Authors: Nico Baumgart, Markus Lange-Hegermann, Mike M\"ucke
Abstract: In industrial manufacturing, numerous tasks of visually inspecting or detecting specific objects exist that are currently performed manually or by classical image processing methods. Therefore, introducing recent deep learning models to industrial environments holds the potential to increase productivity and enable new applications. However, gathering and labeling sufficient data is often intractable, complicating the implementation of such projects. Hence, image synthesis methods are commonly used to generate synthetic training data from 3D models and annotate them automatically, although it results in a sim-to-real domain gap. In this paper, we investigate the sim-to-real generalization performance of standard object detectors on the complex industrial application of terminal strip object detection. Combining domain randomization and domain knowledge, we created an image synthesis pipeline for automatically generating the training data. Moreover, we manually annotated 300 real images of terminal strips for the evaluation. The results show the cruciality of the objects of interest to have the same scale in either domain. Nevertheless, under optimized scaling conditions, the sim-to-real performance difference in mean average precision amounts to 2.69 % for RetinaNet and 0.98 % for Faster R-CNN, qualifying this approach for industrial requirements.
Authors: ShengYun Peng, Seongmin Lee, Xiaojing Wang, Rajarajeswari Balasubramaniyan, Duen Horng Chau
Abstract: Tables convey factual and quantitative data with implicit conventions created by humans that are often challenging for machines to parse. Prior work on table structure recognition (TSR) has mainly centered around complex task-specific combinations of available inputs and tools. We present UniTable, a training framework that unifies both the training paradigm and training objective of TSR. Its training paradigm combines the simplicity of purely pixel-level inputs with the effectiveness and scalability empowered by self-supervised pretraining (SSP) from diverse unannotated tabular images. Our framework unifies the training objectives of all three TSR tasks - extracting table structure, cell content, and cell bounding box (bbox) - into a unified task-agnostic training objective: language modeling. Extensive quantitative and qualitative analyses highlight UniTable's state-of-the-art (SOTA) performance on four of the largest TSR datasets. To promote reproducible research, enhance transparency, and SOTA innovations, we open-source our code at https://github.com/poloclub/unitable and release the first-of-its-kind Jupyter Notebook of the whole inference pipeline, fine-tuned across multiple TSR datasets, supporting all three TSR tasks.
Authors: Aosong Feng, Weikang Qiu, Jinbin Bai, Kaicheng Zhou, Zhen Dong, Xiao Zhang, Rex Ying, Leandros Tassiulas
Abstract: Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content. Among various editing methods, editing within the prompt space gains more attention due to its capacity and simplicity of controlling semantics. However, since diffusion models are commonly pretrained on descriptive text captions, direct editing of words in text prompts usually leads to completely different generated images, violating the requirements for image editing. On the other hand, existing editing methods usually consider introducing spatial masks to preserve the identity of unedited regions, which are usually ignored by DPMs and therefore lead to inharmonic editing results. Targeting these two challenges, in this work, we propose to disentangle the comprehensive image-prompt interaction into several item-prompt interactions, with each item linked to a special learned prompt. The resulting framework, named D-Edit, is based on pretrained diffusion models with cross-attention layers disentangled and adopts a two-step optimization to build item-prompt associations. Versatile image editing can then be applied to specific items by manipulating the corresponding prompts. We demonstrate state-of-the-art results in four types of editing operations including image-based, text-based, mask-based editing, and item removal, covering most types of editing applications, all within a single unified framework. Notably, D-Edit is the first framework that can (1) achieve item editing through mask editing and (2) combine image and text-based editing. We demonstrate the quality and versatility of the editing results for a diverse collection of images through both qualitative and quantitative evaluations.
Authors: Yuli Wu, Julian Wittmann, Peter Walter, Johannes Stegmaier
Abstract: Implantable retinal prostheses offer a promising solution to restore partial vision by circumventing damaged photoreceptor cells in the retina and directly stimulating the remaining functional retinal cells. However, the information transmission between the camera and retinal cells is often limited by the low resolution of the electrode array and the lack of specificity for different ganglion cell types, resulting in suboptimal stimulations. In this work, we propose to utilize normalizing flow-based conditional invertible neural networks to optimize retinal implant stimulation in an unsupervised manner. The invertibility of these networks allows us to use them as a surrogate for the computational model of the visual system, while also encoding input camera signals into optimized electrical stimuli on the electrode array. Compared to other methods, such as trivial downsampling, linear models, and feed-forward convolutional neural networks, the flow-based invertible neural network and its conditional extension yield better visual reconstruction qualities w.r.t. various metrics using a physiologically validated simulation tool.
Authors: Rohith Peddi, Saksham Singh, Saurabh, Parag Singla, Vibhav Gogate
Abstract: Spatio-temporal scene graphs represent interactions in a video by decomposing scenes into individual objects and their pair-wise temporal relationships. Long-term anticipation of the fine-grained pair-wise relationships between objects is a challenging problem. To this end, we introduce the task of Scene Graph Anticipation (SGA). We adapt state-of-the-art scene graph generation methods as baselines to anticipate future pair-wise relationships between objects and propose a novel approach SceneSayer. In SceneSayer, we leverage object-centric representations of relationships to reason about the observed video frames and model the evolution of relationships between objects. We take a continuous time perspective and model the latent dynamics of the evolution of object interactions using concepts of NeuralODE and NeuralSDE, respectively. We infer representations of future relationships by solving an Ordinary Differential Equation and a Stochastic Differential Equation, respectively. Extensive experimentation on the Action Genome dataset validates the efficacy of the proposed methods.
Authors: Kaiwen Cai, Zhekai Duan, Gaowen Liu, Charles Fleming, Chris Xiaoxuan Lu
Abstract: Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce EdgeVL, a novel framework that bridges this gap by seamlessly integrating dual-modality knowledge distillation and quantization-aware contrastive learning. This approach enables the adaptation of large VL models, like CLIP, for efficient use with both RGB and non-RGB images on resource-limited devices without the need for manual annotations. EdgeVL not only transfers visual language alignment capabilities to compact models but also maintains feature quality post-quantization, significantly enhancing open-vocabulary classification performance across various visual modalities. Our work represents the first systematic effort to adapt large VL models for edge deployment, showcasing up to 15.4% accuracy improvements on multiple datasets and up to 93-fold reduction in model size.
Authors: Xiang Li, Kai Qiu, Jinglu Wang, Xiaohao Xu, Rita Singh, Kashu Yamazak, Hao Chen, Xiaonan Huang, Bhiksha Raj
Abstract: Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite progress in this field, the robustness of referring perception models (RPMs) against disruptive perturbations is not well explored. This work thoroughly assesses the resilience of RPMs against various perturbations in both general and specific contexts. Recognizing the complex nature of referring perception tasks, we present a comprehensive taxonomy of perturbations, and then develop a versatile toolbox for synthesizing and evaluating the effects of composite disturbances. Employing this toolbox, we construct $\text{R}^2$-Bench, a benchmark for assessing the Robustness of Referring perception models under noisy conditions across five key tasks. Moreover, we propose the $\text{R}^2$-Agent, an LLM-based agent that simplifies and automates model evaluation via natural language instructions. Our investigation uncovers the vulnerabilities of current RPMs to various perturbations and provides tools for assessing model robustness, potentially promoting the safe and resilient integration of intelligent systems into complex real-world scenarios.
Authors: Cheng Peng, Yutao Tang, Yifan Zhou, Nengyu Wang, Xijun Liu, Deming Li, Rama Chellappa
Abstract: Recent efforts in using 3D Gaussians for scene reconstruction and novel view synthesis can achieve impressive results on curated benchmarks; however, images captured in real life are often blurry. In this work, we analyze the robustness of Gaussian-Splatting-based methods against various image blur, such as motion blur, defocus blur, downscaling blur, \etc. Under these degradations, Gaussian-Splatting-based methods tend to overfit and produce worse results than Neural-Radiance-Field-based methods. To address this issue, we propose Blur Agnostic Gaussian Splatting (BAGS). BAGS introduces additional 2D modeling capacities such that a 3D-consistent and high quality scene can be reconstructed despite image-wise blur. Specifically, we model blur by estimating per-pixel convolution kernels from a Blur Proposal Network (BPN). BPN is designed to consider spatial, color, and depth variations of the scene to maximize modeling capacity. Additionally, BPN also proposes a quality-assessing mask, which indicates regions where blur occur. Finally, we introduce a coarse-to-fine kernel optimization scheme; this optimization scheme is fast and avoids sub-optimal solutions due to a sparse point cloud initialization, which often occurs when we apply Structure-from-Motion on blurry images. We demonstrate that BAGS achieves photorealistic renderings under various challenging blur conditions and imaging geometry, while significantly improving upon existing approaches.
Authors: Bla\v{z} Rolih, Samet Ak\c{c}ay, Dick Ameln, Ashwin Vaidya
Abstract: Industrial anomaly detection is an important task within computer vision with a wide range of practical use cases. The small size of anomalous regions in many real-world datasets necessitates processing the images at a high resolution. This frequently poses significant challenges concerning memory consumption during the model training and inference stages, leaving some existing methods impractical for widespread adoption. To overcome this challenge, we present the tiled ensemble approach, which reduces memory consumption by dividing the input images into a grid of tiles and training a dedicated model for each tile location. The tiled ensemble is compatible with any existing anomaly detection model without the need for any modification of the underlying architecture. By introducing overlapping tiles, we utilize the benefits of traditional stacking ensembles, leading to further improvements in anomaly detection capabilities beyond high resolution alone. We perform a comprehensive analysis using diverse underlying architectures, including Padim, PatchCore, FastFlow, and Reverse Distillation, on two standard anomaly detection datasets: MVTec and VisA. Our method demonstrates a notable improvement across setups while remaining within GPU memory constraints, consuming only as much GPU memory as a single model needs to process a single tile.
Authors: Antonino Greco, Markus Siegel
Abstract: Understanding how visual information is encoded in biological and artificial systems often requires vision scientists to generate appropriate stimuli to test specific hypotheses. Although deep neural network models have revolutionized the field of image generation with methods such as image style transfer, available methods for video generation are scarce. Here, we introduce the Spatiotemporal Style Transfer (STST) algorithm, a dynamic visual stimulus generation framework that allows powerful manipulation and synthesis of video stimuli for vision research. It is based on a two-stream deep neural network model that factorizes spatial and temporal features to generate dynamic visual stimuli whose model layer activations are matched to those of input videos. As an example, we show that our algorithm enables the generation of model metamers, dynamic stimuli whose layer activations within our two-stream model are matched to those of natural videos. We show that these generated stimuli match the low-level spatiotemporal features of their natural counterparts but lack their high-level semantic features, making it a powerful paradigm to study object recognition. Late layer activations in deep vision models exhibited a lower similarity between natural and metameric stimuli compared to early layers, confirming the lack of high-level information in the generated stimuli. Finally, we use our generated stimuli to probe the representational capabilities of predictive coding deep networks. These results showcase potential applications of our algorithm as a versatile tool for dynamic stimulus generation in vision science.
