our findings highlight the potential of multimodal LLMs to enhance computer vision tasks such as zero-shot image classification, offering a significant improvement over traditional methods.
Authors: Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, Dinesh Manocha
Abstract: Recent interest in Large Vision-Language Models (LVLMs) for practical applications is moderated by the significant challenge of hallucination or the inconsistency between the factual information and the generated text. In this paper, we first perform an in-depth analysis of hallucinations and discover several novel insights about how and when LVLMs hallucinate. From our analysis, we show that: (1) The community's efforts have been primarily targeted towards reducing hallucinations related to visual recognition (VR) prompts (e.g., prompts that only require describing the image), thereby ignoring hallucinations for cognitive prompts (e.g., prompts that require additional skills like reasoning on contents of the image). (2) LVLMs lack visual perception, i.e., they can see but not necessarily understand or perceive the input image. We analyze responses to cognitive prompts and show that LVLMs hallucinate due to a perception gap: although LVLMs accurately recognize visual elements in the input image and possess sufficient cognitive skills, they struggle to respond accurately and hallucinate. To overcome this shortcoming, we propose Visual Description Grounded Decoding (VDGD), a simple, robust, and training-free method for alleviating hallucinations. Specifically, we first describe the image and add it as a prefix to the instruction. Next, during auto-regressive decoding, we sample from the plausible candidates according to their KL-Divergence (KLD) to the description, where lower KLD is given higher preference. Experimental results on several benchmarks and LVLMs show that VDGD improves significantly over other baselines in reducing hallucinations. We also propose VaLLu, a benchmark for the comprehensive evaluation of the cognitive capabilities of LVLMs.
Authors: Yue Zhang, Hehe Fan, Yi Yang
Abstract: To bridge the gap between vision and language modalities, Multimodal Large Language Models (MLLMs) usually learn an adapter that converts visual inputs to understandable tokens for Large Language Models (LLMs). However, most adapters generate consistent visual tokens, regardless of the specific objects of interest mentioned in the prompt. Since these adapters distribute equal attention to every detail in the image and focus on the entire scene, they may increase the cognitive load for LLMs, particularly when processing complex scenes. To alleviate this problem, we propose prompt-aware adapters. These adapters are designed with the capability to dynamically embed visual inputs based on the specific focus of the prompt. Specifically, prompt-aware adapters utilize both global and local textual features to capture the most relevant visual clues from the prompt at both coarse and fine granularity levels. This approach significantly enhances the ability of LLMs to understand and interpret visual content. Experiments on various visual question answering tasks, such as counting and position reasoning, demonstrate the effectiveness of prompt-aware adapters.
Authors: Yongsheng Yu, Jiebo Luo
Abstract: Conventional demographic inference methods have predominantly operated under the supervision of accurately labeled data, yet struggle to adapt to shifting social landscapes and diverse cultural contexts, leading to narrow specialization and limited accuracy in applications. Recently, the emergence of large multimodal models (LMMs) has shown transformative potential across various research tasks, such as visual comprehension and description. In this study, we explore the application of LMMs to demographic inference and introduce a benchmark for both quantitative and qualitative evaluation. Our findings indicate that LMMs possess advantages in zero-shot learning, interpretability, and handling uncurated 'in-the-wild' inputs, albeit with a propensity for off-target predictions. To enhance LMM performance and achieve comparability with supervised learning baselines, we propose a Chain-of-Thought augmented prompting approach, which effectively mitigates the off-target prediction issue.
Authors: Ted Lentsch, Holger Caesar, Dariu M. Gavrila
Abstract: Unsupervised 3D object detection methods have emerged to leverage vast amounts of data efficiently without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect objects but penalize the detections of static instances during training. Multiple rounds of (self) training are used in which detected static instances are added to the set of training targets; this procedure to improve performance is computationally expensive. To address this, we propose the method UNION. We use spatial clustering and self-supervised scene flow to obtain a set of static and dynamic object proposals from LiDAR. Subsequently, object proposals' visual appearances are encoded to distinguish static objects in the foreground and background by selecting static instances that are visually similar to dynamic objects. As a result, static and dynamic foreground objects are obtained together, and existing detectors can be trained with a single training. In addition, we extend 3D object discovery to detection by using object appearance-based cluster labels as pseudo-class labels for training object classification. We conduct extensive experiments on the nuScenes dataset and increase the state-of-the-art performance for unsupervised object discovery, i.e. UNION more than doubles the average precision to 33.9. The code will be made publicly available.
Authors: Benjamin Gallusser, Martin Weigert
Abstract: Cell tracking is an omnipresent image analysis task in live-cell microscopy. It is similar to multiple object tracking (MOT), however, each frame contains hundreds of similar-looking objects that can divide, making it a challenging problem. Current state-of-the-art approaches follow the tracking-by-detection paradigm, i.e. first all cells are detected per frame and successively linked in a second step to form biologically consistent cell tracks. Linking is commonly solved via discrete optimization methods, which require manual tuning of hyperparameters for each dataset and are therefore cumbersome to use in practice. Here we propose Trackastra, a general purpose cell tracking approach that uses a simple transformer architecture to directly learn pairwise associations of cells within a temporal window from annotated data. Importantly, unlike existing transformer-based MOT pipelines, our learning architecture also accounts for dividing objects such as cells and allows for accurate tracking even with simple greedy linking, thus making strides towards removing the requirement for a complex linking step. The proposed architecture operates on the full spatio-temporal context of detections within a time window by avoiding the computational burden of processing dense images. We show that our tracking approach performs on par with or better than highly tuned state-of-the-art cell tracking algorithms for various biological datasets, such as bacteria, cell cultures and fluorescent particles. We provide code at https://github.com/weigertlab/trackastra.
Authors: Elias Nehme, Rotem Mulayoff, Tomer Michaeli
Abstract: When solving ill-posed inverse problems, one often desires to explore the space of potential solutions rather than be presented with a single plausible reconstruction. Valuable insights into these feasible solutions and their associated probabilities are embedded in the posterior distribution. However, when confronted with data of high dimensionality (such as images), visualizing this distribution becomes a formidable challenge, necessitating the application of effective summarization techniques before user examination. In this work, we introduce a new approach for visualizing posteriors across multiple levels of granularity using tree-valued predictions. Our method predicts a tree-valued hierarchical summarization of the posterior distribution for any input measurement, in a single forward pass of a neural network. We showcase the efficacy of our approach across diverse datasets and image restoration challenges, highlighting its prowess in uncertainty quantification and visualization. Our findings reveal that our method performs comparably to a baseline that hierarchically clusters samples from a diffusion-based posterior sampler, yet achieves this with orders of magnitude greater speed.
Authors: Jiajin Zhang, Ge Wang, Mannudeep K. Kalra, Pingkun Yan
Abstract: In medical image analysis, the expertise scarcity and the high cost of data annotation limits the development of large artificial intelligence models. This paper investigates the potential of transfer learning with pre-trained vision-language models (VLMs) in this domain. Currently, VLMs still struggle to transfer to the underrepresented diseases with minimal presence and new diseases entirely absent from the pretraining dataset. We argue that effective adaptation of VLMs hinges on the nuanced representation learning of disease concepts. By capitalizing on the joint visual-linguistic capabilities of VLMs, we introduce disease-informed contextual prompting in a novel disease prototype learning framework. This approach enables VLMs to grasp the concepts of new disease effectively and efficiently, even with limited data. Extensive experiments across multiple image modalities showcase notable enhancements in performance compared to existing techniques.
Authors: Boyang Zheng, Jinjin Gu, Shijun Li, Chao Dong
Abstract: The success of large language models (LLMs) has fostered a new research trend of multi-modality large language models (MLLMs), which changes the paradigm of various fields in computer vision. Though MLLMs have shown promising results in numerous high-level vision and vision-language tasks such as VQA and text-to-image, no works have demonstrated how low-level vision tasks can benefit from MLLMs. We find that most current MLLMs are blind to low-level features due to their design of vision modules, thus are inherently incapable for solving low-level vision tasks. In this work, we purpose $\textbf{LM4LV}$, a framework that enables a FROZEN LLM to solve a range of low-level vision tasks without any multi-modal data or prior. This showcases the LLM's strong potential in low-level vision and bridges the gap between MLLMs and low-level vision tasks. We hope this work can inspire new perspectives on LLMs and deeper understanding of their mechanisms.
Authors: Chunjiang Ge, Sijie Cheng, Ziming Wang, Jiale Yuan, Yuan Gao, Jun Song, Shiji Song, Gao Huang, Bo Zheng
Abstract: High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual tokens. However, the redundancy in visual tokens is the key problem as it leads to more substantial compute. To mitigate this issue, we propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM to replace Vision Transformer (ViT). ConvLLaVA compresses high-resolution images into information-rich visual features, effectively preventing the generation of excessive visual tokens. To enhance the capabilities of ConvLLaVA, we propose two critical optimizations. Since the low-resolution pretrained ConvNeXt underperforms when directly applied on high resolution, we update it to bridge the gap. Moreover, since ConvNeXt's original compression ratio is inadequate for much higher resolution inputs, we train a successive stage to further compress the visual tokens, thereby reducing redundancy. These optimizations enable ConvLLaVA to support inputs of 1536x1536 resolution generating only 576 visual tokens, capable of handling images of arbitrary aspect ratios. Experimental results demonstrate that our method achieves competitive performance with state-of-the-art models on mainstream benchmarks. The ConvLLaVA model series are publicly available at https://github.com/alibaba/conv-llava.
Authors: Xudong Han, Nobuyuki Oishi, Yueying Tian, Elif Ucurum, Rupert Young, Chris Chatwin, Philip Birch
Abstract: Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based algorithms, such as the Kalman Filter, often work well in linear motion scenarios but struggle to accurately predict the locations of objects undergoing complex and non-linear movements. To tackle these scenarios, we propose a motion-based MOT approach with an enhanced temporal motion predictor, ETTrack. Specifically, the motion predictor integrates a transformer model and a Temporal Convolutional Network (TCN) to capture short-term and long-term motion patterns, and it predicts the future motion of individual objects based on the historical motion information. Additionally, we propose a novel Momentum Correction Loss function that provides additional information regarding the motion direction of objects during training. This allows the motion predictor rapidly adapt to motion variations and more accurately predict future motion. Our experimental results demonstrate that ETTrack achieves a competitive performance compared with state-of-the-art trackers on DanceTrack and SportsMOT, scoring 56.4% and 74.4% in HOTA metrics, respectively.
Authors: Feng Liang, Akio Kodaira, Chenfeng Xu, Masayoshi Tomizuka, Kurt Keutzer, Diana Marculescu
Abstract: This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to process limited frames, we opt to process frames in a streaming fashion, to support unlimited frames. At the heart of StreamV2V lies a backward-looking principle that relates the present to the past. This is realized by maintaining a feature bank, which archives information from past frames. For incoming frames, StreamV2V extends self-attention to include banked keys and values and directly fuses similar past features into the output. The feature bank is continually updated by merging stored and new features, making it compact but informative. StreamV2V stands out for its adaptability and efficiency, seamlessly integrating with image diffusion models without fine-tuning. It can run 20 FPS on one A100 GPU, being 15x, 46x, 108x, and 158x faster than FlowVid, CoDeF, Rerender, and TokenFlow, respectively. Quantitative metrics and user studies confirm StreamV2V's exceptional ability to maintain temporal consistency.
Authors: Yuchi Wang, Junliang Guo, Jianhong Bai, Runyi Yu, Tianyu He, Xu Tan, Xu Sun, Jiang Bian
Abstract: Recent talking avatar generation models have made strides in achieving realistic and accurate lip synchronization with the audio, but often fall short in controlling and conveying detailed expressions and emotions of the avatar, making the generated video less vivid and controllable. In this paper, we propose a novel text-guided approach for generating emotionally expressive 2D avatars, offering fine-grained control, improved interactivity, and generalizability to the resulting video. Our framework, named InstructAvatar, leverages a natural language interface to control the emotion as well as the facial motion of avatars. Technically, we design an automatic annotation pipeline to construct an instruction-video paired training dataset, equipped with a novel two-branch diffusion-based generator to predict avatars with audio and text instructions at the same time. Experimental results demonstrate that InstructAvatar produces results that align well with both conditions, and outperforms existing methods in fine-grained emotion control, lip-sync quality, and naturalness. Our project page is https://wangyuchi369.github.io/InstructAvatar/.
Authors: Ke Fan, Junshu Tang, Weijian Cao, Ran Yi, Moran Li, Jingyu Gong, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Lizhuang Ma
Abstract: Text-to-motion synthesis is a crucial task in computer vision. Existing methods are limited in their universality, as they are tailored for single-person or two-person scenarios and can not be applied to generate motions for more individuals. To achieve the number-free motion synthesis, this paper reconsiders motion generation and proposes to unify the single and multi-person motion by the conditional motion distribution. Furthermore, a generation module and an interaction module are designed for our FreeMotion framework to decouple the process of conditional motion generation and finally support the number-free motion synthesis. Besides, based on our framework, the current single-person motion spatial control method could be seamlessly integrated, achieving precise control of multi-person motion. Extensive experiments demonstrate the superior performance of our method and our capability to infer single and multi-human motions simultaneously.
Authors: Xuanjia Zhao, Jian Guan, Congyi Fan, Dongli Xu, Youtian Lin, Haiwei Pan, Pengming Feng
Abstract: Drag-based image editing using generative models provides precise control over image contents, enabling users to manipulate anything in an image with a few clicks. However, prevailing methods typically adopt $n$-step iterations for latent semantic optimization to achieve drag-based image editing, which is time-consuming and limits practical applications. In this paper, we introduce a novel one-step drag-based image editing method, i.e., FastDrag, to accelerate the editing process. Central to our approach is a latent warpage function (LWF), which simulates the behavior of a stretched material to adjust the location of individual pixels within the latent space. This innovation achieves one-step latent semantic optimization and hence significantly promotes editing speeds. Meanwhile, null regions emerging after applying LWF are addressed by our proposed bilateral nearest neighbor interpolation (BNNI) strategy. This strategy interpolates these regions using similar features from neighboring areas, thus enhancing semantic integrity. Additionally, a consistency-preserving strategy is introduced to maintain the consistency between the edited and original images by adopting semantic information from the original image, saved as key and value pairs in self-attention module during diffusion inversion, to guide the diffusion sampling. Our FastDrag is validated on the DragBench dataset, demonstrating substantial improvements in processing time over existing methods, while achieving enhanced editing performance.
Authors: Sohag Kumar Mondal, Md. Simul Hasan Talukder, Mohammad Aljaidi, Rejwan Bin Sulaiman, Md Mohiuddin Sarker Tushar, Amjad A Alsuwaylimi
Abstract: Blood cell classification and counting are vital for the diagnosis of various blood-related diseases, such as anemia, leukemia, and thrombocytopenia. The manual process of blood cell classification and counting is time-consuming, prone to errors, and labor-intensive. Therefore, we have proposed a DL based automated system for blood cell classification and counting from microscopic blood smear images. We classify total of nine types of blood cells, including Erythrocyte, Erythroblast, Neutrophil, Basophil, Eosinophil, Lymphocyte, Monocyte, Immature Granulocytes, and Platelet. Several preprocessing steps like image resizing, rescaling, contrast enhancement and augmentation are utilized. To segment the blood cells from the entire microscopic images, we employed the U-Net model. This segmentation technique aids in extracting the region of interest (ROI) by removing complex and noisy background elements. Both pixel-level metrics such as accuracy, precision, and sensitivity, and object-level evaluation metrics like Intersection over Union (IOU) and Dice coefficient are considered to comprehensively evaluate the performance of the U-Net model. The segmentation model achieved impressive performance metrics, including 98.23% accuracy, 98.40% precision, 98.25% sensitivity, 95.97% Intersection over Union (IOU), and 97.92% Dice coefficient. Subsequently, a watershed algorithm is applied to the segmented images to separate overlapped blood cells and extract individual cells. We have proposed a BloodCell-Net approach incorporated with custom light weight convolutional neural network (LWCNN) for classifying individual blood cells into nine types. Comprehensive evaluation of the classifier's performance is conducted using metrics including accuracy, precision, recall, and F1 score. The classifier achieved an average accuracy of 97.10%, precision of 97.19%, recall of 97.01%, and F1 score of 97.10%.
Authors: Divij Jain, Saatvik Kher, Lena Liang, Yufeng Wu, Ashley Zheng, Xizhen Cai, Anna Plantinga, Elizabeth Upton
Abstract: We propose a machine learning pipeline for forensic shoeprint pattern matching that improves on the accuracy and generalisability of existing methods. We extract 2D coordinates from shoeprint scans using edge detection and align the two shoeprints with iterative closest point (ICP). We then extract similarity metrics to quantify how well the two prints match and use these metrics to train a random forest that generates a probabilistic measurement of how likely two prints are to have originated from the same outsole. We assess the generalisability of machine learning methods trained on lab shoeprint scans to more realistic crime scene shoeprint data by evaluating the accuracy of our methods on several shoeprint scenarios: partial prints, prints with varying levels of blurriness, prints with different amounts of wear, and prints from different shoe models. We find that models trained on one type of shoeprint yield extremely high levels of accuracy when tested on shoeprint pairs of the same scenario but fail to generalise to other scenarios. We also discover that models trained on a variety of scenarios predict almost as accurately as models trained on specific scenarios.
Authors: Kendall Schmidt (American College of Radiology, USA), Benjamin Bearce (The Massachusetts General Hospital, USA,University of Colorado, USA), Ken Chang (The Massachusetts General Hospital), Laura Coombs (American College of Radiology, USA), Keyvan Farahani (National Institutes of Health National Cancer Institute, USA), Marawan Elbatele (Computer Vision,Robotics Institute, University of Girona, Spain), Kaouther Mouhebe (Computer Vision,Robotics Institute, University of Girona, Spain), Robert Marti (Computer Vision,Robotics Institute, University of Girona, Spain), Ruipeng Zhang (Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, China,Shanghai AI Laboratory, China), Yao Zhang (Shanghai AI Laboratory, China), Yanfeng Wang (Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, China,Shanghai AI Laboratory, China), Yaojun Hu (Real Doctor AI Research Centre, Zhejiang University, China), Haochao Ying (Real Doctor AI Research Centre, Zhejiang University, China,School of Public Health, Zhejiang University, China), Yuyang Xu (Real Doctor AI Research Centre, Zhejiang University, China,College of Computer Science,Technology, Zhejiang University, China), Conrad Testagrose (University of North Florida College of Computing Jacksonville, USA), Mutlu Demirer (Mayo Clinic Florida Radiology, USA), Vikash Gupta (Mayo Clinic Florida Radiology, USA), \"Unal Ak\"unal (Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany), Markus Bujotzek (Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany), Klaus H. Maier-Hein (Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany), Yi Qin (Electronic,Computer Engineering, Hong Kong University of Science,Technology, China), Xiaomeng Li (Electronic,Computer Engineering, Hong Kong University of Science,Technology, China), Jayashree Kalpathy-Cramer (The Massachusetts General Hospital, USA,University of Colorado, USA), Holger R. Roth (NVIDIA, USA)
Abstract: The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical School's Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location.
Authors: Zakariya Chaouai, Mohamed Tamaazousti
Abstract: Most of the recent literature on image Super-Resolution (SR) can be classified into two main approaches. The first one involves learning a corruption model tailored to a specific dataset, aiming to mimic the noise and corruption in low-resolution images, such as sensor noise. However, this approach is data-specific, tends to lack adaptability, and its accuracy diminishes when faced with unseen types of image corruptions. A second and more recent approach, referred to as Robust Super-Resolution (RSR), proposes to improve real-world SR by harnessing the generalization capabilities of a model by making it robust to adversarial attacks. To delve further into this second approach, our paper explores the universality of various methods for enhancing the robustness of deep learning SR models. In other words, we inquire: "Which robustness method exhibits the highest degree of adaptability when dealing with a wide range of adversarial attacks ?". Our extensive experimentation on both synthetic and real-world images empirically demonstrates that median randomized smoothing (MRS) is more general in terms of robustness compared to adversarial learning techniques, which tend to focus on specific types of attacks. Furthermore, as expected, we also illustrate that the proposed universal robust method enables the SR model to handle standard corruptions more effectively, such as blur and Gaussian noise, and notably, corruptions naturally present in real-world images. These results support the significance of shifting the paradigm in the development of real-world SR methods towards RSR, especially via MRS.
Authors: Weiyu Li, Jiarui Liu, Rui Chen, Yixun Liang, Xuelin Chen, Ping Tan, Xiaoxiao Long
Abstract: We present a novel generative 3D modeling system, coined CraftsMan, which can generate high-fidelity 3D geometries with highly varied shapes, regular mesh topologies, and detailed surfaces, and, notably, allows for refining the geometry in an interactive manner. Despite the significant advancements in 3D generation, existing methods still struggle with lengthy optimization processes, irregular mesh topologies, noisy surfaces, and difficulties in accommodating user edits, consequently impeding their widespread adoption and implementation in 3D modeling software. Our work is inspired by the craftsman, who usually roughs out the holistic figure of the work first and elaborates the surface details subsequently. Specifically, we employ a 3D native diffusion model, which operates on latent space learned from latent set-based 3D representations, to generate coarse geometries with regular mesh topology in seconds. In particular, this process takes as input a text prompt or a reference image and leverages a powerful multi-view (MV) diffusion model to generate multiple views of the coarse geometry, which are fed into our MV-conditioned 3D diffusion model for generating the 3D geometry, significantly improving robustness and generalizability. Following that, a normal-based geometry refiner is used to significantly enhance the surface details. This refinement can be performed automatically, or interactively with user-supplied edits. Extensive experiments demonstrate that our method achieves high efficacy in producing superior-quality 3D assets compared to existing methods. HomePage: https://craftsman3d.github.io/, Code: https://github.com/wyysf-98/CraftsMan
URLs: https://craftsman3d.github.io/,, https://github.com/wyysf-98/CraftsMan
Authors: Md Yousuf Harun, Kyungbok Lee, Jhair Gallardo, Giri Krishnan, Christopher Kanan
Abstract: Embeddings produced by pre-trained deep neural networks (DNNs) are widely used; however, their efficacy for downstream tasks can vary widely. We study the factors influencing out-of-distribution (OOD) generalization of pre-trained DNN embeddings through the lens of the tunnel effect hypothesis, which suggests deeper DNN layers compress representations and hinder OOD performance. Contrary to earlier work, we find the tunnel effect is not universal. Based on 10,584 linear probes, we study the conditions that mitigate the tunnel effect by varying DNN architecture, training dataset, image resolution, and augmentations. We quantify each variable's impact using a novel SHAP analysis. Our results emphasize the danger of generalizing findings from toy datasets to broader contexts.
Authors: Yutao Feng, Yintong Shang, Xiang Feng, Lei Lan, Shandian Zhe, Tianjia Shao, Hongzhi Wu, Kun Zhou, Hao Su, Chenfanfu Jiang, Yin Yang
Abstract: We present ElastoGen, a knowledge-driven model that generates physically accurate and coherent 4D elastodynamics. Instead of relying on petabyte-scale data-driven learning, ElastoGen leverages the principles of physics-in-the-loop and learns from established physical knowledge, such as partial differential equations and their numerical solutions. The core idea of ElastoGen is converting the global differential operator, corresponding to the nonlinear elastodynamic equations, into iterative local convolution-like operations, which naturally fit modern neural networks. Each network module is specifically designed to support this goal rather than functioning as a black box. As a result, ElastoGen is exceptionally lightweight in terms of both training requirements and network scale. Additionally, due to its alignment with physical procedures, ElastoGen efficiently generates accurate dynamics for a wide range of hyperelastic materials and can be easily integrated with upstream and downstream deep modules to enable end-to-end 4D generation.
Authors: Maxime Burchi, Radu Timofte
Abstract: The DreamerV3 agent recently demonstrated state-of-the-art performance in diverse domains, learning powerful world models in latent space using a pixel reconstruction loss. However, while the reconstruction loss is essential to Dreamer's performance, it also necessitates modeling unnecessary information. Consequently, Dreamer sometimes fails to perceive crucial elements which are necessary for task-solving when visual distractions are present in the observation, significantly limiting its potential. In this paper, we present MuDreamer, a robust reinforcement learning agent that builds upon the DreamerV3 algorithm by learning a predictive world model without the need for reconstructing input signals. Rather than relying on pixel reconstruction, hidden representations are instead learned by predicting the environment value function and previously selected actions. Similar to predictive self-supervised methods for images, we find that the use of batch normalization is crucial to prevent learning collapse. We also study the effect of KL balancing between model posterior and prior losses on convergence speed and learning stability. We evaluate MuDreamer on the commonly used DeepMind Visual Control Suite and demonstrate stronger robustness to visual distractions compared to DreamerV3 and other reconstruction-free approaches, replacing the environment background with task-irrelevant real-world videos. Our method also achieves comparable performance on the Atari100k benchmark while benefiting from faster training.
Authors: Guoyao Shen, Mengyu Li, Stephan Anderson, Chad W. Farris, Xin Zhang
Abstract: Purpose: To develop and evaluate a deep learning model for general accelerated MRI reconstruction. Materials and Methods: This retrospective study built a magnetic resonance image processing transformer (MR-IPT) which includes multi-head-tails and a single shared window transformer main body. Three mutations of MR-IPT with different transformer structures were implemented to guide the design of our MR-IPT model. Pre-trained on the MRI set of RadImageNet including 672675 images with multiple anatomy categories, the model was further migrated and evaluated on fastMRI knee dataset with 25012 images for downstream reconstruction tasks. We performed comparison studies with three CNN-based conventional networks in zero- and few-shot learning scenarios. Transfer learning process was conducted on both MR-IPT and CNN networks to further validate the generalizability of MR-IPT. To study the model performance stability, we evaluated our model with various downstream dataset sizes ranging from 10 to 2500 images. Result: The MR-IPT model provided superior performance in multiple downstream tasks compared to conventional CNN networks. MR-IPT achieved a PSNR/SSIM of 26.521/0.6102 (4-fold) and 24.861/0.4996 (8-fold) in 10-epoch learning, surpassing UNet128 at 25.056/0.5832 (4-fold) and 22.984/0.4637 (8-fold). With the same large-scale pre-training, MR-IPT provided a 5% performance boost compared to UNet128 in zero-shot learning in 8-fold and 3% in 4-fold. Conclusion: MR-IPT framework benefits from its transformer-based structure and large-scale pre-training and can serve as a solid backbone in other downstream tasks with zero- and few-shot learning.
Authors: Nohemi Sofia Leon Contreras, Marina D'Amato, Francesco Ciompi, Clement Grisi, Witali Aswolinskiy, Simona Vatrano, Filippo Fraggetta, Iris Nagtegaal
Abstract: Training neural networks with high-quality pixel-level annotation in histopathology whole-slide images (WSI) is an expensive process due to gigapixel resolution of WSIs. However, recent advances in self-supervised learning have shown that highly descriptive image representations can be learned without the need for annotations. We investigate the application of the recent Hierarchical Image Pyramid Transformer (HIPT) model for the specific task of classification of colorectal biopsies and polyps. After evaluating the effectiveness of TCGA-learned features in the original HIPT model, we incorporate colon biopsy image information into HIPT's pretraining using two distinct strategies: (1) fine-tuning HIPT from the existing TCGA weights and (2) pretraining HIPT from random weight initialization. We compare the performance of these pretraining regimes on two colorectal biopsy classification tasks: binary and multiclass classification.
Authors: Huali Ren, Anli Yan, Chong-zhi Gao, Hongyang Yan, Zhenxin Zhang, Jin Li
Abstract: Visual Prompt Learning (VPL) differs from traditional fine-tuning methods in reducing significant resource consumption by avoiding updating pre-trained model parameters. Instead, it focuses on learning an input perturbation, a visual prompt, added to downstream task data for making predictions. Since learning generalizable prompts requires expert design and creation, which is technically demanding and time-consuming in the optimization process, developers of Visual Prompts as a Service (VPaaS) have emerged. These developers profit by providing well-crafted prompts to authorized customers. However, a significant drawback is that prompts can be easily copied and redistributed, threatening the intellectual property of VPaaS developers. Hence, there is an urgent need for technology to protect the rights of VPaaS developers. To this end, we present a method named \textbf{WVPrompt} that employs visual prompt watermarking in a black-box way. WVPrompt consists of two parts: prompt watermarking and prompt verification. Specifically, it utilizes a poison-only backdoor attack method to embed a watermark into the prompt and then employs a hypothesis-testing approach for remote verification of prompt ownership. Extensive experiments have been conducted on three well-known benchmark datasets using three popular pre-trained models: RN50, BIT-M, and Instagram. The experimental results demonstrate that WVPrompt is efficient, harmless, and robust to various adversarial operations.
Authors: Zhigao Cai, Xing-Ming Zhao
Abstract: Automatic segmentation of the fetal brain is still challenging due to the health state of fetal development, motion artifacts, and variability across gestational ages, since existing methods rely on high-quality datasets of healthy fetuses. In this work, we propose a novel cascade network called CasUNext to enhance the accuracy and generalization of fetal brain MRI segmentation. CasUNext incorporates depth-wise separable convolution, attention mechanisms, and a two-step cascade architecture for efficient high-precision segmentation. The first network localizes the fetal brain region, while the second network focuses on detailed segmentation. We evaluate CasUNext on 150 fetal MRI scans between 20 to 36 weeks from two scanners made by Philips and Siemens including axial, coronal, and sagittal views, and also validated on a dataset of 50 abnormal fetuses. Results demonstrate that CasUNext achieves improved segmentation performance compared to U-Nets and other state-of-the-art approaches. It obtains an average Dice coefficient of 96.1% and mean intersection over union of 95.9% across diverse scenarios. CasUNext shows promising capabilities for handling the challenges of multi-view fetal MRI and abnormal cases, which could facilitate various quantitative analyses and apply to multi-site data.
Authors: Zhongnian Li, Jinghao Xu, Peng Ying, Meng Wei, Tongfeng Sun, Xinzheng Xu
Abstract: Weakly supervised learning has recently achieved considerable success in reducing annotation costs and label noise. Unfortunately, existing weakly supervised learning methods are short of ability in generating reliable labels via pre-trained vision-language models (VLMs). In this paper, we propose a novel weakly supervised labeling setting, namely True-False Labels (TFLs) which can achieve high accuracy when generated by VLMs. The TFL indicates whether an instance belongs to the label, which is randomly and uniformly sampled from the candidate label set. Specifically, we theoretically derive a risk-consistent estimator to explore and utilize the conditional probability distribution information of TFLs. Besides, we propose a convolutional-based Multi-modal Prompt Retrieving (MRP) method to bridge the gap between the knowledge of VLMs and target learning tasks. Experimental results demonstrate the effectiveness of the proposed TFL setting and MRP learning method. The code to reproduce the experiments is at https://github.com/Tranquilxu/TMP.
Authors: Zhibo Wang, Peng Kuang, Zhixuan Chu, Jingyi Wang, Kui Ren
Abstract: Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts in real-world scenarios. To tackle the problem, numerous debias approaches have been proposed and benchmarked on datasets intentionally designed with severe biases. However, it remains to be asked: \textit{1. Do existing benchmarks really capture biases in the real world? 2. Can existing debias methods handle biases in the real world?} To answer the questions, we revisit biased distributions in existing benchmarks and real-world datasets, and propose a fine-grained framework for analyzing dataset bias by disentangling it into the magnitude and prevalence of bias. We observe and theoretically demonstrate that existing benchmarks poorly represent real-world biases. We further introduce two novel biased distributions to bridge this gap, forming a nuanced evaluation framework for real-world debiasing. Building upon these results, we evaluate existing debias methods with our evaluation framework. Results show that existing methods are incapable of handling real-world biases. Through in-depth analysis, we propose a simple yet effective approach that can be easily applied to existing debias methods, named Debias in Destruction (DiD). Empirical results demonstrate the superiority of DiD, improving the performance of existing methods on all types of biases within the proposed evaluation framework.
Authors: Jia He, Bonan Li, Ge Yang, Ziwen Liu
Abstract: Solving 3D medical inverse problems such as image restoration and reconstruction is crucial in modern medical field. However, the curse of dimensionality in 3D medical data leads mainstream volume-wise methods to suffer from high resource consumption and challenges models to successfully capture the natural distribution, resulting in inevitable volume inconsistency and artifacts. Some recent works attempt to simplify generation in the latent space but lack the capability to efficiently model intricate image details. To address these limitations, we present Blaze3DM, a novel approach that enables fast and high-fidelity generation by integrating compact triplane neural field and powerful diffusion model. In technique, Blaze3DM begins by optimizing data-dependent triplane embeddings and a shared decoder simultaneously, reconstructing each triplane back to the corresponding 3D volume. To further enhance 3D consistency, we introduce a lightweight 3D aware module to model the correlation of three vertical planes. Then, diffusion model is trained on latent triplane embeddings and achieves both unconditional and conditional triplane generation, which is finally decoded to arbitrary size volume. Extensive experiments on zero-shot 3D medical inverse problem solving, including sparse-view CT, limited-angle CT, compressed-sensing MRI, and MRI isotropic super-resolution, demonstrate that Blaze3DM not only achieves state-of-the-art performance but also markedly improves computational efficiency over existing methods (22~40x faster than previous work).
Authors: Saul Fuster, Umay Kiraz, Trygve Eftest{\o}l, Emiel A. M. Janssen, Kjersti Engan
Abstract: The most prevalent form of bladder cancer is urothelial carcinoma, characterized by a high recurrence rate and substantial lifetime treatment costs for patients. Grading is a prime factor for patient risk stratification, although it suffers from inconsistencies and variations among pathologists. Moreover, absence of annotations in medical imaging difficults training deep learning models. To address these challenges, we introduce a pipeline designed for bladder cancer grading using histological slides. First, it extracts urothelium tissue tiles at different magnification levels, employing a convolutional neural network for processing for feature extraction. Then, it engages in the slide-level prediction process. It employs a nested multiple instance learning approach with attention to predict the grade. To distinguish different levels of malignancy within specific regions of the slide, we include the origins of the tiles in our analysis. The attention scores at region level is shown to correlate with verified high-grade regions, giving some explainability to the model. Clinical evaluations demonstrate that our model consistently outperforms previous state-of-the-art methods.
Authors: Yongliang Wu, Shiji Zhou, Mingzhuo Yang, Lianzhe Wang, Wenbo Zhu, Heng Chang, Xiao Zhou, Xu Yang
Abstract: Current text-to-image diffusion models have achieved groundbreaking results in image generation tasks. However, the unavoidable inclusion of sensitive information during pre-training introduces significant risks such as copyright infringement and privacy violations in the generated images. Machine Unlearning (MU) provides a effective way to the sensitive concepts captured by the model, has been shown to be a promising approach to addressing these issues. Nonetheless, existing MU methods for concept erasure encounter two primary bottlenecks: 1) generalization issues, where concept erasure is effective only for the data within the unlearn set, and prompts outside the unlearn set often still result in the generation of sensitive concepts; and 2) utility drop, where erasing target concepts significantly degrades the model's performance. To this end, this paper first proposes a concept domain correction framework for unlearning concepts in diffusion models. By aligning the output domains of sensitive concepts and anchor concepts through adversarial training, we enhance the generalizability of the unlearning results. Secondly, we devise a concept-preserving scheme based on gradient surgery. This approach alleviates the parts of the unlearning gradient that contradict the relearning gradient, ensuring that the process of unlearning minimally disrupts the model's performance. Finally, extensive experiments validate the effectiveness of our model, demonstrating our method's capability to address the challenges of concept unlearning in diffusion models while preserving model utility.