Authors: Adriano D'Alessandro, Ali Mahdavi-Amiri, Ghassan Hamarneh
Abstract: Object counting methods typically rely on manually annotated datasets. The cost of creating such datasets has restricted the versatility of these networks to count objects from specific classes (such as humans or penguins), and counting objects from diverse categories remains a challenge. The availability of robust text-to-image latent diffusion models (LDMs) raises the question of whether these models can be utilized to generate counting datasets. However, LDMs struggle to create images with an exact number of objects based solely on text prompts but they can be used to offer a dependable \textit{sorting} signal by adding and removing objects within an image. Leveraging this data, we initially introduce an unsupervised sorting methodology to learn object-related features that are subsequently refined and anchored for counting purposes using counting data generated by LDMs. Further, we present a density classifier-guided method for dividing an image into patches containing objects that can be reliably counted. Consequently, we can generate counting data for any type of object and count them in an unsupervised manner. Our approach outperforms other unsupervised and few-shot alternatives and is not restricted to specific object classes for which counting data is available. Code to be released upon acceptance.
Authors: Edgar Medina, Leyong Loh
Abstract: Human motion prediction is still an open problem, which is extremely important for autonomous driving and safety applications. Although there are great advances in this area, the widely studied topic of adversarial attacks has not been applied to multi-regression models such as GCNs and MLP-based architectures in human motion prediction. This work intends to reduce this gap using extensive quantitative and qualitative experiments in state-of-the-art architectures similar to the initial stages of adversarial attacks in image classification. The results suggest that models are susceptible to attacks even on low levels of perturbation. We also show experiments with 3D transformations that affect the model performance, in particular, we show that most models are sensitive to simple rotations and translations which do not alter joint distances. We conclude that similar to earlier CNN models, motion forecasting tasks are susceptible to small perturbations and simple 3D transformations.
Authors: Lezhong Wang, Jeppe Revall Frisvad, Mark Bo Jensen, Siavash Arjomand Bigdeli
Abstract: The demand for stereo images increases as manufacturers launch more XR devices. To meet this demand, we introduce StereoDiffusion, a method that, unlike traditional inpainting pipelines, is trainning free, remarkably straightforward to use, and it seamlessly integrates into the original Stable Diffusion model. Our method modifies the latent variable to provide an end-to-end, lightweight capability for fast generation of stereo image pairs, without the need for fine-tuning model weights or any post-processing of images. Using the original input to generate a left image and estimate a disparity map for it, we generate the latent vector for the right image through Stereo Pixel Shift operations, complemented by Symmetric Pixel Shift Masking Denoise and Self-Attention Layers Modification methods to align the right-side image with the left-side image. Moreover, our proposed method maintains a high standard of image quality throughout the stereo generation process, achieving state-of-the-art scores in various quantitative evaluations.
Authors: Suozhi Huang, Juexiao Zhang, Yiming Li, Chen Feng
Abstract: Collaborative perception leverages rich visual observations from multiple robots to extend a single robot's perception ability beyond its field of view. Many prior works receive messages broadcast from all collaborators, leading to a scalability challenge when dealing with a large number of robots and sensors. In this work, we aim to address \textit{scalable camera-based collaborative perception} with a Transformer-based architecture. Our key idea is to enable a single robot to intelligently discern the relevance of the collaborators and their associated cameras according to a learned spatial prior. This proactive understanding of the visual features' relevance does not require the transmission of the features themselves, enhancing both communication and computation efficiency. Specifically, we present ActFormer, a Transformer that learns bird's eye view (BEV) representations by using predefined BEV queries to interact with multi-robot multi-camera inputs. Each BEV query can actively select relevant cameras for information aggregation based on pose information, instead of interacting with all cameras indiscriminately. Experiments on the V2X-Sim dataset demonstrate that ActFormer improves the detection performance from 29.89% to 45.15% in terms of AP@0.7 with about 50% fewer queries, showcasing the effectiveness of ActFormer in multi-agent collaborative 3D object detection.
Authors: Wanwen Chen, Adam Schmidt, Eitan Prisman, Septimiu E Salcudean
Abstract: Finding point-level correspondences is a fundamental problem in ultrasound (US), since it can enable US landmark tracking for intraoperative image guidance in different surgeries, including head and neck. Most existing US tracking methods, e.g., those based on optical flow or feature matching, were initially designed for RGB images before being applied to US. Therefore domain shift can impact their performance. Training could be supervised by ground-truth correspondences, but these are expensive to acquire in US. To solve these problems, we propose a self-supervised pixel-level tracking model called PIPsUS. Our model can track an arbitrary number of points in one forward pass and exploits temporal information by considering multiple, instead of just consecutive, frames. We developed a new self-supervised training strategy that utilizes a long-term point-tracking model trained for RGB images as a teacher to guide the model to learn realistic motions and use data augmentation to enforce tracking from US appearance. We evaluate our method on neck and oral US and echocardiography, showing higher point tracking accuracy when compared with fast normalized cross-correlation and tuned optical flow. Code will be available once the paper is accepted.
Authors: Zewen Chen, Haina Qin, Juan Wang, Chunfeng Yuan, Bing Li, Weiming Hu, Liang Wang
Abstract: Due to the diversity of assessment requirements in various application scenarios for the IQA task, existing IQA methods struggle to directly adapt to these varied requirements after training. Thus, when facing new requirements, a typical approach is fine-tuning these models on datasets specifically created for those requirements. However, it is time-consuming to establish IQA datasets. In this work, we propose a Prompt-based IQA (PromptIQA) that can directly adapt to new requirements without fine-tuning after training. On one hand, it utilizes a short sequence of Image-Score Pairs (ISP) as prompts for targeted predictions, which significantly reduces the dependency on the data requirements. On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements. Experiments indicate that the PromptIQA outperforms SOTA methods with higher performance and better generalization. The code will be available.
Authors: Jaehyeok Shim, Kyungdon Joo
Abstract: We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predominantly focus on single latent type, such as point or grid latents. In contrast, the proposed DITTO leverages both point and grid latents (i.e., dual latent) to enhance their strengths, the stability of grid latents and the detail-rich capability of point latents. Concretely, DITTO consists of dual latent encoder and integrated implicit decoder. In the dual latent encoder, a dual latent layer, which is the key module block composing the encoder, refines both latents in parallel, maintaining their distinct shapes and enabling recursive interaction. Notably, a newly proposed dynamic sparse point transformer within the dual latent layer effectively refines point latents. Then, the integrated implicit decoder systematically combines these refined latents, achieving high-fidelity 3D reconstruction and surpassing previous state-of-the-art methods on object- and scene-level datasets, especially in thin and detailed structures.
Authors: Zichong Meng, Jie Zhang, Changdi Yang, Zheng Zhan, Pu Zhao, Yanzhi WAng
Abstract: Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data. Recent exemplar-free CIL methods attempt to mitigate catastrophic forgetting by synthesizing previous task data. However, they fail to overcome the catastrophic forgetting due to the inability to deal with the significant domain gap between real and synthetic data. To overcome these issues, we propose a novel exemplar-free CIL method. Our method adopts multi-distribution matching (MDM) diffusion models to unify quality and bridge domain gaps among all domains of training data. Moreover, our approach integrates selective synthetic image augmentation (SSIA) to expand the distribution of the training data, thereby improving the model's plasticity and reinforcing the performance of our method's ultimate component, multi-domain adaptation (MDA). With the proposed integrations, our method then reformulates exemplar-free CIL into a multi-domain adaptation problem to implicitly address the domain gap problem to enhance model stability during incremental training. Extensive experiments on benchmark class incremental datasets and settings demonstrate that our method excels previous exemplar-free CIL methods and achieves state-of-the-art performance.
Authors: Zichong Meng, Changdi Yang, Jun Liu, Hao Tang, Pu Zhao, Yanzhi Wang
Abstract: Recent advances in image editing have been driven by the development of denoising diffusion models, marking a significant leap forward in this field. Despite these advances, the generalization capabilities of recent image editing approaches remain constrained. In response to this challenge, our study introduces a novel image editing framework with enhanced generalization robustness by boosting in-context learning capability and unifying language instruction. This framework incorporates a module specifically optimized for image editing tasks, leveraging the VMamba Block and an editing-shift matching strategy to augment in-context learning. Furthermore, we unveil a selective area-matching technique specifically engineered to address and rectify corrupted details in generated images, such as human facial features, to further improve the quality. Another key innovation of our approach is the integration of a language unification technique, which aligns language embeddings with editing semantics to elevate the quality of image editing. Moreover, we compile the first dataset for image editing with visual prompts and editing instructions that could be used to enhance in-context capability. Trained on this dataset, our methodology not only achieves superior synthesis quality for trained tasks, but also demonstrates robust generalization capability across unseen vision tasks through tailored prompts.
Authors: Jiabao Zhang, Yu Zhang
Abstract: Mapping plays a crucial role in location and navigation within automatic systems. However, the presence of dynamic objects in 3D point cloud maps generated from scan sensors can introduce map distortion and long traces, thereby posing challenges for accurate mapping and navigation. To address this issue, we propose ERASOR++, an enhanced approach based on the Egocentric Ratio of Pseudo Occupancy for effective dynamic object removal. To begin, we introduce the Height Coding Descriptor, which combines height difference and height layer information to encode the point cloud. Subsequently, we propose the Height Stack Test, Ground Layer Test, and Surrounding Point Test methods to precisely and efficiently identify the dynamic bins within point cloud bins, thus overcoming the limitations of prior approaches. Through extensive evaluation on open-source datasets, our approach demonstrates superior performance in terms of precision and efficiency compared to existing methods. Furthermore, the techniques described in our work hold promise for addressing various challenging tasks or aspects through subsequent migration.
Authors: Yunhao Li, Hao Wang, Qin Li, Xue Ma, Jiali Yao, Shaohua Dong, Heng Fan, Libo Zhang
Abstract: Current multi-object tracking (MOT) aims to predict trajectories of targets (i.e.,"where") in videos. Yet, knowing merely "where" is insufficient in many crucial applications. In comparison, semantic understanding such as fine-grained behaviors, interactions, and overall summarized captions (i.e., "what") from videos, associated with "where", is highly-desired for comprehensive video analysis. Thus motivated, we introduce Semantic Multi-Object Tracking (SMOT), that aims to estimate object trajectories and meanwhile understand semantic details of associated trajectories including instance captions, instance interactions, and overall video captions, integrating "where" and "what" for tracking. In order to foster the exploration of SMOT, we propose BenSMOT, a large-scale Benchmark for Semantic MOT. Specifically, BenSMOT comprises 3,292 videos with 151K frames, covering various scenarios for semantic tracking of humans. BenSMOT provides annotations for the trajectories of targets, along with associated instance captions in natural language, instance interactions, and overall caption for each video sequence. To our best knowledge, BenSMOT is the first publicly available benchmark for SMOT. Besides, to encourage future research, we present a novel tracker named SMOTer, which is specially designed and end-to-end trained for SMOT, showing promising performance. By releasing BenSMOT, we expect to go beyond conventional MOT by predicting "where" and "what" for SMOT, opening up a new direction in tracking for video understanding. Our BenSMOT and SMOTer will be released.