Authors: Jianbiao Mei, Yukai Ma, Xuemeng Yang, Licheng Wen, Xinyu Cai, Xin Li, Daocheng Fu, Bo Zhang, Pinlong Cai, Min Dou, Botian Shi, Liang He, Yong Liu, Yu Qiao
Abstract: Autonomous driving has advanced significantly due to sensors, machine learning, and artificial intelligence improvements. However, prevailing methods struggle with intricate scenarios and causal relationships, hindering adaptability and interpretability in varied environments. To address the above problems, we introduce LeapAD, a novel paradigm for autonomous driving inspired by the human cognitive process. Specifically, LeapAD emulates human attention by selecting critical objects relevant to driving decisions, simplifying environmental interpretation, and mitigating decision-making complexities. Additionally, LeapAD incorporates an innovative dual-process decision-making module, which consists of an Analytic Process (System-II) for thorough analysis and reasoning, along with a Heuristic Process (System-I) for swift and empirical processing. The Analytic Process leverages its logical reasoning to accumulate linguistic driving experience, which is then transferred to the Heuristic Process by supervised fine-tuning. Through reflection mechanisms and a growing memory bank, LeapAD continuously improves itself from past mistakes in a closed-loop environment. Closed-loop testing in CARLA shows that LeapAD outperforms all methods relying solely on camera input, requiring 1-2 orders of magnitude less labeled data. Experiments also demonstrate that as the memory bank expands, the Heuristic Process with only 1.8B parameters can inherit the knowledge from a GPT-4 powered Analytic Process and achieve continuous performance improvement. Code will be released at https://github.com/PJLab-ADG/LeapAD.
Authors: Abdur Rahman, Rajat Chawla, Muskaan Kumar, Arkajit Datta, Adarsh Jha, Mukunda NS, Ishaan Bhola
Abstract: In the rapidly evolving landscape of AI research and application, Multimodal Large Language Models (MLLMs) have emerged as a transformative force, adept at interpreting and integrating information from diverse modalities such as text, images, and Graphical User Interfaces (GUIs). Despite these advancements, the nuanced interaction and understanding of GUIs pose a significant challenge, limiting the potential of existing models to enhance automation levels. To bridge this gap, this paper presents V-Zen, an innovative Multimodal Large Language Model (MLLM) meticulously crafted to revolutionise the domain of GUI understanding and grounding. Equipped with dual-resolution image encoders, V-Zen establishes new benchmarks in efficient grounding and next-action prediction, thereby laying the groundwork for self-operating computer systems. Complementing V-Zen is the GUIDE dataset, an extensive collection of real-world GUI elements and task-based sequences, serving as a catalyst for specialised fine-tuning. The successful integration of V-Zen and GUIDE marks the dawn of a new era in multimodal AI research, opening the door to intelligent, autonomous computing experiences. This paper extends an invitation to the research community to join this exciting journey, shaping the future of GUI automation. In the spirit of open science, our code, data, and model will be made publicly available, paving the way for multimodal dialogue scenarios with intricate and precise interactions.
Authors: Yuandou Wang, Neel Kanwal, Kjersti Engan, Chunming Rong, Paola Grosso, Zhiming Zhao
Abstract: Running deep neural networks for large medical images is a resource-hungry and time-consuming task with centralized computing. Outsourcing such medical image processing tasks to hybrid clouds has benefits, such as a significant reduction of execution time and monetary cost. However, due to privacy concerns, it is still challenging to process sensitive medical images over clouds, which would hinder their deployment in many real-world applications. To overcome this, we first formulate the overall optimization objectives of the privacy-preserving distributed system model, i.e., minimizing the amount of information about the private data learned by the adversaries throughout the process, reducing the maximum execution time and cost under the user budget constraint. We propose a novel privacy-preserving and cost-effective method called PriCE to solve this multi-objective optimization problem. We performed extensive simulation experiments for artifact detection tasks on medical images using an ensemble of five deep convolutional neural network inferences as the workflow task. Experimental results show that PriCE successfully splits a wide range of input gigapixel medical images with graph-coloring-based strategies, yielding desired output utility and lowering the privacy risk, makespan, and monetary cost under user's budget.
Authors: Shiyu Qin, Jinpeng Wang, Yimin Zhou, Bin Chen, Tianci Luo, Baoyi An, Tao Dai, Shutao Xia, Yaowei Wang
Abstract: Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e., rate-distortion trade-off) and efficiency remains a challenge. Recently, state-space models (SSMs) have shown promise due to their long-range modeling capacity and efficiency. Inspired by this, we take the first step to explore SSMs for visual compression. We introduce MambaVC, a simple, strong and efficient compression network based on SSM. MambaVC develops a visual state space (VSS) block with a 2D selective scanning (2DSS) module as the nonlinear activation function after each downsampling, which helps to capture informative global contexts and enhances compression. On compression benchmark datasets, MambaVC achieves superior rate-distortion performance with lower computational and memory overheads. Specifically, it outperforms CNN and Transformer variants by 9.3% and 15.6% on Kodak, respectively, while reducing computation by 42% and 24%, and saving 12% and 71% of memory. MambaVC shows even greater improvements with high-resolution images, highlighting its potential and scalability in real-world applications. We also provide a comprehensive comparison of different network designs, underscoring MambaVC's advantages.
Authors: Jorge Condor, Sebastien Speierer, Lukas Bode, Aljaz Bozic, Simon Green, Piotr Didyk, Adrian Jarabo
Abstract: We propose a volumetric representation based on primitives to model scattering and emissive media. Accurate scene representations enabling efficient rendering are essential for many computer graphics applications. General and unified representations that can handle surface and volume-based representations simultaneously, allowing for physically accurate modeling, remain a research challenge. Inspired by recent methods for scene reconstruction that leverage mixtures of 3D Gaussians to model radiance fields, we formalize and generalize the modeling of scattering and emissive media using mixtures of simple kernel-based volumetric primitives. We introduce closed-form solutions for transmittance and free-flight distance sampling for 3D Gaussian kernels, and propose several optimizations to use our method efficiently within any off-the-shelf volumetric path tracer by leveraging ray tracing for efficiently querying the medium. We demonstrate our method as an alternative to other forms of volume modeling (e.g. voxel grid-based representations) for forward and inverse rendering of scattering media. Furthermore, we adapt our method to the problem of radiance field optimization and rendering, and demonstrate comparable performance to the state of the art, while providing additional flexibility in terms of performance and usability.
Authors: Ali Rasekh, Reza Heidari, Amir Hosein Haji Mohammad Rezaie, Parsa Sharifi Sedeh, Zahra Ahmadi, Prasenjit Mitra, Wolfgang Nejdl
Abstract: With the increasing availability of diverse data types, particularly images and time series data from medical experiments, there is a growing demand for techniques designed to combine various modalities of data effectively. Our motivation comes from the important areas of predicting mortality and phenotyping where using different modalities of data could significantly improve our ability to predict. To tackle this challenge, we introduce a new method that uses two separate encoders, one for each type of data, allowing the model to understand complex patterns in both visual and time-based information. Apart from the technical challenges, our goal is to make the predictive model more robust in noisy conditions and perform better than current methods. We also deal with imbalanced datasets and use an uncertainty loss function, yielding improved results while simultaneously providing a principled means of modeling uncertainty. Additionally, we include attention mechanisms to fuse different modalities, allowing the model to focus on what's important for each task. We tested our approach using the comprehensive multimodal MIMIC dataset, combining MIMIC-IV and MIMIC-CXR datasets. Our experiments show that our method is effective in improving multimodal deep learning for clinical applications. The code will be made available online.
Authors: Lijie Hu, Chenyang Ren, Zhengyu Hu, Cheng-Long Wang, Di Wang
Abstract: Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on cases where the data, including concepts, are clean. In many scenarios, we always need to remove/insert some training data or new concepts from trained CBMs due to different reasons, such as privacy concerns, data mislabelling, spurious concepts, and concept annotation errors. Thus, the challenge of deriving efficient editable CBMs without retraining from scratch persists, particularly in large-scale applications. To address these challenges, we propose Editable Concept Bottleneck Models (ECBMs). Specifically, ECBMs support three different levels of data removal: concept-label-level, concept-level, and data-level. ECBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for re-training. Experimental results demonstrate the efficiency and effectiveness of our ECBMs, affirming their adaptability within the realm of CBMs.
Authors: Aleksei Leonov, Aleksei Zakharov, Sergey Koshelev, Maxim Pisov, Anvar Kurmukov, Mikhail Belyaev
Abstract: Automatic ribs segmentation and numeration can increase computed tomography assessment speed and reduce radiologists mistakes. We introduce a model for multilabel ribs segmentation with hierarchical loss function, which enable to improve multilabel segmentation quality. Also we propose postprocessing technique to further increase labeling quality. Our model achieved new state-of-the-art 98.2% label accuracy on public RibSeg v2 dataset, surpassing previous result by 6.7%.
Authors: Yuyang Xue, Jingshuai Liu, Steven McDonagh, Sotirios A. Tsaftaris
Abstract: Machine unlearning is a promising paradigm for removing unwanted data samples from a trained model, towards ensuring compliance with privacy regulations and limiting harmful biases. Although unlearning has been shown in, e.g., classification and recommendation systems, its potential in medical image-to-image translation, specifically in image recon-struction, has not been thoroughly investigated. This paper shows that machine unlearning is possible in MRI tasks and has the potential to benefit for bias removal. We set up a protocol to study how much shared knowledge exists between datasets of different organs, allowing us to effectively quantify the effect of unlearning. Our study reveals that combining training data can lead to hallucinations and reduced image quality in the reconstructed data. We use unlearning to remove hallucinations as a proxy exemplar of undesired data removal. Indeed, we show that machine unlearning is possible without full retraining. Furthermore, our observations indicate that maintaining high performance is feasible even when using only a subset of retain data. We have made our code publicly accessible.
Authors: Huy V. Vo, Vasil Khalidov, Timoth\'ee Darcet, Th\'eo Moutakanni, Nikita Smetanin, Marc Szafraniec, Hugo Touvron, Camille Couprie, Maxime Oquab, Armand Joulin, Herv\'e J\'egou, Patrick Labatut, Piotr Bojanowski
Abstract: Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some limitations similar to those encountered in supervised learning, e.g., the crowd-sourced selection of data is costly and time-consuming, preventing scaling the dataset size. In this work, we consider the problem of automatic curation of high-quality datasets for self-supervised pre-training. We posit that such datasets should be large, diverse and balanced, and propose a clustering-based approach for building ones satisfying all these criteria. Our method involves successive and hierarchical applications of $k$-means on a large and diverse data repository to obtain clusters that distribute uniformly among data concepts, followed by a hierarchical, balanced sampling step from these clusters. Extensive experiments on three different data domains including web-based images, satellite images and text show that features trained on our automatically curated datasets outperform those trained on uncurated data while being on par or better than ones trained on manually curated data.
Authors: Nicolai Steinke, Daniel G\"ohring, Ra\`ul Rojas
Abstract: The precise point cloud ground segmentation is a crucial prerequisite of virtually all perception tasks for LiDAR sensors in autonomous vehicles. Especially the clustering and extraction of objects from a point cloud usually relies on an accurate removal of ground points. The correct estimation of the surrounding terrain is important for aspects of the drivability of a surface, path planning, and obstacle prediction. In this article, we propose our system GroundGrid which relies on 2D elevation maps to solve the terrain estimation and point cloud ground segmentation problems. We evaluate the ground segmentation and terrain estimation performance of GroundGrid and compare it to other state-of-the-art methods using the SemanticKITTI dataset and a novel evaluation method relying on airborne LiDAR scanning. The results show that GroundGrid is capable of outperforming other state-of-the-art systems with an average IoU of 94.78% while maintaining a high run-time performance of 171Hz. The source code is available at https://github.com/dcmlr/groundgrid
Authors: Wei Wu, Xiaoxin Feng, Ziyan Gao, Yuheng Kan
Abstract: Data-driven autonomous driving motion generation tasks are frequently impacted by the limitations of dataset size and the domain gap between datasets, which precludes their extensive application in real-world scenarios. To address this issue, we introduce SMART, a novel autonomous driving motion generation paradigm that models vectorized map and agent trajectory data into discrete sequence tokens. These tokens are then processed through a decoder-only transformer architecture to train for the next token prediction task across spatial-temporal series. This GPT-style method allows the model to learn the motion distribution in real driving scenarios. SMART achieves state-of-the-art performance across most of the metrics on the generative Sim Agents challenge, ranking 1st on the leaderboards of Waymo Open Motion Dataset (WOMD), demonstrating remarkable inference speed. Moreover, SMART represents the generative model in the autonomous driving motion domain, exhibiting zero-shot generalization capabilities: Using only the NuPlan dataset for training and WOMD for validation, SMART achieved a competitive score of 0.71 on the Sim Agents challenge. Lastly, we have collected over 1 billion motion tokens from multiple datasets, validating the model's scalability. These results suggest that SMART has initially emulated two important properties: scalability and zero-shot generalization, and preliminarily meets the needs of large-scale real-time simulation applications. We have released all the code to promote the exploration of models for motion generation in the autonomous driving field.
Authors: Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Aman Chadha, Samrat Mondal
Abstract: The mining of adverse drug events (ADEs) is pivotal in pharmacovigilance, enhancing patient safety by identifying potential risks associated with medications, facilitating early detection of adverse events, and guiding regulatory decision-making. Traditional ADE detection methods are reliable but slow, not easily adaptable to large-scale operations, and offer limited information. With the exponential increase in data sources like social media content, biomedical literature, and Electronic Medical Records (EMR), extracting relevant ADE-related information from these unstructured texts is imperative. Previous ADE mining studies have focused on text-based methodologies, overlooking visual cues, limiting contextual comprehension, and hindering accurate interpretation. To address this gap, we present a MultiModal Adverse Drug Event (MMADE) detection dataset, merging ADE-related textual information with visual aids. Additionally, we introduce a framework that leverages the capabilities of LLMs and VLMs for ADE detection by generating detailed descriptions of medical images depicting ADEs, aiding healthcare professionals in visually identifying adverse events. Using our MMADE dataset, we showcase the significance of integrating visual cues from images to enhance overall performance. This approach holds promise for patient safety, ADE awareness, and healthcare accessibility, paving the way for further exploration in personalized healthcare.
Authors: Zhicheng Ding, Zhixin Lai, Siyang Li, Panfeng Li, Qikai Yang, Edward Wong
Abstract: Real-time object tracking necessitates a delicate balance between speed and accuracy, a challenge exacerbated by the computational demands of deep learning methods. In this paper, we propose Confidence-Triggered Detection (CTD), an innovative approach that strategically bypasses object detection for frames closely resembling intermediate states, leveraging tracker confidence scores. CTD not only enhances tracking speed but also preserves accuracy, surpassing existing tracking algorithms. Through extensive evaluation across various tracker confidence thresholds, we identify an optimal trade-off between tracking speed and accuracy, providing crucial insights for parameter fine-tuning and enhancing CTD's practicality in real-world scenarios. Our experiments across diverse detection models underscore the robustness and versatility of the CTD framework, demonstrating its potential to enable real-time tracking in resource-constrained environments.
Authors: Karthik Seemakurthy, Erchan Aptoula, Charles Fox, Petra Bosilj
Abstract: Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features, so that a model can generalise better to previously unseen target domains. An approach to domain generalisation for object detection is proposed, the first such approach applicable to any object detection architecture. Based on a rigorous mathematical analysis, we extend approaches based on feature alignment with a novel component for performing class conditional alignment at the instance level, in addition to aligning the marginal feature distributions across domains at the image level. This allows us to fully address both components of domain shift, i.e. covariate and concept shift, and learn a domain agnostic feature representation. We perform extensive evaluation with both one-stage (FCOS, YOLO) and two-stage (FRCNN) detectors, on a newly proposed benchmark comprising several different datasets for autonomous driving applications (Cityscapes, BDD10K, ACDC, IDD) as well as the GWHD dataset for precision agriculture, and show consistent improvements to the generalisation and localisation performance over baselines and state-of-the-art.
Authors: Junsheng Zhou, Baorui Ma, Shujuan Li, Yu-Shen Liu, Yi Fang, Zhizhong Han
Abstract: Surface reconstruction for point clouds is an important task in 3D computer vision. Most of the latest methods resolve this problem by learning signed distance functions from point clouds, which are limited to reconstructing closed surfaces. Some other methods tried to represent open surfaces using unsigned distance functions (UDF) which are learned from ground truth distances. However, the learned UDF is hard to provide smooth distance fields due to the discontinuous character of point clouds. In this paper, we propose CAP-UDF, a novel method to learn consistency-aware UDF from raw point clouds. We achieve this by learning to move queries onto the surface with a field consistency constraint, where we also enable to progressively estimate a more accurate surface. Specifically, we train a neural network to gradually infer the relationship between queries and the approximated surface by searching for the moving target of queries in a dynamic way. Meanwhile, we introduce a polygonization algorithm to extract surfaces using the gradients of the learned UDF. We conduct comprehensive experiments in surface reconstruction for point clouds, real scans or depth maps, and further explore our performance in unsupervised point normal estimation, which demonstrate non-trivial improvements of CAP-UDF over the state-of-the-art methods.