Authors: Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, Jun Zhu
Abstract: Feed-forward 3D generative models like the Large Reconstruction Model (LRM) have demonstrated exceptional generation speed. However, the transformer-based methods do not leverage the geometric priors of the triplane component in their architecture, often leading to sub-optimal quality given the limited size of 3D data and slow training. In this work, we present the Convolutional Reconstruction Model (CRM), a high-fidelity feed-forward single image-to-3D generative model. Recognizing the limitations posed by sparse 3D data, we highlight the necessity of integrating geometric priors into network design. CRM builds on the key observation that the visualization of triplane exhibits spatial correspondence of six orthographic images. First, it generates six orthographic view images from a single input image, then feeds these images into a convolutional U-Net, leveraging its strong pixel-level alignment capabilities and significant bandwidth to create a high-resolution triplane. CRM further employs Flexicubes as geometric representation, facilitating direct end-to-end optimization on textured meshes. Overall, our model delivers a high-fidelity textured mesh from an image in just 10 seconds, without any test-time optimization.
Authors: Guoqing Zhang, Wenbo Zhao, Jian Liu, Xianming Liu
Abstract: Sampling is widely used in various point cloud tasks as it can effectively reduce resource consumption. Recently, some methods have proposed utilizing neural networks to optimize the sampling process for various task requirements. Currently, deep downsampling methods can be categorized into two main types: generative-based and score-based. Generative-based methods directly generate sampled point clouds using networks, whereas score-based methods assess the importance of points according to specific rules and then select sampled point clouds based on their scores. However, these methods often result in noticeable clustering effects in high-intensity feature areas, compromising their ability to preserve small-scale features and leading to the loss of some structures, thereby affecting the performance of subsequent tasks. In this paper, we propose REPS, a reconstruction-based scoring strategy that evaluates the importance of each vertex by removing and reconstructing them using surrounding vertices. Our reconstruction process comprises point reconstruction and shape reconstruction. The two aforementioned reconstruction methods effectively evaluate the importance of vertices by removing them at different scales for reconstruction. These reconstructions ensure that our method maintains the overall geometric features of the point cloud and avoids disturbing small-scale structures during sampling. Additionally, we propose the Global-Local Fusion Attention (GLFA) module, which aggregates local and global attention features of point clouds, ensuring high-quality reconstruction and sampling effects. Our method outperforms previous approaches in preserving the structural features of the sampled point clouds. Furthermore, abundant experimental results demonstrate the superior performance of our method across various common tasks.
Authors: Yunpeng Qu, Kun Yuan, Kai Zhao, Qizhi Xie, Jinhua Hao, Ming Sun, Chao Zhou
Abstract: Diffusion-based methods, endowed with a formidable generative prior, have received increasing attention in Image Super-Resolution (ISR) recently. However, as low-resolution (LR) images often undergo severe degradation, it is challenging for ISR models to perceive the semantic and degradation information, resulting in restoration images with incorrect content or unrealistic artifacts. To address these issues, we propose a \textit{Cross-modal Priors for Super-Resolution (XPSR)} framework. Within XPSR, to acquire precise and comprehensive semantic conditions for the diffusion model, cutting-edge Multimodal Large Language Models (MLLMs) are utilized. To facilitate better fusion of cross-modal priors, a \textit{Semantic-Fusion Attention} is raised. To distill semantic-preserved information instead of undesired degradations, a \textit{Degradation-Free Constraint} is attached between LR and its high-resolution (HR) counterpart. Quantitative and qualitative results show that XPSR is capable of generating high-fidelity and high-realism images across synthetic and real-world datasets. Codes will be released at \url{https://github.com/qyp2000/XPSR}.
Authors: Xiang Huang, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Wangmeng Xiang, Baigui Sun, Xiao Wu
Abstract: Autonomous driving systems demand real-time, accurate perception to navigate complex environments. Addressing this, we introduce the Dynamic Router Network (DyRoNet), a framework that innovates with low-rank dynamic routing for enhanced streaming perception. By integrating specialized pre-trained branch networks, fine-tuned for various environmental conditions, DyRoNet achieves a balance between latency and precision. Its core feature, the speed router module, intelligently directs input data to the best-suited branch network, optimizing performance. The extensive evaluations reveal that DyRoNet adapts effectively to multiple branch selection strategies, setting a new benchmark in performance across a range of scenarios. DyRoNet not only establishes a new benchmark for streaming perception but also provides valuable engineering insights for future work. More project information is available at https://tastevision.github.io/DyRoNet/
Authors: Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin
Abstract: Image composition involves seamlessly integrating given objects into a specific visual context. The current training-free methods rely on composing attention weights from several samplers to guide the generator. However, since these weights are derived from disparate contexts, their combination leads to coherence confusion in synthesis and loss of appearance information. These issues worsen with their excessive focus on background generation, even when unnecessary in this task. This not only slows down inference but also compromises foreground generation quality. Moreover, these methods introduce unwanted artifacts in the transition area. In this paper, we formulate image composition as a subject-based local editing task, solely focusing on foreground generation. At each step, the edited foreground is combined with the noisy background to maintain scene consistency. To address the remaining issues, we propose PrimeComposer, a faster training-free diffuser that composites the images by well-designed attention steering across different noise levels. This steering is predominantly achieved by our Correlation Diffuser, utilizing its self-attention layers at each step. Within these layers, the synthesized subject interacts with both the referenced object and background, capturing intricate details and coherent relationships. This prior information is encoded into the attention weights, which are then integrated into the self-attention layers of the generator to guide the synthesis process. Besides, we introduce a Region-constrained Cross-Attention to confine the impact of specific subject-related words to desired regions, addressing the unwanted artifacts shown in the prior method thereby further improving the coherence in the transition area. Our method exhibits the fastest inference efficiency and extensive experiments demonstrate our superiority both qualitatively and quantitatively.
Authors: Yitao Zhu, Sheng Wang, Mengjie Xu, Zixu Zhuang, Zhixin Wang, Kaidong Wang, Han Zhang, Qian Wang
Abstract: Multiple cameras can provide multi-view video coverage of a person. It is necessary to fuse multi-view data, e.g., for subsequent behavioral analysis, while such fusion often relies on calibration of cameras in traditional solutions. However, it is non-trivial to calibrate multiple cameras. In this work, we propose a method to reconstruct 3D human body from multiple uncalibrated camera views. First, we adopt a pre-trained human body encoder to process each individual camera view, such that human body models and parameters can be reconstructed for each view. Next, instead of simply averaging models across views, we train a network to determine the weights of individual views for their fusion, based on the parameters estimated for joints and hands of human body as well as camera positions. Further, we turn to the mesh surface of human body for dynamic fusion, such that facial expression can be seamlessly integrated into the model of human body. Our method has demonstrated superior performance in reconstructing human body upon two public datasets. More importantly, our method can flexibly support ad-hoc deployment of an arbitrary number of cameras, which has significant potential in related applications. We will release source code upon acceptance of the paper.
Authors: Yifan Mao, Jian Liu, Xianming Liu
Abstract: Monocular depth estimation is a crucial task in computer vision. While existing methods have shown impressive results under standard conditions, they often face challenges in reliably performing in scenarios such as low-light or rainy conditions due to the absence of diverse training data. This paper introduces a novel approach named Stealing Stable Diffusion (SSD) prior for robust monocular depth estimation. The approach addresses this limitation by utilizing stable diffusion to generate synthetic images that mimic challenging conditions. Additionally, a self-training mechanism is introduced to enhance the model's depth estimation capability in such challenging environments. To enhance the utilization of the stable diffusion prior further, the DINOv2 encoder is integrated into the depth model architecture, enabling the model to leverage rich semantic priors and improve its scene understanding. Furthermore, a teacher loss is introduced to guide the student models in acquiring meaningful knowledge independently, thus reducing their dependency on the teacher models. The effectiveness of the approach is evaluated on nuScenes and Oxford RobotCar, two challenging public datasets, with the results showing the efficacy of the method. Source code and weights are available at: https://github.com/hitcslj/SSD.
Authors: Geonho Bang, Kwangjin Choi, Jisong Kim, Dongsuk Kum, Jun Won Choi
Abstract: The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve the representation of radar data by leveraging LiDAR data. RadarDistill successfully transfers desirable characteristics of LiDAR features into radar features using three key components: Cross-Modality Alignment (CMA), Activation-based Feature Distillation (AFD), and Proposal-based Feature Distillation (PFD). CMA enhances the density of radar features through multiple layers of dilation operations, effectively addressing the challenges of inefficient knowledge transfer from LiDAR to radar. AFD is designed to transfer knowledge from significant areas of the LiDAR features, specifically those regions where activation intensity exceeds a predetermined threshold. PFD guides the radar network to mimic LiDAR network features in the object proposals for accurately detected results while moderating features for misdetected proposals like false positives. Our comparative analyses conducted on the nuScenes datasets demonstrate that RadarDistill achieves state-of-the-art (SOTA) performance for radar-only object detection task, recording 20.5% in mAP and 43.7% in NDS. Also, RadarDistill significantly improves the performance of the camera-radar fusion model.
Authors: Xinyao Li, Jingjing Li, Fengling Li, Lei Zhu, Ke Lu
Abstract: Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models. This work focuses on adaptively utilizing knowledge from multiple source-pretrained models to an unlabeled target domain without accessing the source data. Despite being a practically useful setting, existing methods require extensive parameter tuning over each source model, which is computationally expensive when facing abundant source domains or larger source models. To address this challenge, we propose a novel approach which is free of the parameter tuning over source backbones. Our technical contribution lies in the Bi-level ATtention ENsemble (Bi-ATEN) module, which learns both intra-domain weights and inter-domain ensemble weights to achieve a fine balance between instance specificity and domain consistency. By slightly tuning source bottlenecks, we achieve comparable or even superior performance on a challenging benchmark DomainNet with less than 3% trained parameters and 8 times of throughput compared with SOTA method. Furthermore, with minor modifications, the proposed module can be easily equipped to existing methods and gain more than 4% performance boost. Code is available at https://github.com/TL-UESTC/Bi-ATEN.
Authors: Daegyu Kim, Jooyoung Choi, Chaehun Shin, Uiwon Hwang, Sungroh Yoon
Abstract: We introduce the Approximated Optimal Transport (AOT) technique, a novel training scheme for diffusion-based generative models. Our approach aims to approximate and integrate optimal transport into the training process, significantly enhancing the ability of diffusion models to estimate the denoiser outputs accurately. This improvement leads to ODE trajectories of diffusion models with lower curvature and reduced truncation errors during sampling. We achieve superior image quality and reduced sampling steps by employing AOT in training. Specifically, we achieve FID scores of 1.88 with just 27 NFEs and 1.73 with 29 NFEs in unconditional and conditional generations, respectively. Furthermore, when applying AOT to train the discriminator for guidance, we establish new state-of-the-art FID scores of 1.68 and 1.58 for unconditional and conditional generations, respectively, each with 29 NFEs. This outcome demonstrates the effectiveness of AOT in enhancing the performance of diffusion models.