Authors: Marziyeh Bamdad, Davide Scaramuzza, Alireza Darvishy
Abstract: In recent decades, several assistive technologies have been developed to improve the ability of blind and visually impaired individuals to navigate independently and safely. At the same time, simultaneous localization and mapping (SLAM) techniques have become sufficiently robust and efficient to be adopted in developing these assistive technologies. We present the first systematic literature review of 54 recent studies on SLAM-based solutions for blind and visually impaired people, focusing on literature published from 2017 onward. This review explores various localization and mapping techniques employed in this context. We systematically identified and categorized diverse SLAM approaches and analyzed their localization and mapping techniques, sensor types, computing resources, and machine-learning methods. We discuss the advantages and limitations of these techniques for blind and visually impaired navigation. Moreover, we examine the major challenges described across studies, including practical considerations that affect usability and adoption. Our analysis also evaluates the effectiveness of these SLAM-based solutions in real-world scenarios and user satisfaction, providing insights into their practical impact on BVI mobility. The insights derived from this review identify critical gaps and opportunities for future research activities, particularly in addressing the challenges presented by dynamic and complex environments. We explain how SLAM technology offers the potential to improve the ability of visually impaired individuals to navigate effectively. Finally, we present future opportunities and challenges in this domain.
Authors: Zhen Jia, Zhang Zhang, Liang Wang, Tieniu Tan
Abstract: Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value. Many researchers have been devoted to synthesizing high-fidelity human images as one of the most commonly seen object categories in daily lives, where a large number of studies are performed based on various models, task settings and applications. Thus, it is necessary to give a comprehensive overview on these variant methods on human image generation. In this paper, we divide human image generation techniques into three paradigms, i.e., data-driven methods, knowledge-guided methods and hybrid methods. For each paradigm, the most representative models and the corresponding variants are presented, where the advantages and characteristics of different methods are summarized in terms of model architectures. Besides, the main public human image datasets and evaluation metrics in the literature are summarized. Furthermore, due to the wide application potentials, the typical downstream usages of synthesized human images are covered. Finally, the challenges and potential opportunities of human image generation are discussed to shed light on future research.
Authors: Vihaan Misra, Peter Schaldenbrand, Jean Oh
Abstract: If a picture paints a thousand words, sound may voice a million. While recent robotic painting and image synthesis methods have achieved progress in generating visuals from text inputs, the translation of sound into images is vastly unexplored. Generally, sound-based interfaces and sonic interactions have the potential to expand accessibility and control for the user and provide a means to convey complex emotions and the dynamic aspects of the real world. In this paper, we propose an approach for using sound and speech to guide a robotic painting process, known here as robot synesthesia. For general sound, we encode the simulated paintings and input sounds into the same latent space. For speech, we decouple speech into its transcribed text and the tone of the speech. Whereas we use the text to control the content, we estimate the emotions from the tone to guide the mood of the painting. Our approach has been fully integrated with FRIDA, a robotic painting framework, adding sound and speech to FRIDA's existing input modalities, such as text and style. In two surveys, participants were able to correctly guess the emotion or natural sound used to generate a given painting more than twice as likely as random chance. On our sound-guided image manipulation and music-guided paintings, we discuss the results qualitatively.
Authors: Cong Zhang, Honggang Qi, Shuhui Wang, Yuezun Li, Siwei Lyu
Abstract: DeepFakes have raised serious societal concerns, leading to a great surge in detection-based forensics methods in recent years. Face forgery recognition is a standard detection method that usually follows a two-phase pipeline. While those methods perform well in ideal experimental environment, they face challenges when dealing with DeepFakes in the wild involving complex background and multiple faces of varying sizes. Moreover, most face forgery recognition methods can only process one face at a time. One straightforward way to address this issue is to simultaneous process multi-face by integrating face extraction and forgery detection in an end-to-end fashion by adapting advanced object detection architectures. However, as these object detection architectures are designed to capture the discriminative features of different object categories rather than the subtle forgery traces among the faces, the direct adaptation suffers from limited representation ability. In this paper, we propose COMICS, an end-to-end framework for multi-face forgery detection. COMICS integrates face extraction and forgery detection in a seamless manner and adapts to advanced object detection architectures. The proposed bi-grained contrastive learning approach explores face forgery traces at both the coarse- and fine-grained levels. Specifically, coarse-grained level contrastive learning captures the discriminative features among positive and negative proposal pairs at multiple layers produced by the proposal generator, and fine-grained level contrastive learning captures the pixel-wise discrepancy between the forged and original areas of the same face and the pixel-wise content inconsistency among different faces. Extensive experiments on the OpenForensics and FFIW datasets demonstrate that our method outperforms other counterparts and shows great potential for being integrated into various architectures.
Authors: Nafiseh Kakhani, Moien Rangzan, Ali Jamali, Sara Attarchi, Seyed Kazem Alavipanah, Thomas Scholten
Abstract: Digital soil mapping (DSM) is an advanced approach that integrates statistical modeling and cutting-edge technologies, including machine learning (ML) methods, to accurately depict soil properties and their spatial distribution. Soil organic carbon (SOC) is a crucial soil attribute providing valuable insights into soil health, nutrient cycling, greenhouse gas emissions, and overall ecosystem productivity. This study highlights the significance of spatial-temporal deep learning (DL) techniques within the DSM framework. A novel architecture is proposed, incorporating spatial information using a base convolutional neural network (CNN) model and spatial attention mechanism, along with climate temporal information using a long short-term memory (LSTM) network, for SOC prediction across Europe. The model utilizes a comprehensive set of environmental features, including Landsat-8 images, topography, remote sensing indices, and climate time series, as input features. Results demonstrate that the proposed framework outperforms conventional ML approaches like random forest commonly used in DSM, yielding lower root mean square error (RMSE). This model is a robust tool for predicting SOC and could be applied to other soil properties, thereby contributing to the advancement of DSM techniques and facilitating land management and decision-making processes based on accurate information.
Authors: Wenhui Zhu, Peijie Qiu, Xiwen Chen, Oana M. Dumitrascu, Yalin Wang
Abstract: Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. However, due to their weak supervision nature, the MIL methods were susceptible to overfitting and required assistance in developing comprehensive representations of target instances. While regularization typically effectively combated overfitting, its integration with the MIL model has been frequently overlooked in prior studies. Meanwhile, current regularization methods for MIL have shown limitations in their capacity to uncover a diverse array of representations. In this study, we delve into the realm of regularization within the MIL model, presenting a novel approach in the form of a Progressive Dropout Layer (PDL). We aim to not only address overfitting but also empower the MIL model in uncovering intricate and impactful feature representations. The proposed method was orthogonal to existing MIL methods and could be easily integrated into them to boost performance. Our extensive evaluation across a range of MIL benchmark datasets demonstrated that the incorporation of the PDL into multiple MIL methods not only elevated their classification performance but also augmented their potential for weakly-supervised feature localizations.
Authors: Wenjing Xie, Tao Hu, Neiwen Ling, Guoliang Xing, Chun Jason Xue, Nan Guan
Abstract: Fusing Radar and Lidar sensor data can fully utilize their complementary advantages and provide more accurate reconstruction of the surrounding for autonomous driving systems. Surround Radar/Lidar can provide 360-degree view sampling with the minimal cost, which are promising sensing hardware solutions for autonomous driving systems. However, due to the intrinsic physical constraints, the rotating speed of surround Radar, and thus the frequency to generate Radar data frames, is much lower than surround Lidar. Existing Radar/Lidar fusion methods have to work at the low frequency of surround Radar, which cannot meet the high responsiveness requirement of autonomous driving systems.This paper develops techniques to fuse surround Radar/Lidar with working frequency only limited by the faster surround Lidar instead of the slower surround Radar, based on the state-of-the-art object detection model MVDNet. The basic idea of our approach is simple: we let MVDNet work with temporally unaligned data from Radar/Lidar, so that fusion can take place at any time when a new Lidar data frame arrives, instead of waiting for the slow Radar data frame. However, directly applying MVDNet to temporally unaligned Radar/Lidar data greatly degrades its object detection accuracy. The key information revealed in this paper is that we can achieve high output frequency with little accuracy loss by enhancing the training procedure to explore the temporal redundancy in MVDNet so that it can tolerate the temporal unalignment of input data. We explore several different ways of training enhancement and compare them quantitatively with experiments.
Authors: Andreas Haghofer, Eda Parlak, Alexander Bartel, Taryn A. Donovan, Charles-Antoine Assenmacher, Pompei Bolfa, Michael J. Dark, Andrea Fuchs-Baumgartinger, Andrea Klang, Kathrin J\"ager, Robert Klopfleisch, Sophie Merz, Barbara Richter, F. Yvonne Schulman, Hannah Janout, Jonathan Ganz, Josef Scharinger, Marc Aubreville, Stephan M. Winkler, Matti Kiupel, Christof A. Bertram
Abstract: Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurements of nuclear characteristics (morphometry) can improve reproducibility, but manual methods are time consuming. The aim of this study was to explore the limitations of estimates and develop alternative morphometric solutions for canine cutaneous mast cell tumors (ccMCT). We assessed the following nuclear evaluation methods for measurement accuracy, reproducibility, and prognostic utility: 1) anisokaryosis (karyomegaly) estimates by 11 pathologists; 2) gold standard manual morphometry of at least 100 nuclei; 3) practicable manual morphometry with stratified sampling of 12 nuclei by 9 pathologists; and 4) automated morphometry using a deep learning-based segmentation algorithm. The study dataset comprised 96 ccMCT with available outcome information. The study dataset comprised 96 ccMCT with available outcome information. Inter-rater reproducibility of karyomegaly estimates was low ($\kappa$ = 0.226), while it was good (ICC = 0.654) for practicable morphometry of the standard deviation (SD) of nuclear size. As compared to gold standard manual morphometry (AUC = 0.839, 95% CI: 0.701 - 0.977), the prognostic value (tumor-specific survival) of SDs of nuclear area for practicable manual morphometry (12 nuclei) and automated morphometry were high with an area under the ROC curve (AUC) of 0.868 (95% CI: 0.737 - 0.991) and 0.943 (95% CI: 0.889 - 0.996), respectively. This study supports the use of manual morphometry with stratified sampling of 12 nuclei and algorithmic morphometry to overcome the poor reproducibility of estimates.
Authors: Shuai Yang, Yukang Chen, Luozhou Wang, Shu Liu, Yingcong Chen
Abstract: Denoising Diffusion Probabilistic Models (DDPMs) have garnered popularity for data generation across various domains. However, a significant bottleneck is the necessity for whole-network computation during every step of the generative process, leading to high computational overheads. This paper presents a novel framework, Denoising Diffusion Step-aware Models (DDSM), to address this challenge. Unlike conventional approaches, DDSM employs a spectrum of neural networks whose sizes are adapted according to the importance of each generative step, as determined through evolutionary search. This step-wise network variation effectively circumvents redundant computational efforts, particularly in less critical steps, thereby enhancing the efficiency of the diffusion model. Furthermore, the step-aware design can be seamlessly integrated with other efficiency-geared diffusion models such as DDIMs and latent diffusion, thus broadening the scope of computational savings. Empirical evaluations demonstrate that DDSM achieves computational savings of 49% for CIFAR-10, 61% for CelebA-HQ, 59% for LSUN-bedroom, 71% for AFHQ, and 76% for ImageNet, all without compromising the generation quality.
Authors: Bohan Zeng, Shanglin Li, Yutang Feng, Ling Yang, Hong Li, Sicheng Gao, Jiaming Liu, Conghui He, Wentao Zhang, Jianzhuang Liu, Baochang Zhang, Shuicheng Yan
Abstract: Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to supervise 3D object generation. These methods enable the synthesis of detailed and photorealistic textured objects. However, the appearance of 3D objects produced by these text-to-3D models is unpredictable, and it is hard for the single-image-to-3D methods to deal with complex images, thus posing a challenge in generating appearance-controllable 3D objects. To achieve controllable complex 3D object synthesis, we propose IPDreamer, a novel approach that incorporates image prompt adaption to extract detailed and comprehensive appearance features from complex images, which are then utilized for 3D object generation. Our results demonstrate that IPDreamer effectively generates high-quality 3D objects that are consistent with both the provided text and the appearance of complex image prompts, demonstrating its promising capability in appearance-controllable 3D object generation. Our code is available at https://github.com/zengbohan0217/IPDreamer.
Authors: Liao Pan, Yang Feng, Wu Di, Liu Bo, Zhang Xingle
Abstract: Decoder-only models, such as GPT, have demonstrated superior performance in many areas compared to traditional encoder-decoder structure transformer models. Over the years, end-to-end models based on the traditional transformer structure, like MOTR, have achieved remarkable performance in multi-object tracking. However, the significant computational resource consumption of these models leads to less friendly inference speeds and training times. To address these issues, this paper attempts to construct a lightweight Decoder-only model: DecoderTracker for end-to-end multi-object tracking. Specifically, drawing on some real-time detection models, we have developed an image feature extraction network which can efficiently extract features from images to replace the encoder structure. In addition to minor innovations in the network, we analyze the potential reasons for the slow training of MOTR-like models and propose an effective training strategy to mitigate the issue of prolonged training times. On the DanceTrack dataset, without any bells and whistles, DecoderTracker's tracking performance slightly surpasses that of MOTR, with approximately twice the inference speed. Furthermore, DecoderTracker requires significantly less training time compared to MOTR.
Authors: Soham Chitnis, Kiran Mantripragada, Faisal Z. Qureshi
Abstract: The hyperspectral pixel unmixing aims to find the underlying materials (endmembers) and their proportions (abundances) in pixels of a hyperspectral image. This work extends the Latent Dirichlet Variational Autoencoder (LDVAE) pixel unmixing scheme by taking into account local spatial context while performing pixel unmixing. The proposed method uses an isotropic convolutional neural network with spatial attention to encode pixels as a dirichlet distribution over endmembers. We have evaluated our model on Samson, Hydice Urban, Cuprite, and OnTech-HSI-Syn-21 datasets. Our model also leverages the transfer learning paradigm for Cuprite Dataset, where we train the model on synthetic data and evaluate it on the real-world data. The results suggest that incorporating spatial context improves both endmember extraction and abundance estimation.
Authors: Evelyn Mannix, Howard Bondell
Abstract: This paper describes PAWS-VMK, a prototypical deep learning approach that obtains state-of-the-art results for image classification tasks in both a semi-supervised learning (SSL) and out-of-distribution (OOD) detection context. We consider developments in the fields of SSL, OOD detection, and computer vision foundation models to introduce a number of innovations that connect the key ideas within these works to create PAWS-VMK. These innovations include (1) parametric von Mises-Fisher Stochastic Neighbour Embedding (vMF-SNE) to initialise a projection head for SSL using the high-quality embeddings of the foundation model; (2) the PAWS-MixMatch loss, that creates more compact embeddings and obtains higher accuracy in comparison to the consistency loss used in PAWS and (3) simple $k$-Means prototype selection (SKMPS), a simple technique that obtains competitive performance with more complex unsupervised label selection approaches. PAWS-VMK sets new benchmarks in semi-supervised learning for CIFAR-10 (99.2%) and CIFAR-100 (89.8%) with four labelled instances per class, and Food-101 (90.1%) with two labelled instances per class. We also observe that PAWS-VMK can efficiently detect OOD samples in a manner that is competitive with specialised methods specifically designed for this purpose, achieving 93.1/98.0 and 95.2/96.3 on the CIFAR-10 and CIFAR-100 OpenOOD benchmarks.
Authors: Jiaming Zhou, Hanjun Li, Kun-Yu Lin, Junwei Liang
Abstract: Developing end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding. Due to the unaffordable cost of end-to-end training on the whole long videos, existing works generally train models on short clips trimmed from long videos. However, this ``trimming-then-training'' practice requires action interval annotations for clip-level supervision, i.e., knowing which actions are trimmed into the clips. Unfortunately, collecting such annotations is very expensive and prevents model training at scale. To this end, this work aims to build a weakly supervised end-to-end framework for training recognition models on long videos, with only video-level action category labels. Without knowing the precise temporal locations of actions in long videos, our proposed weakly supervised framework, namely AdaptFocus, estimates where and how likely the actions will occur to adaptively focus on informative action clips for end-to-end training. The effectiveness of the proposed AdaptFocus framework is demonstrated on three long-video datasets. Furthermore, for downstream long-video tasks, our AdaptFocus framework provides a weakly supervised feature extraction pipeline for extracting more robust long-video features, such that the state-of-the-art methods on downstream tasks are significantly advanced. We will release the code and models.
Authors: Yunfei Fan, Tianyu Zhao, Guidong Wang
Abstract: Accuracy and computational efficiency are the most important metrics to Visual Inertial Navigation System (VINS). The existing VINS algorithms with either high accuracy or low computational complexity, are difficult to provide the high precision localization in resource-constrained devices. To this end, we propose a novel filter-based VINS framework named SchurVINS, which could guarantee both high accuracy by building a complete residual model and low computational complexity with Schur complement. Technically, we first formulate the full residual model where Gradient, Hessian and observation covariance are explicitly modeled. Then Schur complement is employed to decompose the full model into ego-motion residual model and landmark residual model. Finally, Extended Kalman Filter (EKF) update is implemented in these two models with high efficiency. Experiments on EuRoC and TUM-VI datasets show that our method notably outperforms state-of-the-art (SOTA) methods in both accuracy and computational complexity. The experimental code of SchurVINS is available at https://github.com/bytedance/SchurVINS.
Authors: Rosco Hunter, {\L}ukasz Dudziak, Mohamed S. Abdelfattah, Abhinav Mehrotra, Sourav Bhattacharya, Hongkai Wen
Abstract: Text-to-image diffusion models have demonstrated unprecedented capabilities for flexible and realistic image synthesis. Nevertheless, these models rely on a time-consuming sampling procedure, which has motivated attempts to reduce their latency. When improving efficiency, researchers often use the original diffusion model to train an additional network designed specifically for fast image generation. In contrast, our approach seeks to reduce latency directly, without any retraining, fine-tuning, or knowledge distillation. In particular, we find the repeated calculation of attention maps to be costly yet redundant, and instead suggest reusing them during sampling. Our specific reuse strategies are based on ODE theory, which implies that the later a map is reused, the smaller the distortion in the final image. We empirically compare these reuse strategies with few-step sampling procedures of comparable latency, finding that reuse generates images that are closer to those produced by the original high-latency diffusion model.
Authors: Yuyang Wang, Yizhi Hao, Amando Xu Cong
Abstract: In the realm of digital media, the advent of AI-generated synthetic images has introduced significant challenges in distinguishing between real and fabricated visual content. These images, often indistinguishable from authentic ones, pose a threat to the credibility of digital media, with potential implications for disinformation and fraud. Our research addresses this challenge by employing machine learning techniques to discern between AI-generated and genuine images. Central to our approach is the CIFAKE dataset, a comprehensive collection of images labeled as "Real" and "Fake". We refine and adapt advanced deep learning architectures like ResNet, VGGNet, and DenseNet, utilizing transfer learning to enhance their precision in identifying synthetic images. We also compare these with a baseline model comprising a vanilla Support Vector Machine (SVM) and a custom Convolutional Neural Network (CNN). The experimental results were significant, demonstrating that our optimized deep learning models outperform traditional methods, with DenseNet achieving an accuracy of 97.74%. Our application study contributes by applying and optimizing these advanced models for synthetic image detection, conducting a comparative analysis using various metrics, and demonstrating their superior capability in identifying AI-generated images over traditional machine learning techniques. This research not only advances the field of digital media integrity but also sets a foundation for future explorations into the ethical and technical dimensions of AI-generated content in digital media.
Authors: Mathis Petrovich, Or Litany, Umar Iqbal, Michael J. Black, G\"ul Varol, Xue Bin Peng, Davis Rempe
Abstract: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts. Our code and models are publicly available at https://mathis.petrovich.fr/stmc.
Authors: Dat Nguyen, Nesryne Mejri, Inder Pal Singh, Polina Kuleshova, Marcella Astrid, Anis Kacem, Enjie Ghorbel, Djamila Aouada
Abstract: This paper introduces a novel approach for high-quality deepfake detection called Localized Artifact Attention Network (LAA-Net). Existing methods for high-quality deepfake detection are mainly based on a supervised binary classifier coupled with an implicit attention mechanism. As a result, they do not generalize well to unseen manipulations. To handle this issue, two main contributions are made. First, an explicit attention mechanism within a multi-task learning framework is proposed. By combining heatmap-based and self-consistency attention strategies, LAA-Net is forced to focus on a few small artifact-prone vulnerable regions. Second, an Enhanced Feature Pyramid Network (E-FPN) is proposed as a simple and effective mechanism for spreading discriminative low-level features into the final feature output, with the advantage of limiting redundancy. Experiments performed on several benchmarks show the superiority of our approach in terms of Area Under the Curve (AUC) and Average Precision (AP). The code is available at https://github.com/10Ring/LAA-Net.
Authors: Zhennan Wu, Yang Li, Han Yan, Taizhang Shang, Weixuan Sun, Senbo Wang, Ruikai Cui, Weizhe Liu, Hiroyuki Sato, Hongdong Li, Pan Ji
Abstract: We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene meshes. Through per-block fitting, all training blocks are converted into the hybrid neural fields: with a tri-plane containing the geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the signed distance values. A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed. Diffusion applied to the latent representations allows for high-quality and diverse 3D scene generation. To expand a scene during generation, one needs only to append empty blocks to overlap with the current scene and extrapolate existing latent tri-planes to populate new blocks. The extrapolation is done by conditioning the generation process with the feature samples from the overlapping tri-planes during the denoising iterations. Latent tri-plane extrapolation produces semantically and geometrically meaningful transitions that harmoniously blend with the existing scene. A 2D layout conditioning mechanism is used to control the placement and arrangement of scene elements. Experimental results indicate that BlockFusion is capable of generating diverse, geometrically consistent and unbounded large 3D scenes with unprecedented high-quality shapes in both indoor and outdoor scenarios.
Authors: Yura Perugachi-Diaz, Arwin Gansekoele, Sandjai Bhulai
Abstract: Neural image compression has made a great deal of progress. State-of-the-art models are based on variational autoencoders and are outperforming classical models. Neural compression models learn to encode an image into a quantized latent representation that can be efficiently sent to the decoder, which decodes the quantized latent into a reconstructed image. While these models have proven successful in practice, they lead to sub-optimal results due to imperfect optimization and limitations in the encoder and decoder capacity. Recent work shows how to use stochastic Gumbel annealing (SGA) to refine the latents of pre-trained neural image compression models. We extend this idea by introducing SGA+, which contains three different methods that build upon SGA. We show how our method improves the overall compression performance in terms of the R-D trade-off, compared to its predecessors. Additionally, we show how refinement of the latents with our best-performing method improves the compression performance on both the Tecnick and CLIC dataset. Our method is deployed for a pre-trained hyperprior and for a more flexible model. Further, we give a detailed analysis of our proposed methods and show that they are less sensitive to hyperparameter choices. Finally, we show how each method can be extended to three- instead of two-class rounding.
Authors: Xinhai Hou, Cheng Jiang, Akhil Kondepudi, Yiwei Lyu, Asadur Chowdury, Honglak Lee, Todd C. Hollon
Abstract: Whole slide imaging is fundamental to biomedical microscopy and computational pathology. Previously, learning representations for gigapixel-sized whole slide images (WSIs) has relied on multiple instance learning with weak labels, which do not annotate the diverse morphologic features and spatial heterogeneity of WSIs. A high-quality self-supervised learning method for WSIs would provide transferable visual representations for downstream computational pathology tasks, without the need for dense annotations. We present Slide Pre-trained Transformers (SPT) for gigapixel-scale self-supervision of WSIs. Treating WSI patches as tokens, SPT combines data transformation strategies from language and vision modeling into a general and unified framework to generate views of WSIs for self-supervised pretraining. SPT leverages the inherent regional heterogeneity, histologic feature variability, and information redundancy within WSIs to learn high-quality whole slide representations. We benchmark SPT visual representations on five diagnostic tasks across three biomedical microscopy datasets. SPT significantly outperforms baselines for histopathologic diagnosis, cancer subtyping, and genetic mutation prediction. Finally, we demonstrate that SPT consistently improves whole slide representations when using off-the-shelf, in-domain, and foundational patch encoders for whole slide multiple instance learning.
Authors: Abdullah Hamdi, Luke Melas-Kyriazi, Jinjie Mai, Guocheng Qian, Ruoshi Liu, Carl Vondrick, Bernard Ghanem, Andrea Vedaldi
Abstract: Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However, it may require a large number of Gaussians, which creates a substantial memory footprint. This paper introduces GES (Generalized Exponential Splatting), a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes, requiring far fewer particles to represent a scene and thus significantly outperforming Gaussian Splatting methods in efficiency with a plug-and-play replacement ability for Gaussian-based utilities. GES is validated theoretically and empirically in both principled 1D setup and realistic 3D scenes. It is shown to represent signals with sharp edges more accurately, which are typically challenging for Gaussians due to their inherent low-pass characteristics. Our empirical analysis demonstrates that GEF outperforms Gaussians in fitting natural-occurring signals (e.g. squares, triangles, and parabolic signals), thereby reducing the need for extensive splitting operations that increase the memory footprint of Gaussian Splatting. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%. The code is available on the project website https://abdullahamdi.com/ges .
Authors: Wenxuan Wang, Yisi Zhang, Xingjian He, Yichen Yan, Zijia Zhao, Xinlong Wang, Jing Liu
Abstract: Visual grounding (VG) aims at locating the foreground entities that match the given natural language expressions. Previous datasets and methods for classic VG task mainly rely on the prior assumption that the given expression must literally refer to the target object, which greatly impedes the practical deployment of agents in real-world scenarios. Since users usually prefer to provide intention-based expression for the desired object instead of covering all the details, it is necessary for the agents to interpret the intention-driven instructions. Thus, in this work, we take a step further to the intention-driven visual-language (V-L) understanding. To promote classic VG towards human intention interpretation, we propose a new intention-driven visual grounding (IVG) task and build a large-scale IVG dataset termed IntentionVG with free-form intention expressions. Considering that practical agents need to move and find specific targets among various scenarios to realize the grounding task, our IVG task and IntentionVG dataset have taken the crucial properties of both multi-scenario perception and egocentric view into consideration. Besides, various types of models are set up as the baselines to realize our IVG task. Extensive experiments on our IntentionVG dataset and baselines demonstrate the necessity and efficacy of our method for the V-L field. To foster future research in this direction, our newly built dataset and baselines will be publicly available at https://github.com/Rubics-Xuan/IVG.
Authors: Sen Li, Ruochen Wang, Cho-Jui Hsieh, Minhao Cheng, Tianyi Zhou
Abstract: Existing text-to-image models still struggle to generate images of multiple objects, especially in handling their spatial positions, relative sizes, overlapping, and attribute bindings. To efficiently address these challenges, we develop a training-free Multimodal-LLM agent (MuLan), as a human painter, that can progressively generate multi-object with intricate planning and feedback control. MuLan harnesses a large language model (LLM) to decompose a prompt to a sequence of sub-tasks, each generating only one object by stable diffusion, conditioned on previously generated objects. Unlike existing LLM-grounded methods, MuLan only produces a high-level plan at the beginning while the exact size and location of each object are determined upon each sub-task by an LLM and attention guidance. Moreover, MuLan adopts a vision-language model (VLM) to provide feedback to the image generated in each sub-task and control the diffusion model to re-generate the image if it violates the original prompt. Hence, each model in every step of MuLan only needs to address an easy sub-task it is specialized for. The multi-step process also allows human users to monitor the generation process and make preferred changes at any intermediate step via text prompts, thereby improving the human-AI collaboration experience. We collect 200 prompts containing multi-objects with spatial relationships and attribute bindings from different benchmarks to evaluate MuLan. The results demonstrate the superiority of MuLan in generating multiple objects over baselines and its creativity when collaborating with human users. The code is available at https://github.com/measure-infinity/mulan-code.
Authors: Xinchen Zhang, Ling Yang, Yaqi Cai, Zhaochen Yu, Kai-Ni Wang, Jiake Xie, Ye Tian, Minkai Xu, Yong Tang, Yujiu Yang, Bin Cui
Abstract: Diffusion models have achieved remarkable advancements in text-to-image generation. However, existing models still have many difficulties when faced with multiple-object compositional generation. In this paper, we propose RealCompo, a new training-free and transferred-friendly text-to-image generation framework, which aims to leverage the respective advantages of text-to-image models and spatial-aware image diffusion models (e.g., layout, keypoints and segmentation maps) to enhance both realism and compositionality of the generated images. An intuitive and novel balancer is proposed to dynamically balance the strengths of the two models in denoising process, allowing plug-and-play use of any model without extra training. Extensive experiments show that our RealCompo consistently outperforms state-of-the-art text-to-image models and spatial-aware image diffusion models in multiple-object compositional generation while keeping satisfactory realism and compositionality of the generated images. Notably, our RealCompo can be seamlessly extended with a wide range of spatial-aware image diffusion models and stylized diffusion models. Our code is available at: https://github.com/YangLing0818/RealCompo
Authors: Lixian Zhang, Runmin Dong, Shuai Yuan, Jinxiao Zhang, Mengxuan Chen, Juepeng Zheng, Haohuan Fu
Abstract: Nighttime light (NTL) remote sensing observation serves as a unique proxy for quantitatively assessing progress toward meeting a series of Sustainable Development Goals (SDGs), such as poverty estimation, urban sustainable development, and carbon emission. However, existing NTL observations often suffer from pervasive degradation and inconsistency, limiting their utility for computing the indicators defined by the SDGs. In this study, we propose a novel approach to reconstruct high-resolution NTL images using multi-modal remote sensing data. To support this research endeavor, we introduce DeepLightMD, a comprehensive dataset comprising data from five heterogeneous sensors, offering fine spatial resolution and rich spectral information at a national scale. Additionally, we present DeepLightSR, a calibration-aware method for building bridges between spatially heterogeneous modality data in the multi-modality super-resolution. DeepLightSR integrates calibration-aware alignment, an auxiliary-to-main multi-modality fusion, and an auxiliary-embedded refinement to effectively address spatial heterogeneity, fuse diversely representative features, and enhance performance in $8\times$ super-resolution (SR) tasks. Extensive experiments demonstrate the superiority of DeepLightSR over 8 competing methods, as evidenced by improvements in PSNR (2.01 dB $ \sim $ 13.25 dB) and PIQE (0.49 $ \sim $ 9.32). Our findings underscore the practical significance of our proposed dataset and model in reconstructing high-resolution NTL data, supporting efficiently and quantitatively assessing the SDG progress.
Authors: Weilin Wan, Weizhong Zhang, Quan Zhou, Fan Yi, Cheng Jin
Abstract: Out-of-distribution detection (OOD) is a crucial technique for deploying machine learning models in the real world to handle the unseen scenarios. In this paper, we first propose a simple yet effective Neural Activation Prior (NAP) for OOD detection. Our neural activation prior is based on a key observation that, for a channel before the global pooling layer of a fully trained neural network, the probability of a few neurons being activated with a large response by an in-distribution (ID) sample is significantly higher than that by an OOD sample. An intuitive explanation is that for a model fully trained on ID dataset, each channel would play a role in detecting a certain pattern in the ID dataset, and a few neurons can be activated with a large response when the pattern is detected in an input sample. Then, a new scoring function based on this prior is proposed to highlight the role of these strongly activated neurons in OOD detection. Our approach is plug-and-play and does not lead to any performance degradation on ID data classification and requires no extra training or statistics from training or external datasets. Notice that previous methods primarily rely on post-global-pooling features of the neural networks, while the within-channel distribution information we leverage would be discarded by the global pooling operator. Consequently, our method is orthogonal to existing approaches and can be effectively combined with them in various applications. Experimental results show that our method achieves the state-of-the-art performance on CIFAR benchmark and ImageNet dataset, which demonstrates the power of the proposed prior. Finally, we extend our method to Transformers and the experimental findings indicate that NAP can also significantly enhance the performance of OOD detection on Transformers, thereby demonstrating the broad applicability of this prior knowledge.
Authors: Kun-Yu Lin, Henghui Ding, Jiaming Zhou, Yu-Ming Tang, Yi-Xing Peng, Zhilin Zhao, Chen Change Loy, Wei-Shi Zheng
Abstract: Building upon the impressive success of CLIP (Contrastive Language-Image Pretraining), recent pioneer works have proposed to adapt the powerful CLIP to video data, leading to efficient and effective video learners for open-vocabulary action recognition. Inspired by that humans perform actions in diverse environments, our work delves into an intriguing question: Can CLIP-based video learners effectively generalize to video domains they have not encountered during training? To answer this, we establish a CROSS-domain Open-Vocabulary Action recognition benchmark named XOV-Action, and conduct a comprehensive evaluation of five state-of-the-art CLIP-based video learners under various types of domain gaps. The evaluation demonstrates that previous methods exhibit limited action recognition performance in unseen video domains, revealing potential challenges of the cross-domain open-vocabulary action recognition task. In this paper, we focus on one critical challenge of the task, namely scene bias, and accordingly contribute a novel scene-aware video-text alignment method. Our key idea is to distinguish video representations apart from scene-encoded text representations, aiming to learn scene-agnostic video representations for recognizing actions across domains. Extensive experiments demonstrate the effectiveness of our method. The benchmark and code will be available at https://github.com/KunyuLin/XOV-Action/.
Authors: Evelyn Mannix, Howard Bondell
Abstract: Interpretable computer vision models are able to explain their reasoning through comparing the distances between the image patch embeddings and prototypes within a latent space. However, many of these approaches introduce additional complexity, can require multiple training steps and often have a performance cost in comparison to black-box approaches. In this work, we introduce Component Features (ComFe), a novel interpretable-by-design image classification approach that is highly scalable and can obtain better accuracy and robustness in comparison to non-interpretable methods. Inspired by recent developments in computer vision foundation models, ComFe uses a transformer-decoder head and a hierarchical mixture-modelling approach with a foundation model backbone to obtain higher accuracy compared to previous interpretable models across a range of fine-grained vision benchmarks, without the need to individually tune hyper-parameters for each dataset. With only global image labels and no segmentation or part annotations, ComFe can identify consistent component features within an image and determine which of these features are informative in making a prediction.
Authors: Sijia Chen, En Yu, Jinyang Li, Wenbing Tao
Abstract: Multiple Object Tracking (MOT) is a critical area within computer vision, with a broad spectrum of practical implementations. Current research has primarily focused on the development of tracking algorithms and enhancement of post-processing techniques. Yet, there has been a lack of thorough examination concerning the nature of tracking data it self. In this study, we pioneer an exploration into the distribution patterns of tracking data and identify a pronounced long-tail distribution issue within existing MOT datasets. We note a significant imbalance in the distribution of trajectory lengths across different pedestrians, a phenomenon we refer to as ``pedestrians trajectory long-tail distribution''. Addressing this challenge, we introduce a bespoke strategy designed to mitigate the effects of this skewed distribution. Specifically, we propose two data augmentation strategies, including Stationary Camera View Data Augmentation (SVA) and Dynamic Camera View Data Augmentation (DVA) , designed for viewpoint states and the Group Softmax (GS) module for Re-ID. SVA is to backtrack and predict the pedestrian trajectory of tail classes, and DVA is to use diffusion model to change the background of the scene. GS divides the pedestrians into unrelated groups and performs softmax operation on each group individually. Our proposed strategies can be integrated into numerous existing tracking systems, and extensive experimentation validates the efficacy of our method in reducing the influence of long-tail distribution on multi-object tracking performance. The code is available at https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT.
URLs: https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT.