Authors: Youngju Na, Woo Jae Kim, Kyu Beom Han, Suhyeon Ha, Sung-eui Yoon
Abstract: Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes. However, existing methods select only informative and relevant views using predefined scores for training and testing phases. This constraint renders the model impractical in real-world scenarios, where the availability of favorable combinations cannot always be ensured. We introduce and validate a view-combination score to indicate the effectiveness of the input view combination. We observe that previous methods output degenerate solutions under arbitrary and unfavorable sets. Building upon this finding, we propose \textbf{UFORecon}, a robust view-combination generalizable surface reconstruction framework. To achieve this, we apply cross-view matching transformers to model interactions between source images and build correlation frustums to capture global correlations. Additionally, we explicitly encode pairwise feature similarities as view-consistent priors. Our proposed framework significantly outperforms previous methods in terms of view-combination generalizability and also in the conventional generalizable protocol trained with favorable view-combinations. The code is available at \url{https://github.com/Youngju-Na/UFORecon}.
Authors: Seokjun Lee, Seung-Won Jung, Hyunseok Seo
Abstract: Currently, image generation and synthesis have remarkably progressed with generative models. Despite photo-realistic results, intrinsic discrepancies are still observed in the frequency domain. The spectral discrepancy appeared not only in generative adversarial networks but in diffusion models. In this study, we propose a framework to effectively mitigate the disparity in frequency domain of the generated images to improve generative performance of both GAN and diffusion models. This is realized by spectrum translation for the refinement of image generation (STIG) based on contrastive learning. We adopt theoretical logic of frequency components in various generative networks. The key idea, here, is to refine the spectrum of the generated image via the concept of image-to-image translation and contrastive learning in terms of digital signal processing. We evaluate our framework across eight fake image datasets and various cutting-edge models to demonstrate the effectiveness of STIG. Our framework outperforms other cutting-edges showing significant decreases in FID and log frequency distance of spectrum. We further emphasize that STIG improves image quality by decreasing the spectral anomaly. Additionally, validation results present that the frequency-based deepfake detector confuses more in the case where fake spectrums are manipulated by STIG.
Authors: Kaede Shiohara, Toshihiko Yamasaki
Abstract: Face personalization aims to insert specific faces, taken from images, into pretrained text-to-image diffusion models. However, it is still challenging for previous methods to preserve both the identity similarity and editability due to overfitting to training samples. In this paper, we propose Face2Diffusion (F2D) for high-editability face personalization. The core idea behind F2D is that removing identity-irrelevant information from the training pipeline prevents the overfitting problem and improves editability of encoded faces. F2D consists of the following three novel components: 1) Multi-scale identity encoder provides well-disentangled identity features while keeping the benefits of multi-scale information, which improves the diversity of camera poses. 2) Expression guidance disentangles face expressions from identities and improves the controllability of face expressions. 3) Class-guided denoising regularization encourages models to learn how faces should be denoised, which boosts the text-alignment of backgrounds. Extensive experiments on the FaceForensics++ dataset and diverse prompts demonstrate our method greatly improves the trade-off between the identity- and text-fidelity compared to previous state-of-the-art methods.
Authors: Kuo Xu, Maoyu Wang, Muyu Wang, Lincong Feng, Tianhui Zhang, Xiaoli Liu
Abstract: The recent advancements in 2D generation technology have sparked a widespread discussion on using 2D priors for 3D shape and texture content generation. However, these methods often overlook the subsequent user operations, such as texture aliasing and blurring that occur when the user acquires the 3D model and simplifies its structure. Traditional graphics methods partially alleviate this issue, but recent texture synthesis technologies fail to ensure consistency with the original model's appearance and cannot achieve high-fidelity restoration. Moreover, background noise frequently arises in high-resolution texture synthesis, limiting the practical application of these generation technologies.In this work, we propose a high-resolution and high-fidelity texture restoration technique that uses the rough texture as the initial input to enhance the consistency between the synthetic texture and the initial texture, thereby overcoming the issues of aliasing and blurring caused by the user's structure simplification operations. Additionally, we introduce a background noise smoothing technique based on a self-supervised scheme to address the noise problem in current high-resolution texture synthesis schemes. Our approach enables high-resolution texture synthesis, paving the way for high-definition and high-detail texture synthesis technology. Experiments demonstrate that our scheme outperforms currently known schemes in high-fidelity texture recovery under high-resolution conditions.
Authors: Haochen Han, Qinghua Zheng, Guang Dai, Minnan Luo, Jingdong Wang
Abstract: Collecting well-matched multimedia datasets is crucial for training cross-modal retrieval models. However, in real-world scenarios, massive multimodal data are harvested from the Internet, which inevitably contains Partially Mismatched Pairs (PMPs). Undoubtedly, such semantical irrelevant data will remarkably harm the cross-modal retrieval performance. Previous efforts tend to mitigate this problem by estimating a soft correspondence to down-weight the contribution of PMPs. In this paper, we aim to address this challenge from a new perspective: the potential semantic similarity among unpaired samples makes it possible to excavate useful knowledge from mismatched pairs. To achieve this, we propose L2RM, a general framework based on Optimal Transport (OT) that learns to rematch mismatched pairs. In detail, L2RM aims to generate refined alignments by seeking a minimal-cost transport plan across different modalities. To formalize the rematching idea in OT, first, we propose a self-supervised cost function that automatically learns from explicit similarity-cost mapping relation. Second, we present to model a partial OT problem while restricting the transport among false positives to further boost refined alignments. Extensive experiments on three benchmarks demonstrate our L2RM significantly improves the robustness against PMPs for existing models. The code is available at https://github.com/hhc1997/L2RM.
Authors: Zikang Xu, Fenghe Tang, Quan Quan, Qingsong Yao, S. Kevin Zhou
Abstract: Ensuring fairness in deep-learning-based segmentors is crucial for health equity. Much effort has been dedicated to mitigating unfairness in the training datasets or procedures. However, with the increasing prevalence of foundation models in medical image analysis, it is hard to train fair models from scratch while preserving utility. In this paper, we propose a novel method, Adversarial Privacy-aware Perturbations on Latent Embedding (APPLE), that can improve the fairness of deployed segmentors by introducing a small latent feature perturber without updating the weights of the original model. By adding perturbation to the latent vector, APPLE decorates the latent vector of segmentors such that no fairness-related features can be passed to the decoder of the segmentors while preserving the architecture and parameters of the segmentor. Experiments on two segmentation datasets and five segmentors (three U-Net-like and two SAM-like) illustrate the effectiveness of our proposed method compared to several unfairness mitigation methods.
Authors: Hang Du, Xuejun Yan, Jingjing Wang, Di Xie, Shiliang Pu
Abstract: Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem of surface approximation and employ point-based networks to learn surface representations. However, learning surfaces from sparse point clouds is more challenging, and thus they often suffer from the low-fidelity geometry approximation. To address it, we propose an arbitrary-scale Point cloud Upsampling framework using Voxel-based Network (\textbf{PU-VoxelNet}). Thanks to the completeness and regularity inherited from the voxel representation, voxel-based networks are capable of providing predefined grid space to approximate 3D surface, and an arbitrary number of points can be reconstructed according to the predicted density distribution within each grid cell. However, we investigate the inaccurate grid sampling caused by imprecise density predictions. To address this issue, a density-guided grid resampling method is developed to generate high-fidelity points while effectively avoiding sampling outliers. Further, to improve the fine-grained details, we present an auxiliary training supervision to enforce the latent geometric consistency among local surface patches. Extensive experiments indicate the proposed approach outperforms the state-of-the-art approaches not only in terms of fixed upsampling rates but also for arbitrary-scale upsampling.
Authors: Wendi Zheng, Jiayan Teng, Zhuoyi Yang, Weihan Wang, Jidong Chen, Xiaotao Gu, Yuxiao Dong, Ming Ding, Jie Tang
Abstract: Recent advancements in text-to-image generative systems have been largely driven by diffusion models. However, single-stage text-to-image diffusion models still face challenges, in terms of computational efficiency and the refinement of image details. To tackle the issue, we propose CogView3, an innovative cascaded framework that enhances the performance of text-to-image diffusion. CogView3 is the first model implementing relay diffusion in the realm of text-to-image generation, executing the task by first creating low-resolution images and subsequently applying relay-based super-resolution. This methodology not only results in competitive text-to-image outputs but also greatly reduces both training and inference costs. Our experimental results demonstrate that CogView3 outperforms SDXL, the current state-of-the-art open-source text-to-image diffusion model, by 77.0\% in human evaluations, all while requiring only about 1/2 of the inference time. The distilled variant of CogView3 achieves comparable performance while only utilizing 1/10 of the inference time by SDXL.
Authors: Pengwei Yin, Guanzhong Zeng, Jingjing Wang, Di Xie
Abstract: Gaze estimation methods often experience significant performance degradation when evaluated across different domains, due to the domain gap between the testing and training data. Existing methods try to address this issue using various domain generalization approaches, but with little success because of the limited diversity of gaze datasets, such as appearance, wearable, and image quality. To overcome these limitations, we propose a novel framework called CLIP-Gaze that utilizes a pre-trained vision-language model to leverage its transferable knowledge. Our framework is the first to leverage the vision-and-language cross-modality approach for gaze estimation task. Specifically, we extract gaze-relevant feature by pushing it away from gaze-irrelevant features which can be flexibly constructed via language descriptions. To learn more suitable prompts, we propose a personalized context optimization method for text prompt tuning. Furthermore, we utilize the relationship among gaze samples to refine the distribution of gaze-relevant features, thereby improving the generalization capability of the gaze estimation model. Extensive experiments demonstrate the excellent performance of CLIP-Gaze over existing methods on four cross-domain evaluations.
Authors: Muxi Chen, Yi Liu, Jian Yi, Changran Xu, Qiuxia Lai, Hongliang Wang, Tsung-Yi Ho, Qiang Xu
Abstract: In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first, focusing on image qualities such as aesthetics and realism, and second, examining text conditions through concept coverage and fairness. We introduce an innovative aesthetic score prediction model that assesses the visual appeal of generated images and unveils the first dataset marked with low-quality regions in generated human images to facilitate automatic defect detection. Our exploration into concept coverage probes the model's effectiveness in interpreting and rendering text-based concepts accurately, while our analysis of fairness reveals biases in model outputs, with an emphasis on gender, race, and age. While our study is grounded in human imagery, this dual-faceted approach is designed with the flexibility to be applicable to other forms of image generation, enhancing our understanding of generative models and paving the way to the next generation of more sophisticated, contextually aware, and ethically attuned generative models. We will release our code, the data used for evaluating generative models and the dataset annotated with defective areas soon.