Authors: Jiaxin Guo, Jiangliu Wang, Zhaoshuo Li, Tongyu Jia, Qi Dou, Yun-Hui Liu
Abstract: Soft tissue tracking is crucial for computer-assisted interventions. Existing approaches mainly rely on extracting discriminative features from the template and videos to recover corresponding matches. However, it is difficult to adopt these techniques in surgical scenes, where tissues are changing in shape and appearance throughout the surgery. To address this problem, we exploit optical flow to naturally capture the pixel-wise tissue deformations and adaptively correct the tracked template. Specifically, we first implement an inter-frame matching mechanism to extract a coarse region of interest based on optical flow from consecutive frames. To accommodate appearance change and alleviate drift, we then propose an adaptive-template matching method, which updates the tracked template based on the reliability of the estimates. Our approach, Ada-Tracker, enjoys both short-term dynamics modeling by capturing local deformations and long-term dynamics modeling by introducing global temporal compensation. We evaluate our approach on the public SurgT benchmark, which is generated from Hamlyn, SCARED, and Kidney boundary datasets. The experimental results show that Ada-Tracker achieves superior accuracy and performs more robustly against prior works. Code is available at https://github.com/wrld/Ada-Tracker.
Authors: Jinlu Zhang, Yiyi Zhou, Qiancheng Zheng, Xiaoxiong Du, Gen Luo, Jun Peng, Xiaoshuai Sun, Rongrong Ji
Abstract: Text-to-3D-aware face (T3D Face) generation and manipulation is an emerging research hot spot in machine learning, which still suffers from low efficiency and poor quality. In this paper, we propose an End-to-End Efficient and Effective network for fast and accurate T3D face generation and manipulation, termed $E^3$-FaceNet. Different from existing complex generation paradigms, $E^3$-FaceNet resorts to a direct mapping from text instructions to 3D-aware visual space. We introduce a novel Style Code Enhancer to enhance cross-modal semantic alignment, alongside an innovative Geometric Regularization objective to maintain consistency across multi-view generations. Extensive experiments on three benchmark datasets demonstrate that $E^3$-FaceNet can not only achieve picture-like 3D face generation and manipulation, but also improve inference speed by orders of magnitudes. For instance, compared with Latent3D, $E^3$-FaceNet speeds up the five-view generations by almost 470 times, while still exceeding in generation quality. Our code is released at https://github.com/Aria-Zhangjl/E3-FaceNet.
Authors: Qing Lin, Jingfeng Zhang, Yew Soon Ong, Mengmi Zhang
Abstract: Despite the rapid progress in image generation, emotional image editing remains under-explored. The semantics, context, and structure of an image can evoke emotional responses, making emotional image editing techniques valuable for various real-world applications, including treatment of psychological disorders, commercialization of products, and artistic design. For the first time, we present a novel challenge of emotion-evoked image generation, aiming to synthesize images that evoke target emotions while retaining the semantics and structures of the original scenes. To address this challenge, we propose a diffusion model capable of effectively understanding and editing source images to convey desired emotions and sentiments. Moreover, due to the lack of emotion editing datasets, we provide a unique dataset consisting of 340,000 pairs of images and their emotion annotations. Furthermore, we conduct human psychophysics experiments and introduce four new evaluation metrics to systematically benchmark all the methods. Experimental results demonstrate that our method surpasses all competitive baselines. Our diffusion model is capable of identifying emotional cues from original images, editing images that elicit desired emotions, and meanwhile, preserving the semantic structure of the original images. All code, model, and dataset will be made public.
Authors: Nan Jiang, Zhiyuan Zhang, Hongjie Li, Xiaoxuan Ma, Zan Wang, Yixin Chen, Tengyu Liu, Yixin Zhu, Siyuan Huang
Abstract: Confronting the challenges of data scarcity and advanced motion synthesis in human-scene interaction modeling, we introduce the TRUMANS dataset alongside a novel HSI motion synthesis method. TRUMANS stands as the most comprehensive motion-captured HSI dataset currently available, encompassing over 15 hours of human interactions across 100 indoor scenes. It intricately captures whole-body human motions and part-level object dynamics, focusing on the realism of contact. This dataset is further scaled up by transforming physical environments into exact virtual models and applying extensive augmentations to appearance and motion for both humans and objects while maintaining interaction fidelity. Utilizing TRUMANS, we devise a diffusion-based autoregressive model that efficiently generates HSI sequences of any length, taking into account both scene context and intended actions. In experiments, our approach shows remarkable zero-shot generalizability on a range of 3D scene datasets (e.g., PROX, Replica, ScanNet, ScanNet++), producing motions that closely mimic original motion-captured sequences, as confirmed by quantitative experiments and human studies.
Authors: Soroush Seifi, Daniel Olmeda Reino, Fabien Despinoy, Rahaf Aljundi
Abstract: Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent works attempt to achieve zeroshot semantic segmentation while requiring either large-scale training or additional image/pixel level annotations. In this work, we generate free annotations for any semantic segmentation dataset using existing foundation models. We use CLIP to detect objects and SAM to generate high quality object masks. Next, we build a lightweight module on top of a self-supervised vision encoder, DinoV2, to align the patch features with a pretrained text encoder for zeroshot semantic segmentation. Our approach can bring language-based semantics to any pretrained vision encoder with minimal training. Our module is lightweight, uses foundation models as the sole source of supervision and shows impressive generalization capability from little training data with no annotation.
Authors: Haiwen Huang, Songyou Peng, Dan Zhang, Andreas Geiger
Abstract: Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names is often overlooked in existing datasets. In this paper, we address this underexplored problem by presenting a framework for "renovating" names in open-vocabulary segmentation benchmarks (RENOVATE). Our framework features a renaming model that enhances the quality of names for each visual segment. Through experiments, we demonstrate that our renovated names help train stronger open-vocabulary models with up to 15% relative improvement and significantly enhance training efficiency with improved data quality. We also show that our renovated names improve evaluation by better measuring misclassification and enabling fine-grained model analysis. We will provide our code and relabelings for several popular segmentation datasets (MS COCO, ADE20K, Cityscapes) to the research community.
Authors: Yihong Luo, Xiaolong Chen, Xinghua Qu, Jing Tang
Abstract: We introduce YOSO, a novel generative model designed for rapid, scalable, and high-fidelity one-step image synthesis. YOSO integrates the diffusion process with GANs to achieve the best of two worlds. Specifically, we smooth the distribution by the denoising generator itself, performing self-cooperative learning. We show that our method can serve as a one-step generation model training from scratch with competitive performance. Moreover, we show that our method can be extended to finetune pre-trained text-to-image diffusion for high-quality one-step text-to-image synthesis even with LoRA fine-tuning. In particular, we provide the first diffusion transformer that can generate images in one step trained on 512 resolution, with the capability of adapting to 1024 resolution without extra explicit training. Our code is provided at https://github.com/Luo-Yihong/YOSO
Authors: Otto Seiskari, Jerry Ylilammi, Valtteri Kaatrasalo, Pekka Rantalankila, Matias Turkulainen, Juho Kannala, Arno Solin
Abstract: High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with handheld cameras. We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data suffering from motion blur and rolling shutter distortion. Our approach is based on detailed modelling of the physical image formation process and utilizes velocities estimated using visual-inertial odometry (VIO). Camera poses are considered non-static during the exposure time of a single image frame and camera poses are further optimized in the reconstruction process. We formulate a differentiable rendering pipeline that leverages screen space approximation to efficiently incorporate rolling-shutter and motion blur effects into the 3DGS framework. Our results with both synthetic and real data demonstrate superior performance in mitigating camera motion over existing methods, thereby advancing 3DGS in naturalistic settings.
Authors: Lauren Okamoto, Paritosh Parmar
Abstract: Action quality assessment (AQA) applies computer vision to quantitatively assess the performance or execution of a human action. Current AQA approaches are end-to-end neural models, which lack transparency and tend to be biased because they are trained on subjective human judgements as ground-truth. To address these issues, we introduce a neuro-symbolic paradigm for AQA, which uses neural networks to abstract interpretable symbols from video data and makes quality assessments by applying rules to those symbols. We take diving as the case study. We found that domain experts prefer our system and find it more informative than purely neural approaches to AQA in diving. Our system also achieves state-of-the-art action recognition and temporal segmentation, and automatically generates a detailed report that breaks the dive down into its elements and provides objective scoring with visual evidence. As verified by a group of domain experts, this report may be used to assist judges in scoring, help train judges, and provide feedback to divers. Annotated training data and code: https://github.com/laurenok24/NSAQA.
Authors: Tom Burgert, Beg\"um Demir
Abstract: The application of data augmentation for deep learning (DL) methods plays an important role in achieving state-of-the-art results in supervised, semi-supervised, and self-supervised image classification. In particular, channel transformations (e.g., solarize, grayscale, brightness adjustments) are integrated into data augmentation pipelines for remote sensing (RS) image classification tasks. However, contradicting beliefs exist about their proper applications to RS images. A common point of critique is that the application of channel augmentation techniques may lead to physically inconsistent spectral data (i.e., pixel signatures). To shed light on the open debate, we propose an approach to estimate whether a channel augmentation technique affects the physical information of RS images. To this end, the proposed approach estimates a score that measures the alignment of a pixel signature within a time series that can be naturally subject to deviations caused by factors such as acquisition conditions or phenological states of vegetation. We compare the scores associated with original and augmented pixel signatures to evaluate the physical consistency. Experimental results on a multi-label image classification task show that channel augmentations yielding a score that exceeds the expected deviation of original pixel signatures can not improve the performance of a baseline model trained without augmentation.
Authors: Guang Lin, Zerui Tao, Jianhai Zhang, Toshihisa Tanaka, Qibin Zhao
Abstract: Diffusion models (DMs) based adversarial purification (AP) has shown to be the most powerful alternative to adversarial training (AT). However, these methods neglect the fact that pre-trained diffusion models themselves are not robust to adversarial attacks as well. Additionally, the diffusion process can easily destroy semantic information and generate a high quality image but totally different from the original input image after the reverse process, leading to degraded standard accuracy. To overcome these issues, a natural idea is to harness adversarial training strategy to retrain or fine-tune the pre-trained diffusion model, which is computationally prohibitive. We propose a novel robust reverse process with adversarial guidance, which is independent of given pre-trained DMs and avoids retraining or fine-tuning the DMs. This robust guidance can not only ensure to generate purified examples retaining more semantic content but also mitigate the accuracy-robustness trade-off of DMs for the first time, which also provides DM-based AP an efficient adaptive ability to new attacks. Extensive experiments are conducted on CIFAR-10, CIFAR-100 and ImageNet to demonstrate that our method achieves the state-of-the-art results and exhibits generalization against different attacks.
Authors: Ziyao Zeng, Hyoungseob Park, Daniel Wang, Fengyu Yang, Yangchao Wu, Stefano Soatto, Byung-Woo Hong, Dong Lao, Alex Wong
Abstract: Three-dimensional (3D) reconstruction from a single image is an ill-posed problem with inherent ambiguities, i.e. scale. Predicting a 3D scene from text description(s) is similarly ill-posed, i.e. spatial arrangements of objects described. We investigate the question of whether two inherently ambiguous modalities can be used in conjunction to produce metric-scaled reconstructions. To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene. To this end, we begin by encoding the text caption as a mean and standard deviation; using a variational framework, we learn the distribution of the plausible metric reconstructions of 3D scenes corresponding to the text captions as a prior. To "select" a specific reconstruction or depth map, we encode the given image through a conditional sampler that samples from the latent space of the variational text encoder, which is then decoded to the output depth map. Our approach is trained alternatingly between the text and image branches: in one optimization step, we predict the mean and standard deviation from the text description and sample from a standard Gaussian, and in the other, we sample using a (image) conditional sampler. Once trained, we directly predict depth from the encoded text using the conditional sampler. We demonstrate our approach on indoor (NYUv2) and outdoor (KITTI) scenarios, where we show that language can consistently improve performance in both.
Authors: Swagat Ranjit
Abstract: Foreign currency exchange plays a vital role for trading of currency in the financial market. Due to its volatile nature, prediction of foreign currency exchange is a challenging task. This paper presents different machine learning techniques like Artificial Neural Network (ANN), Recurrent Neural Network (RNN) to develop prediction model between Nepalese Rupees against three major currencies Euro, Pound Sterling and US dollar. Recurrent Neural Network is a type of neural network that have feedback connections. In this paper, prediction model were based on different RNN architectures, feed forward ANN with back propagation algorithm and then compared the accuracy of each model. Different ANN architecture models like Feed forward neural network, Simple Recurrent Neural Network (SRNN), Gated Recurrent Unit (GRU) and Long Short Term Memory (LSTM) were used. Input parameters were open, low, high and closing prices for each currency. From this study, we have found that LSTM networks provided better results than SRNN and GRU networks.
Authors: Jiahao Wang, Wenqi Shao, Mengzhao Chen, Chengyue Wu, Yong Liu, Kaipeng Zhang, Songyang Zhang, Kai Chen, Ping Luo
Abstract: This work examines whether decoder-only Transformers such as LLaMA, which were originally designed for large language models (LLMs), can be adapted to the computer vision field. We first "LLaMAfy" a standard ViT step-by-step to align with LLaMA's architecture, and find that directly applying a casual mask to the self-attention brings an attention collapse issue, resulting in the failure to the network training. We suggest to reposition the class token behind the image tokens with a post-sequence class token technique to overcome this challenge, enabling causal self-attention to efficiently capture the entire image's information. Additionally, we develop a soft mask strategy that gradually introduces a casual mask to the self-attention at the onset of training to facilitate the optimization behavior. The tailored model, dubbed as image LLaMA (iLLaMA), is akin to LLaMA in architecture and enables direct supervised learning. Its causal self-attention boosts computational efficiency and learns complex representation by elevating attention map ranks. iLLaMA rivals the performance with its encoder-only counterparts, achieving 75.1% ImageNet top-1 accuracy with only 5.7M parameters. Scaling the model to ~310M and pre-training on ImageNet-21K further enhances the accuracy to 86.0%. Extensive experiments demonstrate iLLaMA's reliable properties: calibration, shape-texture bias, quantization compatibility, ADE20K segmentation and CIFAR transfer learning. We hope our study can kindle fresh views to visual model design in the wave of LLMs. Pre-trained models and codes are available here.
Authors: Han Lin, Jaemin Cho, Abhay Zala, Mohit Bansal
Abstract: ControlNets are widely used for adding spatial control to text-to-image diffusion models with different conditions, such as depth maps, scribbles/sketches, and human poses. However, when it comes to controllable video generation, ControlNets cannot be directly integrated into new backbones due to feature space mismatches, and training ControlNets for new backbones can be a significant burden for many users. Furthermore, applying ControlNets independently to different frames cannot effectively maintain object temporal consistency. To address these challenges, we introduce Ctrl-Adapter, an efficient and versatile framework that adds diverse controls to any image/video diffusion model through the adaptation of pretrained ControlNets. Ctrl-Adapter offers strong and diverse capabilities, including image and video control, sparse-frame video control, fine-grained patch-level multi-condition control (via an MoE router), zero-shot adaptation to unseen conditions, and supports a variety of downstream tasks beyond spatial control, including video editing, video style transfer, and text-guided motion control. With six diverse U-Net/DiT-based image/video diffusion models (SDXL, PixArt-$\alpha$, I2VGen-XL, SVD, Latte, Hotshot-XL), Ctrl-Adapter matches the performance of pretrained ControlNets on COCO and achieves the state-of-the-art on DAVIS 2017 with significantly lower computation (< 10 GPU hours).
Authors: Yalda Foroutan, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
Abstract: 3D Gaussian Splatting has recently been embraced as a versatile and effective method for scene reconstruction and novel view synthesis, owing to its high-quality results and compatibility with hardware rasterization. Despite its advantages, Gaussian Splatting's reliance on high-quality point cloud initialization by Structure-from-Motion (SFM) algorithms is a significant limitation to be overcome. To this end, we investigate various initialization strategies for Gaussian Splatting and delve into how volumetric reconstructions from Neural Radiance Fields (NeRF) can be utilized to bypass the dependency on SFM data. Our findings demonstrate that random initialization can perform much better if carefully designed and that by employing a combination of improved initialization strategies and structure distillation from low-cost NeRF models, it is possible to achieve equivalent results, or at times even superior, to those obtained from SFM initialization. Source code is available at https://theialab.github.io/nerf-3dgs .
Authors: Jihao Dong, Renjie Pan, Hua Yang
Abstract: Human-Object Interaction (HOI) detection aims to localize human-object pairs and comprehend their interactions. Recently, two-stage transformer-based methods have demonstrated competitive performance. However, these methods frequently focus on object appearance features and ignore global contextual information. Besides, vision-language model CLIP which effectively aligns visual and text embeddings has shown great potential in zero-shot HOI detection. Based on the former facts, We introduce a novel HOI detector named ISA-HOI, which extensively leverages knowledge from CLIP, aligning interactive semantics between visual and textual features. We first extract global context of image and local features of object to Improve interaction Features in images (IF). On the other hand, we propose a Verb Semantic Improvement (VSI) module to enhance textual features of verb labels via cross-modal fusion. Ultimately, our method achieves competitive results on the HICO-DET and V-COCO benchmarks with much fewer training epochs, and outperforms the state-of-the-art under zero-shot settings.
Authors: Ye Fang, Zeyi Sun, Tong Wu, Jiaqi Wang, Ziwei Liu, Gordon Wetzstein, Dahua Lin
Abstract: Physically realistic materials are pivotal in augmenting the realism of 3D assets across various applications and lighting conditions. However, existing 3D assets and generative models often lack authentic material properties. Manual assignment of materials using graphic software is a tedious and time-consuming task. In this paper, we exploit advancements in Multimodal Large Language Models (MLLMs), particularly GPT-4V, to present a novel approach, Make-it-Real: 1) We demonstrate that GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material library. 2) Utilizing a combination of visual cues and hierarchical text prompts, GPT-4V precisely identifies and aligns materials with the corresponding components of 3D objects. 3) The correctly matched materials are then meticulously applied as reference for the new SVBRDF material generation according to the original albedo map, significantly enhancing their visual authenticity. Make-it-Real offers a streamlined integration into the 3D content creation workflow, showcasing its utility as an essential tool for developers of 3D assets.