Authors: Xiwei Hu, Rui Wang, Yixiao Fang, Bin Fu, Pei Cheng, Gang Yu
Abstract: Diffusion models have demonstrated remarkable performance in the domain of text-to-image generation. However, most widely used models still employ CLIP as their text encoder, which constrains their ability to comprehend dense prompts, encompassing multiple objects, detailed attributes, complex relationships, long-text alignment, etc. In this paper, we introduce an Efficient Large Language Model Adapter, termed ELLA, which equips text-to-image diffusion models with powerful Large Language Models (LLM) to enhance text alignment without training of either U-Net or LLM. To seamlessly bridge two pre-trained models, we investigate a range of semantic alignment connector designs and propose a novel module, the Timestep-Aware Semantic Connector (TSC), which dynamically extracts timestep-dependent conditions from LLM. Our approach adapts semantic features at different stages of the denoising process, assisting diffusion models in interpreting lengthy and intricate prompts over sampling timesteps. Additionally, ELLA can be readily incorporated with community models and tools to improve their prompt-following capabilities. To assess text-to-image models in dense prompt following, we introduce Dense Prompt Graph Benchmark (DPG-Bench), a challenging benchmark consisting of 1K dense prompts. Extensive experiments demonstrate the superiority of ELLA in dense prompt following compared to state-of-the-art methods, particularly in multiple object compositions involving diverse attributes and relationships.
Authors: Yisol Choi, Sangkyung Kwak, Kyungmin Lee, Hyungwon Choi, Jinwoo Shin
Abstract: This paper considers image-based virtual try-on, which renders an image of a person wearing a curated garment, given a pair of images depicting the person and the garment, respectively. Previous works adapt existing exemplar-based inpainting diffusion models for virtual try-on to improve the naturalness of the generated visuals compared to other methods (e.g., GAN-based), but they fail to preserve the identity of the garments. To overcome this limitation, we propose a novel diffusion model that improves garment fidelity and generates authentic virtual try-on images. Our method, coined IDM-VTON, uses two different modules to encode the semantics of garment image; given the base UNet of the diffusion model, 1) the high-level semantics extracted from a visual encoder are fused to the cross-attention layer, and then 2) the low-level features extracted from parallel UNet are fused to the self-attention layer. In addition, we provide detailed textual prompts for both garment and person images to enhance the authenticity of the generated visuals. Finally, we present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity. Our experimental results show that our method outperforms previous approaches (both diffusion-based and GAN-based) in preserving garment details and generating authentic virtual try-on images, both qualitatively and quantitatively. Furthermore, the proposed customization method demonstrates its effectiveness in a real-world scenario.
Authors: Qiuhui Chen, Huping Ye, Yi Hong
Abstract: Understanding 3D medical image volumes is a critical task in the medical domain. However, existing 3D convolution and transformer-based methods have limited semantic understanding of an image volume and also need a large set of volumes for training. Recent advances in multi-modal large language models (MLLMs) provide a new and promising way to understand images with the help of text descriptions. However, most current MLLMs are designed for 2D natural images. To enhance the 3D medical image understanding with 2D MLLMs, we propose a novel pre-training framework called Med3DInsight, which marries existing 3D image encoders with 2D MLLMs and bridges them via a designed Plane-Slice-Aware Transformer (PSAT) module. Extensive experiments demonstrate our SOTA performance on two downstream segmentation and classification tasks, including three public datasets with CT and MRI modalities and comparison to more than ten baselines. Med3DInsight can be easily integrated into any current 3D medical image understanding network and improves its performance by a good margin.
Authors: Yuelin Zhang, Wanquan Yan, Kim Yan, Chun Ping Lam, Yufu Qiu, Pengyu Zheng, Raymond Shing-Yan Tang, Shing Shin Cheng
Abstract: Gastric simulators with objective educational feedback have been proven useful for endoscopy training. Existing electronic simulators with feedback are however not commonly adopted due to their high cost. In this work, a motion-guided dual-camera tracker is proposed to provide reliable endoscope tip position feedback at a low cost inside a mechanical simulator for endoscopy skill evaluation, tackling several unique challenges. To address the issue of significant appearance variation of the endoscope tip while keeping dual-camera tracking consistency, the cross-camera mutual template strategy (CMT) is proposed to introduce dynamic transient mutual templates to dual-camera tracking. To alleviate disturbance from large occlusion and distortion by the light source from the endoscope tip, the Mamba-based motion-guided prediction head (MMH) is presented to aggregate visual tracking with historical motion information modeled by the state space model. The proposed tracker was evaluated on datasets captured by low-cost camera pairs during endoscopy procedures performed inside the mechanical simulator. The tracker achieves SOTA performance with robust and consistent tracking on dual cameras. Further downstream evaluation proves that the 3D tip position determined by the proposed tracker enables reliable skill differentiation. The code and dataset will be released upon acceptance.
Authors: Francesco Palandra, Andrea Sanchietti, Daniele Baieri, Emanuele Rodol\`a
Abstract: We present GSEdit, a pipeline for text-guided 3D object editing based on Gaussian Splatting models. Our method enables the editing of the style and appearance of 3D objects without altering their main details, all in a matter of minutes on consumer hardware. We tackle the problem by leveraging Gaussian splatting to represent 3D scenes, and we optimize the model while progressively varying the image supervision by means of a pretrained image-based diffusion model. The input object may be given as a 3D triangular mesh, or directly provided as Gaussians from a generative model such as DreamGaussian. GSEdit ensures consistency across different viewpoints, maintaining the integrity of the original object's information. Compared to previously proposed methods relying on NeRF-like MLP models, GSEdit stands out for its efficiency, making 3D editing tasks much faster. Our editing process is refined via the application of the SDS loss, ensuring that our edits are both precise and accurate. Our comprehensive evaluation demonstrates that GSEdit effectively alters object shape and appearance following the given textual instructions while preserving their coherence and detail.
Authors: Jiayan Cao, Xueyu Zhu, Cheng Qian
Abstract: Lane detection plays a critical role in the field of autonomous driving. Prevailing methods generally adopt basic concepts (anchors, key points, etc.) from object detection and segmentation tasks, while these approaches require manual adjustments for curved objects, involve exhaustive searches on predefined anchors, require complex post-processing steps, and may lack flexibility when applied to real-world scenarios.In this paper, we propose a novel approach, LanePtrNet, which treats lane detection as a process of point voting and grouping on ordered sets: Our method takes backbone features as input and predicts a curve-aware centerness, which represents each lane as a point and assigns the most probable center point to it. A novel point sampling method is proposed to generate a set of candidate points based on the votes received. By leveraging features from local neighborhoods, and cross-instance attention score, we design a grouping module that further performs lane-wise clustering between neighboring and seeding points. Furthermore, our method can accommodate a point-based framework, (PointNet++ series, etc.) as an alternative to the backbone. This flexibility enables effortless extension to 3D lane detection tasks. We conduct comprehensive experiments to validate the effectiveness of our proposed approach, demonstrating its superior performance.
Authors: Zichao Dong, Bowen Pang, Xufeng Huang, Hang Ji, Xin Zhan, Junbo Chen
Abstract: Multi-modality fusion is proven an effective method for 3d perception for autonomous driving. However, most current multi-modality fusion pipelines for LiDAR semantic segmentation have complicated fusion mechanisms. Point painting is a quite straight forward method which directly bind LiDAR points with visual information. Unfortunately, previous point painting like methods suffer from projection error between camera and LiDAR. In our experiments, we find that this projection error is the devil in point painting. As a result of that, we propose a depth aware point painting mechanism, which significantly boosts the multi-modality fusion. Apart from that, we take a deeper look at the desired visual feature for LiDAR to operate semantic segmentation. By Lifting Visual Information as Cue, LVIC ranks 1st on nuScenes LiDAR semantic segmentation benchmark. Our experiments show the robustness and effectiveness. Codes would be make publicly available soon.
Authors: Zijie Fang, Yifeng Wang, Zhi Wang, Jian Zhang, Xiangyang Ji, Yongbing Zhang
Abstract: Recently, pathological diagnosis, the gold standard for cancer diagnosis, has achieved superior performance by combining the Transformer with the multiple instance learning (MIL) framework using whole slide images (WSIs). However, the giga-pixel nature of WSIs poses a great challenge for the quadratic-complexity self-attention mechanism in Transformer to be applied in MIL. Existing studies usually use linear attention to improve computing efficiency but inevitably bring performance bottlenecks. To tackle this challenge, we propose a MamMIL framework for WSI classification by cooperating the selective structured state space model (i.e., Mamba) with MIL for the first time, enabling the modeling of instance dependencies while maintaining linear complexity. Specifically, to solve the problem that Mamba can only conduct unidirectional one-dimensional (1D) sequence modeling, we innovatively introduce a bidirectional state space model and a 2D context-aware block to enable MamMIL to learn the bidirectional instance dependencies with 2D spatial relationships. Experiments on two datasets show that MamMIL can achieve advanced classification performance with smaller memory footprints than the state-of-the-art MIL frameworks based on the Transformer. The code will be open-sourced if accepted.
Authors: Hai Huang, Yan Xia, Shengpeng Ji, Shulei Wang, Hanting Wang, Jieming Zhu, Zhenhua Dong, Zhou Zhao
Abstract: Recent advances in representation learning have demonstrated the significance of multimodal alignment. The Dual Cross-modal Information Disentanglement (DCID) model, utilizing a unified codebook, shows promising results in achieving fine-grained representation and cross-modal generalization. However, it is still hindered by equal treatment of all channels and neglect of minor event information, resulting in interference from irrelevant channels and limited performance in fine-grained tasks. Thus, in this work, We propose a Training-free Optimization of Codebook (TOC) method to enhance model performance by selecting important channels in the unified space without retraining. Additionally, we introduce the Hierarchical Dual Cross-modal Information Disentanglement (H-DCID) approach to extend information separation and alignment to two levels, capturing more cross-modal details. The experiment results demonstrate significant improvements across various downstream tasks, with TOC contributing to an average improvement of 1.70% for DCID on four tasks, and H-DCID surpassing DCID by an average of 3.64%. The combination of TOC and H-DCID further enhances performance, exceeding DCID by 4.43%. These findings highlight the effectiveness of our methods in facilitating robust and nuanced cross-modal learning, opening avenues for future enhancements. The source code and pre-trained models can be accessed at https://github.com/haihuangcode/TOC_H-DCID.
Authors: Jie Shao, Ke Zhu, Hanxiao Zhang, Jianxin Wu
Abstract: This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy that can be optimized through cross-entropy (CE). Specifically, a randomly initialized diffusion model, trained exclusively on the long-tailed dataset, is employed to synthesize new samples for underrepresented classes. Then, we utilize the inherent information in the original dataset to filter out harmful samples and keep the useful ones. Our strategy, Diffusion model for Long-Tail recognition (DiffuLT), represents a pioneering utilization of generative models in long-tail recognition. DiffuLT achieves state-of-the-art results on CIFAR10-LT, CIFAR100-LT, and ImageNet-LT, surpassing the best competitors with non-trivial margins. Abundant ablations make our pipeline interpretable, too. The whole generation pipeline is done without any external data or pre-trained model weights, making it highly generalizable to real-world long-tailed settings.
Authors: Jingyi Zhang, Peng Zhang, Jingjing Wang, Di Xie, Shiliang Pu
Abstract: Previous face forgery detection methods mainly focus on appearance features, which may be easily attacked by sophisticated manipulation. Considering the majority of current face manipulation methods generate fake faces based on a single frame, which do not take frame consistency and coordination into consideration, artifacts on frame sequences are more effective for face forgery detection. However, current sequence-based face forgery detection methods use general video classification networks directly, which discard the special and discriminative motion information for face manipulation detection. To this end, we propose an effective sequence-based forgery detection framework based on an existing video classification method. To make the motion features more expressive for manipulation detection, we propose an alternative motion consistency block instead of the original motion features module. To make the learned features more generalizable, we propose an auxiliary anomaly detection block. With these two specially designed improvements, we make a general video classification network achieve promising results on three popular face forgery datasets.
Authors: Haoxin Xu, Zezheng Zhao, Yuxin Cao, Chunyu Chen, Hao Ge, Ziyao Liu
Abstract: Monocular 3D face reconstruction plays a crucial role in avatar generation, with significant demand in web-related applications such as generating virtual financial advisors in FinTech. Current reconstruction methods predominantly rely on deep learning techniques and employ 2D self-supervision as a means to guide model learning. However, these methods encounter challenges in capturing the comprehensive 3D structural information of the face due to the utilization of 2D images for model training purposes. To overcome this limitation and enhance the reconstruction of 3D structural features, we propose an innovative approach that integrates existing 2D features with 3D features to guide the model learning process. Specifically, we introduce the 3D-ID Loss, which leverages the high-dimensional structure features extracted from a Spectral-Based Graph Convolution Encoder applied to the facial mesh. This approach surpasses the sole reliance on the 3D information provided by the facial mesh vertices coordinates. Our model is trained using 2D-3D data pairs from a combination of datasets and achieves state-of-the-art performance on the NoW benchmark.
Authors: Lucas Farndale, Chris Walsh, Robert Insall, Ke Yuan
Abstract: Multimodal self-supervised representation learning has consistently proven to be a highly effective method in medical image analysis, offering strong task performance and producing biologically informed insights. However, these methods heavily rely on large, paired datasets, which is prohibitive for their use in scenarios where paired data does not exist, or there is only a small amount available. In contrast, image generation methods can work well on very small datasets, and can find mappings between unpaired datasets, meaning an effectively unlimited amount of paired synthetic data can be generated. In this work, we demonstrate that representation learning can be significantly improved by synthetically generating paired information, both compared to training on either single-modality (up to 4.4x error reduction) or authentic multi-modal paired datasets (up to 5.6x error reduction).
Authors: Liting Lin, Heng Fan, Zhipeng Zhang, Yaowei Wang, Yong Xu, Haibin Ling
Abstract: Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models, we propose LoRAT, a method that unveils the power of larger Vision Transformers (ViT) for tracking within laboratory-level resources. The essence of our work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. However, unique challenges and potential domain gaps make this transfer not as easy as the first intuition. Firstly, a transformer-based tracker constructs unshared position embedding for template and search image. This poses a challenge for the transfer of LoRA, usually requiring consistency in the design when applied to the pre-trained backbone, to downstream tasks. Secondly, the inductive bias inherent in convolutional heads diminishes the effectiveness of parameter-efficient fine-tuning in tracking models. To overcome these limitations, we first decouple the position embeddings in transformer-based trackers into shared spatial ones and independent type ones. The shared embeddings, which describe the absolute coordinates of multi-resolution images (namely, the template and search images), are inherited from the pre-trained backbones. In contrast, the independent embeddings indicate the sources of each token and are learned from scratch. Furthermore, we design an anchor-free head solely based on a multilayer perceptron (MLP) to adapt PETR, enabling better performance with less computational overhead. With our design, 1) it becomes practical to train trackers with the ViT-g backbone on GPUs with only memory of 25.8GB (batch size of 16); 2) we reduce the training time of the L-224 variant from 35.0 to 10.8 GPU hours; 3) we improve the LaSOT SUC score from 0.703 to 0.743 with the L-224 variant; 4) we fast the inference speed of the L-224 variant from 52 to 119 FPS. Code and models will be released.
Authors: Dan Guo, Kun Li, Bin Hu, Yan Zhang, Meng Wang
Abstract: Micro-action is an imperceptible non-verbal behaviour characterised by low-intensity movement. It offers insights into the feelings and intentions of individuals and is important for human-oriented applications such as emotion recognition and psychological assessment. However, the identification, differentiation, and understanding of micro-actions pose challenges due to the imperceptible and inaccessible nature of these subtle human behaviors in everyday life. In this study, we innovatively collect a new micro-action dataset designated as Micro-action-52 (MA-52), and propose a benchmark named micro-action network (MANet) for micro-action recognition (MAR) task. Uniquely, MA-52 provides the whole-body perspective including gestures, upper- and lower-limb movements, attempting to reveal comprehensive micro-action cues. In detail, MA-52 contains 52 micro-action categories along with seven body part labels, and encompasses a full array of realistic and natural micro-actions, accounting for 205 participants and 22,422 video instances collated from the psychological interviews. Based on the proposed dataset, we assess MANet and other nine prevalent action recognition methods. MANet incorporates squeeze-and excitation (SE) and temporal shift module (TSM) into the ResNet architecture for modeling the spatiotemporal characteristics of micro-actions. Then a joint-embedding loss is designed for semantic matching between video and action labels; the loss is used to better distinguish between visually similar yet distinct micro-action categories. The extended application in emotion recognition has demonstrated one of the important values of our proposed dataset and method. In the future, further exploration of human behaviour, emotion, and psychological assessment will be conducted in depth. The dataset and source code are released at https://github.com/VUT-HFUT/Micro-Action.
Authors: Junyan Wang, Zhenhong Sun, Zhiyu Tan, Xuanbai Chen, Weihua Chen, Hao Li, Cheng Zhang, Yang Song
Abstract: Vanilla text-to-image diffusion models struggle with generating accurate human images, commonly resulting in imperfect anatomies such as unnatural postures or disproportionate limbs.Existing methods address this issue mostly by fine-tuning the model with extra images or adding additional controls -- human-centric priors such as pose or depth maps -- during the image generation phase. This paper explores the integration of these human-centric priors directly into the model fine-tuning stage, essentially eliminating the need for extra conditions at the inference stage. We realize this idea by proposing a human-centric alignment loss to strengthen human-related information from the textual prompts within the cross-attention maps. To ensure semantic detail richness and human structural accuracy during fine-tuning, we introduce scale-aware and step-wise constraints within the diffusion process, according to an in-depth analysis of the cross-attention layer. Extensive experiments show that our method largely improves over state-of-the-art text-to-image models to synthesize high-quality human images based on user-written prompts. Project page: \url{https://hcplayercvpr2024.github.io}.
Authors: Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao
Abstract: Adversarial attack methods based on point manipulation for 3D point cloud classification have revealed the fragility of 3D models, yet the adversarial examples they produce are easily perceived or defended against. The trade-off between the imperceptibility and adversarial strength leads most point attack methods to inevitably introduce easily detectable outlier points upon a successful attack. Another promising strategy, shape-based attack, can effectively eliminate outliers, but existing methods often suffer significant reductions in imperceptibility due to irrational deformations. We find that concealing deformation perturbations in areas insensitive to human eyes can achieve a better trade-off between imperceptibility and adversarial strength, specifically in parts of the object surface that are complex and exhibit drastic curvature changes. Therefore, we propose a novel shape-based adversarial attack method, HiT-ADV, which initially conducts a two-stage search for attack regions based on saliency and imperceptibility scores, and then adds deformation perturbations in each attack region using Gaussian kernel functions. Additionally, HiT-ADV is extendable to physical attack. We propose that by employing benign resampling and benign rigid transformations, we can further enhance physical adversarial strength with little sacrifice to imperceptibility. Extensive experiments have validated the superiority of our method in terms of adversarial and imperceptible properties in both digital and physical spaces. Our code is avaliable at: https://github.com/TRLou/HiT-ADV.
Authors: Hailang Huang, Zhijie Nie, Ziqiao Wang, Ziyu Shang
Abstract: Current image-text retrieval methods have demonstrated impressive performance in recent years. However, they still face two problems: the inter-modal matching missing problem and the intra-modal semantic loss problem. These problems can significantly affect the accuracy of image-text retrieval. To address these challenges, we propose a novel method called Cross-modal and Uni-modal Soft-label Alignment (CUSA). Our method leverages the power of uni-modal pre-trained models to provide soft-label supervision signals for the image-text retrieval model. Additionally, we introduce two alignment techniques, Cross-modal Soft-label Alignment (CSA) and Uni-modal Soft-label Alignment (USA), to overcome false negatives and enhance similarity recognition between uni-modal samples. Our method is designed to be plug-and-play, meaning it can be easily applied to existing image-text retrieval models without changing their original architectures. Extensive experiments on various image-text retrieval models and datasets, we demonstrate that our method can consistently improve the performance of image-text retrieval and achieve new state-of-the-art results. Furthermore, our method can also boost the uni-modal retrieval performance of image-text retrieval models, enabling it to achieve universal retrieval. The code and supplementary files can be found at https://github.com/lerogo/aaai24_itr_cusa.
Authors: Yi-Fan Zhang, Weichen Yu, Qingsong Wen, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Abstract: In the realms of computer vision and natural language processing, Large Vision-Language Models (LVLMs) have become indispensable tools, proficient in generating textual descriptions based on visual inputs. Despite their advancements, our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior rather than the input image. Our empirical experiments underscore the persistence of this bias, as LVLMs often provide confident answers even in the absence of relevant images or given incongruent visual input. To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies. Firstly, for tasks such as classification or multi-choice question-answering (QA), we propose a ``calibration'' step through affine transformation to adjust the output distribution. This ``Post-Hoc debias'' approach ensures uniform scores for each answer when the image is absent, serving as an effective regularization technique to alleviate the influence of LLM priors. For more intricate open-ended generation tasks, we extend this method to ``Debias sampling'', drawing inspirations from contrastive decoding methods. Furthermore, our investigation sheds light on the instability of LVLMs across various decoding configurations. Through systematic exploration of different settings, we significantly enhance performance, surpassing reported results and raising concerns about the fairness of existing evaluations. Comprehensive experiments substantiate the effectiveness of our proposed strategies in mitigating biases. These strategies not only prove beneficial in minimizing hallucinations but also contribute to the generation of more helpful and precise illustrations.
Authors: Chenglong Wang, Yinqiao Yi, Yida Wang, Chengxiu Zhang, Yun Liu, Kensaku Mori, Mei Yuan, Guang Yang
Abstract: With the ongoing development of deep learning, an increasing number of AI models have surpassed the performance levels of human clinical practitioners. However, the prevalence of AI diagnostic products in actual clinical practice remains significantly lower than desired. One crucial reason for this gap is the so-called `black box' nature of AI models. Clinicians' distrust of black box models has directly hindered the clinical deployment of AI products. To address this challenge, we propose ContrastDiagnosis, a straightforward yet effective interpretable diagnosis framework. This framework is designed to introduce inherent transparency and provide extensive post-hoc explainability for deep learning model, making them more suitable for clinical medical diagnosis. ContrastDiagnosis incorporates a contrastive learning mechanism to provide a case-based reasoning diagnostic rationale, enhancing the model's transparency and also offers post-hoc interpretability by highlighting similar areas. High diagnostic accuracy was achieved with AUC of 0.977 while maintain a high transparency and explainability.