Authors: Dongfu Jiang, Xuan He, Huaye Zeng, Cong Wei, Max Ku, Qian Liu, Wenhu Chen
Abstract: Large multimodal models (LMMs) have shown great results in single-image vision language tasks. However, their abilities to solve multi-image visual language tasks is yet to be improved. The existing LMMs like OpenFlamingo, Emu2, Idefics gain their multi-image ability through pre-training on hundreds of millions of noisy interleaved image-text data from the web, which is neither efficient nor effective. In this paper, we aim to build strong multi-image LMMs via instruction tuning with academic-level resources. Therefore, we meticulously construct Mantis-Instruct containing 721K multi-image instruction data to train a family of models Mantis. The instruction tuning empowers Mantis with different multi-image skills like co-reference, comparison, reasoning, and temporal understanding. We evaluate Mantis on five multi-image benchmarks and seven single-image benchmarks. Mantis-SigLIP can achieve SoTA results on all the multi-image benchmarks and beat the strongest multi-image baseline, Idefics2-8B by an average of 11 absolute points. Notably, Idefics2-8B was pre-trained on 140M interleaved multi-image data, which is 200x larger than Mantis-Instruct. We observe that Mantis performs equivalently well on the held-in and held-out benchmarks, which shows its generalization ability. Notably, we found that Mantis can even match the performance of GPT-4V on multi-image benchmarks. We further evaluate Mantis on single-image benchmarks and demonstrate that Mantis also maintains a strong single-image performance on par with CogVLM and Emu2. Our results show that multi-image abilities are not necessarily gained through massive pre-training, instead, it can be gained by the low-cost instruction tuning. Our work provides new perspectives on how to improve LMMs' multi-image abilities.
Authors: Hongyu Qu, Rui Yan, Xiangbo Shu, Hailiang Gao, Peng Huang, Guo-Sen Xie
Abstract: Recent few-shot action recognition (FSAR) methods typically perform semantic matching on learned discriminative features to achieve promising performance. However, most FSAR methods focus on single-scale (e.g., frame-level, segment-level, etc) feature alignment, which ignores that human actions with the same semantic may appear at different velocities. To this end, we develop a novel Multi-Velocity Progressive-alignment (MVP-Shot) framework to progressively learn and align semantic-related action features at multi-velocity levels. Concretely, a Multi-Velocity Feature Alignment (MVFA) module is designed to measure the similarity between features from support and query videos with different velocity scales and then merge all similarity scores in a residual fashion. To avoid the multiple velocity features deviating from the underlying motion semantic, our proposed Progressive Semantic-Tailored Interaction (PSTI) module injects velocity-tailored text information into the video feature via feature interaction on channel and temporal domains at different velocities. The above two modules compensate for each other to make more accurate query sample predictions under the few-shot settings. Experimental results show our method outperforms current state-of-the-art methods on multiple standard few-shot benchmarks (i.e., HMDB51, UCF101, Kinetics, and SSv2-small).
Authors: Jeongjin Shin
Abstract: Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks. These attacks prompt models to behave similarly to standard models without a trigger; however, they act maliciously upon detecting a predefined trigger. Despite extensive research on backdoor attacks in image classification, their application to object detection remains relatively underexplored. Given the widespread application of object detection in critical real-world scenarios, the sensitivity and potential impact of these vulnerabilities cannot be overstated. In this study, we propose an effective invisible backdoor attack on object detection utilizing a mask-based approach. Three distinct attack scenarios were explored for object detection: object disappearance, object misclassification, and object generation attack. Through extensive experiments, we comprehensively examined the effectiveness of these attacks and tested certain defense methods to determine effective countermeasures.
Authors: Setareh Cohan, Guy Tevet, Daniele Reda, Xue Bin Peng, Michiel van de Panne
Abstract: Motion in-betweening, a fundamental task in character animation, consists of generating motion sequences that plausibly interpolate user-provided keyframe constraints. It has long been recognized as a labor-intensive and challenging process. We investigate the potential of diffusion models in generating diverse human motions guided by keyframes. Unlike previous inbetweening methods, we propose a simple unified model capable of generating precise and diverse motions that conform to a flexible range of user-specified spatial constraints, as well as text conditioning. To this end, we propose Conditional Motion Diffusion In-betweening (CondMDI) which allows for arbitrary dense-or-sparse keyframe placement and partial keyframe constraints while generating high-quality motions that are diverse and coherent with the given keyframes. We evaluate the performance of CondMDI on the text-conditioned HumanML3D dataset and demonstrate the versatility and efficacy of diffusion models for keyframe in-betweening. We further explore the use of guidance and imputation-based approaches for inference-time keyframing and compare CondMDI against these methods.
Authors: Maciej Kilian, Varun Jampani, Luke Zettlemoyer
Abstract: Nearly every recent image synthesis approach, including diffusion, masked-token prediction, and next-token prediction, uses a Transformer network architecture. Despite this common backbone, there has been no direct, compute controlled comparison of how these approaches affect performance and efficiency. We analyze the scalability of each approach through the lens of compute budget measured in FLOPs. We find that token prediction methods, led by next-token prediction, significantly outperform diffusion on prompt following. On image quality, while next-token prediction initially performs better, scaling trends suggest it is eventually matched by diffusion. We compare the inference compute efficiency of each approach and find that next token prediction is by far the most efficient. Based on our findings we recommend diffusion for applications targeting image quality and low latency; and next-token prediction when prompt following or throughput is more important.
Authors: Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Nicu Sebe, Mubarak Shah
Abstract: Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum learning for text-to-image generation. Our method is divided into two training stages. First, a ranking of the examples generated for each prompt is obtained by employing a reward model. Then, increasingly difficult pairs of examples are sampled and provided to a text-to-image generative (diffusion or consistency) model. Generated samples that are far apart in the ranking are considered to form easy pairs, while those that are close in the ranking form hard pairs. In other words, we use the rank difference between samples as a measure of difficulty. The sampled pairs are split into batches according to their difficulty levels, which are gradually used to train the generative model. Our approach, Curriculum DPO, is compared against state-of-the-art fine-tuning approaches on three benchmarks, outperforming the competing methods in terms of text alignment, aesthetics and human preference. Our code is available at https://anonymous.4open.science/r/Curriculum-DPO-EE14.
URLs: https://anonymous.4open.science/r/Curriculum-DPO-EE14.
Authors: Ang\'eline Pouget, Lucas Beyer, Emanuele Bugliarello, Xiao Wang, Andreas Peter Steiner, Xiaohua Zhai, Ibrahim Alabdulmohsin
Abstract: We study cultural and socioeconomic diversity in contrastive vision-language models (VLMs). Using a broad range of benchmark datasets and evaluation metrics, we bring to attention several important findings. First, the common filtering of training data to English image-text pairs disadvantages communities of lower socioeconomic status and negatively impacts cultural understanding. Notably, this performance gap is not captured by - and even at odds with - the currently popular evaluation metrics derived from the Western-centric ImageNet and COCO datasets. Second, pretraining with global, unfiltered data before fine-tuning on English content can improve cultural understanding without sacrificing performance on said popular benchmarks. Third, we introduce the task of geo-localization as a novel evaluation metric to assess cultural diversity in VLMs. Our work underscores the value of using diverse data to create more inclusive multimodal systems and lays the groundwork for developing VLMs that better represent global perspectives.
Authors: Taylor Archibald, Tony Martinez
Abstract: Efficient categorization of historical documents is crucial for fields such as genealogy, legal research, and historical scholarship, where manual classification is impractical for large collections due to its labor-intensive and error-prone nature. To address this, we propose a representational learning strategy that integrates semantic segmentation and deep learning models such as ResNet, CLIP, Document Image Transformer (DiT), and masked auto-encoders (MAE), to generate embeddings that capture document features without predefined labels. To the best of our knowledge, we are the first to evaluate embeddings on fine-grained, unsupervised form classification. To improve these embeddings, we propose to first employ semantic segmentation as a preprocessing step. We contribute two novel datasets$\unicode{x2014}$the French 19th-century and U.S. 1950 Census records$\unicode{x2014}$to demonstrate our approach. Our results show the effectiveness of these various embedding techniques in distinguishing similar document types and indicate that applying semantic segmentation can greatly improve clustering and classification results. The census datasets are available at https://github.com/tahlor/census_forms
Authors: Joanna Waczy\'nska, Piotr Borycki, Joanna Kaleta, S{\l}awomir Tadeja, Przemys{\l}aw Spurek
Abstract: Over the past years, we have observed an abundance of approaches for modeling dynamic 3D scenes using Gaussian Splatting (GS). Such solutions use GS to represent the scene's structure and the neural network to model dynamics. Such approaches allow fast rendering and extracting each element of such a dynamic scene. However, modifying such objects over time is challenging. SC-GS (Sparse Controlled Gaussian Splatting) enhanced with Deformed Control Points partially solves this issue. However, this approach necessitates selecting elements that need to be kept fixed, as well as centroids that should be adjusted throughout editing. Moreover, this task poses additional difficulties regarding the re-productivity of such editing. To address this, we propose Dynamic Multi-Gaussian Soup (D-MiSo), which allows us to model the mesh-inspired representation of dynamic GS. Additionally, we propose a strategy of linking parameterized Gaussian splats, forming a Triangle Soup with the estimated mesh. Consequently, we can separately construct new trajectories for the 3D objects composing the scene. Thus, we can make the scene's dynamic editable over time or while maintaining partial dynamics.
Authors: Zhiheng Feng, Wenhua Wu, Hesheng Wang
Abstract: Road surface reconstruction plays a crucial role in autonomous driving, which can be used for road lane perception and autolabeling tasks. Recently, mesh-based road surface reconstruction algorithms show promising reconstruction results. However, these mesh-based methods suffer from slow speed and poor rendering quality. In contrast, the 3D Gaussian Splatting (3DGS) shows superior rendering speed and quality. Although 3DGS employs explicit Gaussian spheres to represent the scene, it lacks the ability to directly represent the geometric information of the scene. To address this limitation, we propose a novel large-scale road surface reconstruction approach based on 2D Gaussian Splatting (2DGS), named RoGS. The geometric shape of the road is explicitly represented using 2D Gaussian surfels, where each surfel stores color, semantics, and geometric information. Compared to Gaussian spheres, the Gaussian surfels aligns more closely with the physical reality of the road. Distinct from previous initialization methods that rely on point clouds for Gaussian spheres, we introduce a trajectory-based initialization for Gaussian surfels. Thanks to the explicit representation of the Gaussian surfels and a good initialization, our method achieves a significant acceleration while improving reconstruction quality. We achieve excellent results in reconstruction of roads surfaces in a variety of challenging real-world scenes.
Authors: Yong Zhong, Min Zhao, Zebin You, Xiaofeng Yu, Changwang Zhang, Chongxuan Li
Abstract: In this paper, we introduce PoseCrafter, a one-shot method for personalized video generation following the control of flexible poses. Built upon Stable Diffusion and ControlNet, we carefully design an inference process to produce high-quality videos without the corresponding ground-truth frames. First, we select an appropriate reference frame from the training video and invert it to initialize all latent variables for generation. Then, we insert the corresponding training pose into the target pose sequences to enhance faithfulness through a trained temporal attention module. Furthermore, to alleviate the face and hand degradation resulting from discrepancies between poses of training videos and inference poses, we implement simple latent editing through an affine transformation matrix involving facial and hand landmarks. Extensive experiments on several datasets demonstrate that PoseCrafter achieves superior results to baselines pre-trained on a vast collection of videos under 8 commonly used metrics. Besides, PoseCrafter can follow poses from different individuals or artificial edits and simultaneously retain the human identity in an open-domain training video. Our project page is available at https://ml-gsai.github.io/PoseCrafter-demo/.
Authors: Shiqi Yang, Zhi Zhong, Mengjie Zhao, Shusuke Takahashi, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji
Abstract: In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements of text2image or text2audio generation, research in audio2visual or visual2audio generation has been relatively slow. The recent audio-visual generation methods usually resort to huge large language model or composable diffusion models. Instead of designing another giant model for audio-visual generation, in this paper we take a step back showing a simple and lightweight generative transformer, which is not fully investigated in multi-modal generation, can achieve excellent results on image2audio generation. The transformer operates in the discrete audio and visual Vector-Quantized GAN space, and is trained in the mask denoising manner. After training, the classifier-free guidance could be deployed off-the-shelf achieving better performance, without any extra training or modification. Since the transformer model is modality symmetrical, it could also be directly deployed for audio2image generation and co-generation. In the experiments, we show that our simple method surpasses recent image2audio generation methods. Generated audio samples can be found at https://docs.google.com/presentation/d/1ZtC0SeblKkut4XJcRaDsSTuCRIXB3ypxmSi7HTY3IyQ/
URLs: https://docs.google.com/presentation/d/1ZtC0SeblKkut4XJcRaDsSTuCRIXB3ypxmSi7HTY3IyQ/
Authors: Tianwei Yin, Micha\"el Gharbi, Taesung Park, Richard Zhang, Eli Shechtman, Fredo Durand, William T. Freeman
Abstract: Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without enforcing a one-to-one correspondence with the sampling trajectories of their teachers. However, to ensure stable training, DMD requires an additional regression loss computed using a large set of noise-image pairs generated by the teacher with many steps of a deterministic sampler. This is costly for large-scale text-to-image synthesis and limits the student's quality, tying it too closely to the teacher's original sampling paths. We introduce DMD2, a set of techniques that lift this limitation and improve DMD training. First, we eliminate the regression loss and the need for expensive dataset construction. We show that the resulting instability is due to the fake critic not estimating the distribution of generated samples accurately and propose a two time-scale update rule as a remedy. Second, we integrate a GAN loss into the distillation procedure, discriminating between generated samples and real images. This lets us train the student model on real data, mitigating the imperfect real score estimation from the teacher model, and enhancing quality. Lastly, we modify the training procedure to enable multi-step sampling. We identify and address the training-inference input mismatch problem in this setting, by simulating inference-time generator samples during training time. Taken together, our improvements set new benchmarks in one-step image generation, with FID scores of 1.28 on ImageNet-64x64 and 8.35 on zero-shot COCO 2014, surpassing the original teacher despite a 500X reduction in inference cost. Further, we show our approach can generate megapixel images by distilling SDXL, demonstrating exceptional visual quality among few-step methods.
Authors: Govind Mittal, Chinmay Hegde, Nasir Memon
Abstract: With the rise of AI-enabled Real-Time Deepfakes (RTDFs), the integrity of online video interactions has become a growing concern. RTDFs have now made it feasible to replace an imposter's face with their victim in live video interactions. Such advancement in deepfakes also coaxes detection to rise to the same standard. However, existing deepfake detection techniques are asynchronous and hence ill-suited for RTDFs. To bridge this gap, we propose a challenge-response approach that establishes authenticity in live settings. We focus on talking-head style video interaction and present a taxonomy of challenges that specifically target inherent limitations of RTDF generation pipelines. We evaluate representative examples from the taxonomy by collecting a unique dataset comprising eight challenges, which consistently and visibly degrades the quality of state-of-the-art deepfake generators. These results are corroborated both by humans and a new automated scoring function, leading to 88.6% and 80.1% AUC, respectively. The findings underscore the promising potential of challenge-response systems for explainable and scalable real-time deepfake detection in practical scenarios. We provide access to data and code at \url{https://github.com/mittalgovind/GOTCHA-Deepfakes}.
Authors: Guillermo Iglesias, Edgar Talavera, Jes\'us Troya Garc\`ia, Alberto D\'iaz-\'Alvarez, Miguel Grac\'ia-Remesal
Abstract: Comparative diagnostic in brain tumor evaluation makes possible to use the available information of a medical center to compare similar cases when a new patient is evaluated. By leveraging Artificial Intelligence models, the proposed system is able of retrieving the most similar cases of brain tumors for a given query. The primary objective is to enhance the diagnostic process by generating more accurate representations of medical images, with a particular focus on patient-specific normal features and pathologies. The proposed model uses Artificial Intelligence to detect patient features to recommend the most similar cases from a database. The system not only suggests similar cases but also balances the representation of healthy and abnormal features in its design. This not only encourages the generalization of its use but also aids clinicians in their decision-making processes. We conducted a comparative analysis of our approach in relation to similar studies. The proposed architecture obtains a Dice coefficient of 0.474 in both tumoral and healthy regions of the patients, which outperforms previous literature. Our proposed model excels at extracting and combining anatomical and pathological features from brain \glspl{mr}, achieving state-of-the-art results while relying on less expensive label information. This substantially reduces the overall cost of the training process. This paper provides substantial grounds for further exploration of the broader applicability and optimization of the proposed architecture to enhance clinical decision-making. The novel approach presented in this work marks a significant advancement in the field of medical diagnosis, particularly in the context of Artificial Intelligence-assisted image retrieval, and promises to reduce costs and improve the quality of patient care using Artificial Intelligence as a support tool instead of a black box system.