Authors: Thang M. Pham, Peijie Chen, Tin Nguyen, Seunghyun Yoon, Trung Bui, Anh Nguyen
Abstract: CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder. That is, CLIP performs poorly on new classes or the classes whose names rarely appear on the Internet (e.g., scientific names of birds). For fine-grained classification, we propose PEEB - an explainable and editable classifier to (1) express the class name into a set of pre-defined text descriptors that describe the visual parts of that class; and (2) match the embeddings of the detected parts to their textual descriptors in each class to compute a logit score for classification. In a zero-shot setting where the class names are unknown, PEEB outperforms CLIP by a large margin (~10x in accuracy). Compared to part-based classifiers, PEEB is not only the state-of-the-art on the supervised-learning setting (88.80% accuracy) but also the first to enable users to edit the class definitions to form a new classifier without retraining. Compared to concept bottleneck models, PEEB is also the state-of-the-art in both zero-shot and supervised learning settings.
Authors: Juan I. Pisula, Katarzyna Bozek
Abstract: The first step in Multiple Instance Learning (MIL) algorithms for Whole Slide Image (WSI) classification consists of tiling the input image into smaller patches and computing their feature vectors produced by a pre-trained feature extractor model. Feature extractor models that were pre-trained with supervision on ImageNet have proven to transfer well to this domain, however, this pre-training task does not take into account that visual information in neighboring patches is highly correlated. Based on this observation, we propose to increase downstream MIL classification by fine-tuning the feature extractor model using \textit{Masked Context Modelling with Knowledge Distillation}. In this task, the feature extractor model is fine-tuned by predicting masked patches in a bigger context window. Since reconstructing the input image would require a powerful image generation model, and our goal is not to generate realistically looking image patches, we predict instead the feature vectors produced by a larger teacher network. A single epoch of the proposed task suffices to increase the downstream performance of the feature-extractor model when used in a MIL scenario, even capable of outperforming the downstream performance of the teacher model, while being considerably smaller and requiring a fraction of its compute.
Authors: Yushan Zhang, Bastian Wandt, Maria Magnusson, Michael Felsberg
Abstract: Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy, their applicability to real-world systems additionally benefits from a reliability measure. Aiming at improving accuracy while additionally providing an estimate for uncertainty, we propose DiffSF that combines transformer-based scene flow estimation with denoising diffusion models. In the diffusion process, the ground truth scene flow vector field is gradually perturbed by adding Gaussian noise. In the reverse process, starting from randomly sampled Gaussian noise, the scene flow vector field prediction is recovered by conditioning on a source and a target point cloud. We show that the diffusion process greatly increases the robustness of predictions compared to prior approaches resulting in state-of-the-art performance on standard scene flow estimation benchmarks. Moreover, by sampling multiple times with different initial states, the denoising process predicts multiple hypotheses, which enables measuring the output uncertainty, allowing our approach to detect a majority of the inaccurate predictions.
Authors: Ji Zhang, Yiran Ding
Abstract: 3D occupancy prediction based on multi-sensor fusion, crucial for a reliable autonomous driving system, enables fine-grained understanding of 3D scenes. Previous fusion-based 3D occupancy predictions relied on depth estimation for processing 2D image features. However, depth estimation is an ill-posed problem, hindering the accuracy and robustness of these methods. Furthermore, fine-grained occupancy prediction demands extensive computational resources. We introduce OccFusion, a multi-modal fusion method free from depth estimation, and a corresponding point cloud sampling algorithm for dense integration of image features. Building on this, we propose an active training method and an active coarse to fine pipeline, enabling the model to adaptively learn more from complex samples and optimize predictions specifically for challenging areas such as small or overlapping objects. The active methods we propose can be naturally extended to any occupancy prediction model. Experiments on the OpenOccupancy benchmark show our method surpasses existing state-of-the-art (SOTA) multi-modal methods in IoU across all categories. Additionally, our model is more efficient during both the training and inference phases, requiring far fewer computational resources. Comprehensive ablation studies demonstrate the effectiveness of our proposed techniques.
Authors: Enoch Solomon, Abraham Woubie
Abstract: The state-of-the-art face recognition systems are typically trained on a single computer, utilizing extensive image datasets collected from various number of users. However, these datasets often contain sensitive personal information that users may hesitate to disclose. To address potential privacy concerns, we explore the application of federated learning, both with and without secure aggregators, in the context of both supervised and unsupervised face recognition systems. Federated learning facilitates the training of a shared model without necessitating the sharing of individual private data, achieving this by training models on decentralized edge devices housing the data. In our proposed system, each edge device independently trains its own model, which is subsequently transmitted either to a secure aggregator or directly to the central server. To introduce diverse data without the need for data transmission, we employ generative adversarial networks to generate imposter data at the edge. Following this, the secure aggregator or central server combines these individual models to construct a global model, which is then relayed back to the edge devices. Experimental findings based on the CelebA datasets reveal that employing federated learning in both supervised and unsupervised face recognition systems offers dual benefits. Firstly, it safeguards privacy since the original data remains on the edge devices. Secondly, the experimental results demonstrate that the aggregated model yields nearly identical performance compared to the individual models, particularly when the federated model does not utilize a secure aggregator. Hence, our results shed light on the practical challenges associated with privacy-preserving face image training, particularly in terms of the balance between privacy and accuracy.
Authors: Junsu Kim, Yunhoe Ku, Jihyeon Kim, Junuk Cha, Seungryul Baek
Abstract: In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning due to their tendency to forget past knowledge. To overcome this, we introduce a new approach called Vision-Language Model assisted Pseudo-Labeling (VLM-PL). This technique uses Vision-Language Model (VLM) to verify the correctness of pseudo ground-truths (GTs) without requiring additional model training. VLM-PL starts by deriving pseudo GTs from a pre-trained detector. Then, we generate custom queries for each pseudo GT using carefully designed prompt templates that combine image and text features. This allows the VLM to classify the correctness through its responses. Furthermore, VLM-PL integrates refined pseudo and real GTs from upcoming training, effectively combining new and old knowledge. Extensive experiments conducted on the Pascal VOC and MS COCO datasets not only highlight VLM-PL's exceptional performance in multi-scenario but also illuminate its effectiveness in dual-scenario by achieving state-of-the-art results in both.
Authors: H. Keshvarikhojasteh, J. P. W. Pluim, M. Veta
Abstract: In computational pathology, random sampling of patches during training of Multiple Instance Learning (MIL) methods is computationally efficient and serves as a regularization strategy. Despite its promising benefits, questions concerning performance trends for varying sample sizes and its influence on model interpretability remain. Addressing these, we reach an optimal performance enhancement of 1.7% using thirty percent of patches on the CAMELYON16 dataset, and 3.7% with only eight samples on the TUPAC16 dataset. We also find interpretability effects are strongly dataset-dependent, with interpretability impacted on CAMELYON16, while remaining unaffected on TUPAC16. This reinforces that both the performance and interpretability relationships with sampling are closely task-specific. End-to-end training with 1024 samples reveals improvements across both datasets compared to pre-extracted features, further highlighting the potential of this efficient approach.
Authors: Jiajie Fan, Amal Trigui, Thomas B\"ack, Hao Wang
Abstract: A great interest has arisen in using Deep Generative Models (DGM) for generative design. When assessing the quality of the generated designs, human designers focus more on structural plausibility, e.g., no missing component, rather than visual artifacts, e.g., noises in the images. Meanwhile, commonly used metrics such as Fr\'echet Inception Distance (FID) may not evaluate accurately as they tend to penalize visual artifacts instead of structural implausibility. As such, FID might not be suitable to assess the performance of DGMs for a generative design task. In this work, we propose to encode the input designs with a simple Denoising Autoencoder (DAE) and measure the distribution distance in the latent space thereof. We experimentally test our DAE-based metrics with FID and other state-of-the-art metrics on three data sets: compared to FID and some more recent works, e.g., FD$_\text{DINO-V2}$ and topology distance, DAE-based metrics can effectively detect implausible structures and are more consistent with structural inspection by human experts.
Authors: Linwei Chen, Lin Gu, Ying Fu
Abstract: Dilated convolution, which expands the receptive field by inserting gaps between its consecutive elements, is widely employed in computer vision. In this study, we propose three strategies to improve individual phases of dilated convolution from the view of spectrum analysis. Departing from the conventional practice of fixing a global dilation rate as a hyperparameter, we introduce Frequency-Adaptive Dilated Convolution (FADC), which dynamically adjusts dilation rates spatially based on local frequency components. Subsequently, we design two plug-in modules to directly enhance effective bandwidth and receptive field size. The Adaptive Kernel (AdaKern) module decomposes convolution weights into low-frequency and high-frequency components, dynamically adjusting the ratio between these components on a per-channel basis. By increasing the high-frequency part of convolution weights, AdaKern captures more high-frequency components, thereby improving effective bandwidth. The Frequency Selection (FreqSelect) module optimally balances high- and low-frequency components in feature representations through spatially variant reweighting. It suppresses high frequencies in the background to encourage FADC to learn a larger dilation, thereby increasing the receptive field for an expanded scope. Extensive experiments on segmentation and object detection consistently validate the efficacy of our approach. The code is publicly available at \url{https://github.com/Linwei-Chen/FADC}.
Authors: Salome Kazeminia, Max Joosten, Dragan Bosnacki, Carsten Marr
Abstract: Automated disease diagnosis using medical image analysis relies on deep learning, often requiring large labeled datasets for supervised model training. Diseases like Acute Myeloid Leukemia (AML) pose challenges due to scarce and costly annotations on a single-cell level. Multiple Instance Learning (MIL) addresses weakly labeled scenarios but necessitates powerful encoders typically trained with labeled data. In this study, we explore Self-Supervised Learning (SSL) as a pre-training approach for MIL-based AML subtype classification from blood smears, removing the need for labeled data during encoder training. We investigate the three state-of-the-art SSL methods SimCLR, SwAV, and DINO, and compare their performance against supervised pre-training. Our findings show that SSL-pretrained encoders achieve comparable performance, showcasing the potential of SSL in MIL. This breakthrough offers a cost-effective and data-efficient solution, propelling the field of AI-based disease diagnosis.
Authors: Xavier Bou, Gabriele Facciolo, Rafael Grompone von Gioi, Jean-Michel Morel, Thibaud Ehret
Abstract: The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ideas from open-vocabulary detection for the remote sensing domain. We develop a few-shot object detector based on a traditional two-stage architecture, where the classification block is replaced by a prototype-based classifier. A large-scale pre-trained model is used to build class-reference embeddings or prototypes, which are compared to region proposal contents for label prediction. In addition, we propose to fine-tune prototypes on available training images to boost performance and learn differences between similar classes, such as aircraft types. We perform extensive evaluations on two remote sensing datasets containing challenging and rare objects. Moreover, we study the performance of both visual and image-text features, namely DINOv2 and CLIP, including two CLIP models specifically tailored for remote sensing applications. Results indicate that visual features are largely superior to vision-language models, as the latter lack the necessary domain-specific vocabulary. Lastly, the developed detector outperforms fully supervised and few-shot methods evaluated on the SIMD and DIOR datasets, despite minimal training parameters.