Authors: Stephanie Wenxin Liu, Michael Fischer, Paul D. Yoo, Tobias Ritschel
Abstract: Bounding volumes are an established concept in computer graphics and vision tasks but have seen little change since their early inception. In this work, we study the use of neural networks as bounding volumes. Our key observation is that bounding, which so far has primarily been considered a problem of computational geometry, can be redefined as a problem of learning to classify space into free or occupied. This learning-based approach is particularly advantageous in high-dimensional spaces, such as animated scenes with complex queries, where neural networks are known to excel. However, unlocking neural bounding requires a twist: allowing -- but also limiting -- false positives, while ensuring that the number of false negatives is strictly zero. We enable such tight and conservative results using a dynamically-weighted asymmetric loss function. Our results show that our neural bounding produces up to an order of magnitude fewer false positives than traditional methods. In addition, we propose an extension of our bounding method using early exits that accelerates query speeds by 25%. We also demonstrate that our approach is applicable to non-deep learning models that train within seconds. Our project page is at: https://wenxin-liu.github.io/neural_bounding/.
Authors: Prashant Kumar, Kshitij Madhav Bhat, Vedang Bhupesh Shenvi Nadkarni, Prem Kalra
Abstract: Sparse LiDAR point clouds cause severe loss of detail of static structures and reduce the density of static points available for navigation. Reduced density can be detrimental to navigation under several scenarios. We observe that despite high sparsity, in most cases, the global topology of LiDAR outlining the static structures can be inferred. We utilize this property to obtain a backbone skeleton of a LiDAR scan in the form of a single connected component that is a proxy to its global topology. We utilize the backbone to augment new points along static structures to overcome sparsity. Newly introduced points could correspond to existing static structures or to static points that were earlier obstructed by dynamic objects. To the best of our knowledge, we are the first to use such a strategy for sparse LiDAR point clouds. Existing solutions close to our approach fail to identify and preserve the global static LiDAR topology and generate sub-optimal points. We propose GLiDR, a Graph Generative network that is topologically regularized using 0-dimensional Persistent Homology ($\mathcal{PH}$) constraints. This enables GLiDR to introduce newer static points along a topologically consistent global static LiDAR backbone. GLiDR generates precise static points using $32\times$ sparser dynamic scans and performs better than the baselines across three datasets. GLiDR generates a valuable byproduct - an accurate binary segmentation mask of static and dynamic objects that are helpful for navigation planning and safety in constrained environments. The newly introduced static points allow GLiDR to outperform LiDAR-based navigation using SLAM in several settings. Source code is available at https://kshitijbhat.github.io/glidr
Authors: Lukas Radl, Michael Steiner, Mathias Parger, Alexander Weinrauch, Bernhard Kerbl, Markus Steinberger
Abstract: Gaussian Splatting has emerged as a prominent model for constructing 3D representations from images across diverse domains. However, the efficiency of the 3D Gaussian Splatting rendering pipeline relies on several simplifications. Notably, reducing Gaussian to 2D splats with a single view-space depth introduces popping and blending artifacts during view rotation. Addressing this issue requires accurate per-pixel depth computation, yet a full per-pixel sort proves excessively costly compared to a global sort operation. In this paper, we present a novel hierarchical rasterization approach that systematically resorts and culls splats with minimal processing overhead. Our software rasterizer effectively eliminates popping artifacts and view inconsistencies, as demonstrated through both quantitative and qualitative measurements. Simultaneously, our method mitigates the potential for cheating view-dependent effects with popping, ensuring a more authentic representation. Despite the elimination of cheating, our approach achieves comparable quantitative results for test images, while increasing the consistency for novel view synthesis in motion. Due to its design, our hierarchical approach is only 4% slower on average than the original Gaussian Splatting. Notably, enforcing consistency enables a reduction in the number of Gaussians by approximately half with nearly identical quality and view-consistency. Consequently, rendering performance is nearly doubled, making our approach 1.6x faster than the original Gaussian Splatting, with a 50% reduction in memory requirements.
Authors: Jianxiong Li, Jinliang Zheng, Yinan Zheng, Liyuan Mao, Xiao Hu, Sijie Cheng, Haoyi Niu, Jihao Liu, Yu Liu, Jingjing Liu, Ya-Qin Zhang, Xianyuan Zhan
Abstract: Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding. Most existing methods approach these via separate objectives, which often reach sub-optimal solutions. In this paper, we propose a universal unified objective that can simultaneously extract meaningful task progression information from image sequences and seamlessly align them with language instructions. We discover that via implicit preferences, where a visual trajectory inherently aligns better with its corresponding language instruction than mismatched pairs, the popular Bradley-Terry model can transform into representation learning through proper reward reparameterizations. The resulted framework, DecisionNCE, mirrors an InfoNCE-style objective but is distinctively tailored for decision-making tasks, providing an embodied representation learning framework that elegantly extracts both local and global task progression features, with temporal consistency enforced through implicit time contrastive learning, while ensuring trajectory-level instruction grounding via multimodal joint encoding. Evaluation on both simulated and real robots demonstrates that DecisionNCE effectively facilitates diverse downstream policy learning tasks, offering a versatile solution for unified representation and reward learning. Project Page: https://2toinf.github.io/DecisionNCE/
Authors: Lingting Zhu, Noel Codella, Dongdong Chen, Zhenchao Jin, Lu Yuan, Lequan Yu
Abstract: The limited availability of 3D medical image datasets, due to privacy concerns and high collection or annotation costs, poses significant challenges in the field of medical imaging. While a promising alternative is the use of synthesized medical data, there are few solutions for realistic 3D medical image synthesis due to difficulties in backbone design and fewer 3D training samples compared to 2D counterparts. In this paper, we propose GEM-3D, a novel generative approach to the synthesis of 3D medical images and the enhancement of existing datasets using conditional diffusion models. Our method begins with a 2D slice, noted as the informed slice to serve the patient prior, and propagates the generation process using a 3D segmentation mask. By decomposing the 3D medical images into masks and patient prior information, GEM-3D offers a flexible yet effective solution for generating versatile 3D images from existing datasets. GEM-3D can enable dataset enhancement by combining informed slice selection and generation at random positions, along with editable mask volumes to introduce large variations in diffusion sampling. Moreover, as the informed slice contains patient-wise information, GEM-3D can also facilitate counterfactual image synthesis and dataset-level de-enhancement with desired control. Experiments on brain MRI and abdomen CT images demonstrate that GEM-3D is capable of synthesizing high-quality 3D medical images with volumetric consistency, offering a straightforward solution for dataset enhancement during inference. The code is available at https://github.com/HKU-MedAI/GEM-3D.
Authors: Zitao Shuai, Liyue Shen
Abstract: Vision-language pre-training (VLP) has arised as an efficient scheme for multimodal representation learning, but it requires large-scale multimodal data for pre-training, making it an obstacle especially for medical applications. To overcome the data limitation, federated learning (FL) can be a promising strategy to scale up the dataset for medical VLP while protecting data privacy. However, client data are often heterogeneous in real-world scenarios, and we observe that local training on heterogeneous client data would distort the multimodal representation learning and lead to biased cross-modal alignment. To address this challenge, we propose a Federated Align as IDeal (FedAID) framework for federated VLP with robustness to data heterogeneity, to bind local clients with an ideal crossmodal alignment. Specifically, to reduce distortions on global-aggregated features while learning diverse semantics from client datasets during local training, we propose to bind the cross-model aligned representation space learned by local models with an unbiased one via guidance-based regularization. Moreover, we employ a distribution-based min-max optimization to learn the unbiased cross-modal alignment at each communication turn of federated pre-training. The experiments on real-world datasets demonstrate our method successfully promotes efficient federated multimodal learning for medical VLP with data heterogeneity.
Authors: Mingyuan Zhou, Huangjie Zheng, Zhendong Wang, Mingzhang Yin, Hai Huang
Abstract: We introduce Score identity Distillation (SiD), an innovative data-free method that distills the generative capabilities of pretrained diffusion models into a single-step generator. SiD not only facilitates an exponentially fast reduction in Fr\'echet inception distance (FID) during distillation but also approaches or even exceeds the FID performance of the original teacher diffusion models. By reformulating forward diffusion processes as semi-implicit distributions, we leverage three score-related identities to create an innovative loss mechanism. This mechanism achieves rapid FID reduction by training the generator using its own synthesized images, eliminating the need for real data or reverse-diffusion-based generation, all accomplished within significantly shortened generation time. Upon evaluation across four benchmark datasets, the SiD algorithm demonstrates high iteration efficiency during distillation and surpasses competing distillation approaches, whether they are one-step or few-step, data-free, or dependent on training data, in terms of generation quality. This achievement not only redefines the benchmarks for efficiency and effectiveness in diffusion distillation but also in the broader field of diffusion-based generation. The PyTorch implementation is available at https://github.com/mingyuanzhou/SiD
Authors: Zhihao Chen, Yiyuan Ge
Abstract: Underwater Image Enhancement (UIE) techniques aim to address the problem of underwater image degradation due to light absorption and scattering. In recent years, both Convolution Neural Network (CNN)-based and Transformer-based methods have been widely explored. In addition, combining CNN and Transformer can effectively combine global and local information for enhancement. However, this approach is still affected by the secondary complexity of the Transformer and cannot maximize the performance. Recently, the state-space model (SSM) based architecture Mamba has been proposed, which excels in modeling long distances while maintaining linear complexity. This paper explores the potential of this SSM-based model for UIE from both efficiency and effectiveness perspectives. However, the performance of directly applying Mamba is poor because local fine-grained features, which are crucial for image enhancement, cannot be fully utilized. Specifically, we customize the MambaUIE architecture for efficient UIE. Specifically, we introduce visual state space (VSS) blocks to capture global contextual information at the macro level while mining local information at the micro level. Also, for these two kinds of information, we propose a Dynamic Interaction Block (DIB) and Spatial feed-forward Network (SGFN) for intra-block feature aggregation. MambaUIE is able to efficiently synthesize global and local information and maintains a very small number of parameters with high accuracy. Experiments on UIEB datasets show that our method reduces GFLOPs by 67.4% (2.715G) relative to the SOTA method. To the best of our knowledge, this is the first UIE model constructed based on SSM that breaks the limitation of FLOPs on accuracy in UIE. The official repository of MambaUIE at https://github.com/1024AILab/MambaUIE.
Authors: Yujie Xiang, Bojing Liu, Mattias Rantalainen
Abstract: AI-based analysis of histopathology whole slide images (WSIs) is central in computational pathology. However, image quality, including unsharp areas of WSIs, impacts model performance. We investigate the impact of blur and propose a multi-model approach to mitigate negative impact of unsharp image areas. In this study, we use a simulation approach, evaluating model performance under varying levels of added Gaussian blur to image tiles from >900 H&E-stained breast cancer WSIs. To reduce impact of blur, we propose a novel multi-model approach (DeepBlurMM) where multiple models trained on data with variable amounts of Gaussian blur are used to predict tiles based on their blur levels. Using histological grade as a principal example, we found that models trained with mildly blurred tiles improved performance over the base model when moderate-high blur was present. DeepBlurMM outperformed the base model in presence of moderate blur across all tiles (AUC:0.764 vs. 0.710), and in presence of a mix of low, moderate, and high blur across tiles (AUC:0.821 vs. 0.789). Unsharp image tiles in WSIs impact prediction performance. DeepBlurMM improved prediction performance under some conditions and has the potential to increase quality in both research and clinical applications.
Authors: S\'ebastien Quetin, Andrew Heschl, Mauricio Murillo, Rohit Murali, Shirin A. Enger, Farhad Maleki
Abstract: Background and purpose: Deep Learning (DL) has been widely explored for Organs at Risk (OARs) segmentation; however, most studies have focused on a single modality, either CT or MRI, not both simultaneously. This study presents a high-performing DL pipeline for segmentation of 30 OARs from MRI and CT scans of Head and Neck (H&N) cancer patients. Materials and methods: Paired CT and MRI-T1 images from 42 H&N cancer patients alongside annotation for 30 OARs from the H&N OAR CT & MR segmentation challenge dataset were used to develop a segmentation pipeline. After cropping irrelevant regions, rigid followed by non-rigid registration of CT and MRI volumes was performed. Two versions of the CT volume, representing soft tissues and bone anatomy, were stacked with the MRI volume and used as input to an nnU-Net pipeline. Modality Dropout was used during the training to force the model to learn from the different modalities. Segmentation masks were predicted with the trained model for an independent set of 14 new patients. The mean Dice Score (DS) and Hausdorff Distance (HD) were calculated for each OAR across these patients to evaluate the pipeline. Results: This resulted in an overall mean DS and HD of 0.777 +- 0.118 and 3.455 +- 1.679, respectively, establishing the state-of-the-art (SOTA) for this challenge at the time of submission. Conclusion: The proposed pipeline achieved the best DS and HD among all participants of the H&N OAR CT and MR segmentation challenge and sets a new SOTA for automated segmentation of H&N OARs.
Authors: Hyungtae Lim
Abstract: Despite the remarkable advancements in deep learning-based perception technologies and simultaneous localization and mapping (SLAM), one can face the failure of these approaches when robots encounter scenarios outside their modeled experiences (here, the term modeling encompasses both conventional pattern finding and data-driven approaches). In particular, because learning-based methods are prone to catastrophic failure when operated in untrained scenes, there is still a demand for conventional yet robust approaches that work out of the box in diverse scenarios, such as real-world robotic services and SLAM competitions. In addition, the dynamic nature of real-world environments, characterized by changing surroundings over time and the presence of moving objects, leads to undesirable data points that hinder a robot from localization and path planning. Consequently, methodologies that enable long-term map management, such as multi-session SLAM and static map building, become essential. Therefore, to achieve a robust long-term robotic mapping system that can work out of the box, first, I propose (i) fast and robust ground segmentation to reject the ground points, which are featureless and thus not helpful for localization and mapping. Then, by employing the concept of graduated non-convexity (GNC), I propose (ii) outlier-robust registration with ground segmentation that overcomes the presence of gross outliers within the feature matching results, and (iii) hierarchical multi-session SLAM that not only uses our proposed GNC-based registration but also employs a GNC solver to be robust against outlier loop candidates. Finally, I propose (iv) instance-aware static map building that can handle the presence of moving objects in the environment based on the observation that most moving objects in urban environments are inevitably in contact with the ground.
Authors: Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang
Abstract: In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity. Data samples are generally high-dimensional, and for various structured generation tasks, there are additional attributes which are combined to associate with data samples. We show that the space spanned by the combination of dimensions and attributes is insufficiently sampled by existing training scheme of diffusion generative models, causing degraded test time performance. We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc. Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes. Moreover, ComboStoc enables a new way of test time generation which uses insynchronized time steps for different dimensions and attributes, thus allowing for varying degrees of control over them.
Authors: Nikhilanj Pelluri
Abstract: Visual perception and navigation have emerged as major focus areas in the field of embodied artificial intelligence. We consider the task of image-goal navigation, where an agent is tasked to navigate to a goal specified by an image, relying only on images from an onboard camera. This task is particularly challenging since it demands robust scene understanding, goal-oriented planning and long-horizon navigation. Most existing approaches typically learn navigation policies reliant on recurrent neural networks trained via online reinforcement learning. However, training such policies requires substantial computational resources and time, and performance of these models is not reliable on long-horizon navigation. In this work, we present a generative Transformer based model that jointly models image goals, camera observations and the robot's past actions to predict future actions. We use state-of-the-art perception models and navigation policies to learn robust goal conditioned policies without the need for real-time interaction with the environment. Our model demonstrates capability in capturing and associating visual information across long time horizons, helping in effective navigation. NOTE: This work was submitted as part of a Master's Capstone Project and must be treated as such. This is still an early work in progress and not the final version.
Authors: Guanxiong Luo, Shoujin Huang, Martin Uecker
Abstract: Magnetic resonance imaging (MRI) is a widely used non-invasive imaging modality. However, a persistent challenge lies in balancing image quality with imaging speed. This trade-off is primarily constrained by k-space measurements, which traverse specific trajectories in the spatial Fourier domain (k-space). These measurements are often undersampled to shorten acquisition times, resulting in image artifacts and compromised quality. Generative models learn image distributions and can be used to reconstruct high-quality images from undersampled k-space data. In this work, we present the autoregressive image diffusion (AID) model for image sequences and use it to sample the posterior for accelerated MRI reconstruction. The algorithm incorporates both undersampled k-space and pre-existing information. Models trained with fastMRI dataset are evaluated comprehensively. The results show that the AID model can robustly generate sequentially coherent image sequences. In 3D and dynamic MRI, the AID can outperform the standard diffusion model and reduce hallucinations, due to the learned inter-image dependencies.
Authors: Hongxu Jiang, Muhammad Imran, Linhai Ma, Teng Zhang, Yuyin Zhou, Muxuan Liang, Kuang Gong, Wei Shao
Abstract: Denoising diffusion probabilistic models (DDPMs) have achieved unprecedented success in computer vision. However, they remain underutilized in medical imaging, a field crucial for disease diagnosis and treatment planning. This is primarily due to the high computational cost associated with (1) the use of large number of time steps (e.g., 1,000) in diffusion processes and (2) the increased dimensionality of medical images, which are often 3D or 4D. Training a diffusion model on medical images typically takes days to weeks, while sampling each image volume takes minutes to hours. To address this challenge, we introduce Fast-DDPM, a simple yet effective approach capable of improving training speed, sampling speed, and generation quality simultaneously. Unlike DDPM, which trains the image denoiser across 1,000 time steps, Fast-DDPM trains and samples using only 10 time steps. The key to our method lies in aligning the training and sampling procedures to optimize time-step utilization. Specifically, we introduced two efficient noise schedulers with 10 time steps: one with uniform time step sampling and another with non-uniform sampling. We evaluated Fast-DDPM across three medical image-to-image generation tasks: multi-image super-resolution, image denoising, and image-to-image translation. Fast-DDPM outperformed DDPM and current state-of-the-art methods based on convolutional networks and generative adversarial networks in all tasks. Additionally, Fast-DDPM reduced the training time to 0.2x and the sampling time to 0.01x compared to DDPM. Our code is publicly available at: https://github.com/mirthAI/Fast-DDPM.