Authors: Yu Han, Ziwei Long, Yanting Zhang, Jin Wu, Zhijun Fang, Rui Fan
Abstract: Correspondence matching plays a crucial role in numerous robotics applications. In comparison to conventional hand-crafted methods and recent data-driven approaches, there is significant interest in plug-and-play algorithms that make full use of pre-trained backbone networks for multi-scale feature extraction and leverage hierarchical refinement strategies to generate matched correspondences. The primary focus of this paper is to address the limitations of deep feature matching (DFM), a state-of-the-art (SoTA) plug-and-play correspondence matching approach. First, we eliminate the pre-defined threshold employed in the hierarchical refinement process of DFM by leveraging a more flexible nearest neighbor search strategy, thereby preventing the exclusion of repetitive yet valid matches during the early stages. Our second technical contribution is the integration of a patch descriptor, which extends the applicability of DFM to accommodate a wide range of backbone networks pre-trained across diverse computer vision tasks, including image classification, semantic segmentation, and stereo matching. Taking into account the practical applicability of our method in real-world robotics applications, we also propose a novel patch descriptor distillation strategy to further reduce the computational complexity of correspondence matching. Extensive experiments conducted on three public datasets demonstrate the superior performance of our proposed method. Specifically, it achieves an overall performance in terms of mean matching accuracy of 0.68, 0.92, and 0.95 with respect to the tolerances of 1, 3, and 5 pixels, respectively, on the HPatches dataset, outperforming all other SoTA algorithms. Our source code, demo video, and supplement are publicly available at mias.group/GCM.
Authors: Purna Kar, Jordan J. Bird, Yangang Xing, Alexander Sumich, Andrew Knight, Ahmad Lotfi, Benedict Carpenter van Barthold
Abstract: Biophilia is an innate love for living things and nature itself that has been associated with a positive impact on mental health and well-being. This study explores the application of deep learning methods for the classification of Biophilic artwork, in order to learn and explain the different Biophilic characteristics present in a visual representation of a painting. Using the concept of Biophilia that postulates the deep connection of human beings with nature, we use an artificially intelligent algorithm to recognise the different patterns underlying the Biophilic features in an artwork. Our proposed method uses a lower-dimensional representation of an image and a decoder model to extract salient features of the image of each Biophilic trait, such as plants, water bodies, seasons, animals, etc., based on learnt factors such as shape, texture, and illumination. The proposed classification model is capable of extracting Biophilic artwork that not only helps artists, collectors, and researchers studying to interpret and exploit the effects of mental well-being on exposure to nature-inspired visual aesthetics but also enables a methodical exploration of the study of Biophilia and Biophilic artwork for aesthetic preferences. Using the proposed algorithms, we have also created a gallery of Biophilic collections comprising famous artworks from different European and American art galleries, which will soon be published on the Vieunite@ online community.
Authors: Zhengrui Guo, Jiabo Ma, Yingxue Xu, Yihui Wang, Liansheng Wang, Hao Chen
Abstract: Histopathology serves as the gold standard in cancer diagnosis, with clinical reports being vital in interpreting and understanding this process, guiding cancer treatment and patient care. The automation of histopathology report generation with deep learning stands to significantly enhance clinical efficiency and lessen the labor-intensive, time-consuming burden on pathologists in report writing. In pursuit of this advancement, we introduce HistGen, a multiple instance learning-empowered framework for histopathology report generation together with the first benchmark dataset for evaluation. Inspired by diagnostic and report-writing workflows, HistGen features two delicately designed modules, aiming to boost report generation by aligning whole slide images (WSIs) and diagnostic reports from local and global granularity. To achieve this, a local-global hierarchical encoder is developed for efficient visual feature aggregation from a region-to-slide perspective. Meanwhile, a cross-modal context module is proposed to explicitly facilitate alignment and interaction between distinct modalities, effectively bridging the gap between the extensive visual sequences of WSIs and corresponding highly summarized reports. Experimental results on WSI report generation show the proposed model outperforms state-of-the-art (SOTA) models by a large margin. Moreover, the results of fine-tuning our model on cancer subtyping and survival analysis tasks further demonstrate superior performance compared to SOTA methods, showcasing strong transfer learning capability. Dataset, model weights, and source code are available in https://github.com/dddavid4real/HistGen.
Authors: Peidong Li, Wancheng Shen, Qihao Huang, Dixiao Cui
Abstract: Camera-based Bird's-Eye-View (BEV) perception often struggles between adopting 3D-to-2D or 2D-to-3D view transformation (VT). The 3D-to-2D VT typically employs resource intensive Transformer to establish robust correspondences between 3D and 2D feature, while the 2D-to-3D VT utilizes the Lift-Splat-Shoot (LSS) pipeline for real-time application, potentially missing distant information. To address these limitations, we propose DualBEV, a unified framework that utilizes a shared CNN-based feature transformation incorporating three probabilistic measurements for both strategies. By considering dual-view correspondences in one-stage, DualBEV effectively bridges the gap between these strategies, harnessing their individual strengths. Our method achieves state-of-the-art performance without Transformer, delivering comparable efficiency to the LSS approach, with 55.2% mAP and 63.4% NDS on the nuScenes test set. Code will be released at https://github.com/PeidongLi/DualBEV.
Authors: Yahao Lu, Yupei Lin, Han Wu, Xiaoyu Xian, Yukai Shi, Liang Lin
Abstract: Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. Recently, convolutional neural networks have achieved significant advantages in general object detection. With the development of Transformer, the scale of SIRST models is constantly increasing. Due to the limited training samples, performance has not been improved accordingly. The quality, quantity, and diversity of the infrared dataset are critical to the detection of small targets. To highlight this issue, we propose a negative sample augmentation method in this paper. Specifically, a negative augmentation approach is proposed to generate massive negatives for self-supervised learning. Firstly, we perform a sequential noise modeling technology to generate realistic infrared data. Secondly, we fuse the extracted noise with the original data to facilitate diversity and fidelity in the generated data. Lastly, we proposed a negative augmentation strategy to enrich diversity as well as maintain semantic invariance. The proposed algorithm produces a synthetic SIRST-5K dataset, which contains massive pseudo-data and corresponding labels. With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed. Compared with other state-of-the-art (SOTA) methods, our method achieves outstanding performance in terms of probability of detection (Pd), false-alarm rate (Fa), and intersection over union (IoU).
Authors: Mubashir Noman, Muzammal Naseer, Hisham Cholakkal, Rao Muhammad Anwar, Salman Khan, Fahad Shahbaz Khan
Abstract: Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. Different from standard natural image datasets, remote sensing data is acquired from various sensor technologies and exhibit diverse range of scale variations as well as modalities. Existing satellite image pre-training methods either ignore the scale information present in the remote sensing imagery or restrict themselves to use only a single type of data modality. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities. Our proposed approach, named SatMAE++, performs multi-scale pre-training and utilizes convolution based upsampling blocks to reconstruct the image at higher scales making it extensible to include more scales. Compared to existing works, the proposed SatMAE++ with multi-scale pre-training is equally effective for both optical as well as multi-spectral imagery. Extensive experiments on six datasets reveal the merits of proposed contributions, leading to state-of-the-art performance on all datasets. SatMAE++ achieves mean average precision (mAP) gain of 2.5\% for multi-label classification task on BigEarthNet dataset. Our code and pre-trained models are available at \url{https://github.com/techmn/satmae_pp}.
Authors: Huiming Sun, Jiacheng Guo, Zibo Meng, Tianyun Zhang, Jianwu Fang, Yuewei Lin, Hongkai Yu
Abstract: Vehicle detection in Unmanned Aerial Vehicle (UAV) captured images has wide applications in aerial photography and remote sensing. There are many public benchmark datasets proposed for the vehicle detection and tracking in UAV images. Recent studies show that adding an adversarial patch on objects can fool the well-trained deep neural networks based object detectors, posing security concerns to the downstream tasks. However, the current public UAV datasets might ignore the diverse altitudes, vehicle attributes, fine-grained instance-level annotation in mostly side view with blurred vehicle roof, so none of them is good to study the adversarial patch based vehicle detection attack problem. In this paper, we propose a new dataset named EVD4UAV as an altitude-sensitive benchmark to evade vehicle detection in UAV with 6,284 images and 90,886 fine-grained annotated vehicles. The EVD4UAV dataset has diverse altitudes (50m, 70m, 90m), vehicle attributes (color, type), fine-grained annotation (horizontal and rotated bounding boxes, instance-level mask) in top view with clear vehicle roof. One white-box and two black-box patch based attack methods are implemented to attack three classic deep neural networks based object detectors on EVD4UAV. The experimental results show that these representative attack methods could not achieve the robust altitude-insensitive attack performance.
Authors: Chenhui Zhao, Liyue Shen
Abstract: Precision medicine, such as patient-adaptive treatments utilizing medical images, poses new challenges for image segmentation algorithms due to (1) the large variability across different patients and (2) the limited availability of annotated data for each patient. In this work, we propose a data-efficient segmentation method to address these challenges, namely Part-aware Personalized Segment Anything Model (P^2SAM). Without any model fine-tuning, P^2SAM enables seamless adaptation to any new patients relying only on one-shot patient-specific data. We introduce a novel part-aware prompt mechanism to select multiple-point prompts based on part-level features of the one-shot data. To further promote the robustness of the selected prompt, we propose a retrieval approach to handle outlier prompts. Extensive experiments demonstrate that P^2SAM improves the performance by +8.0% and +2.0% mean Dice score within two patient-specific segmentation settings, and exhibits impressive generality across different application domains, e.g., +6.4% mIoU on the PerSeg benchmark. Code will be released upon acceptance.
Authors: Anindya Mondal, Sauradip Nag, Xiatian Zhu, Anjan Dutta
Abstract: Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies come with their own set of limitations, such as the need for manual exemplar input and multiple passes for multiple categories, resulting in significant inefficiencies. This paper introduces a new, more practical approach enabling simultaneous counting of multiple object categories using an open vocabulary framework. Our solution, OmniCount, stands out by using semantic and geometric insights from pre-trained models to count multiple categories of objects as specified by users, all without additional training. OmniCount distinguishes itself by generating precise object masks and leveraging point prompts via the Segment Anything Model for efficient counting. To evaluate OmniCount, we created the OmniCount-191 benchmark, a first-of-its-kind dataset with multi-label object counts, including points, bounding boxes, and VQA annotations. Our comprehensive evaluation in OmniCount-191, alongside other leading benchmarks, demonstrates OmniCount's exceptional performance, significantly outpacing existing solutions and heralding a new era in object counting technology.
Authors: Yabo Zhang, Yuxiang Wei, Xianhui Lin, Zheng Hui, Peiran Ren, Xuansong Xie, Xiangyang Ji, Wangmeng Zuo
Abstract: Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment, owing to insufficient quality and quantity of training videos. In this paper, we introduce VideoElevator, a training-free and plug-and-play method, which elevates the performance of T2V using superior capabilities of T2I. Different from conventional T2V sampling (i.e., temporal and spatial modeling), VideoElevator explicitly decomposes each sampling step into temporal motion refining and spatial quality elevating. Specifically, temporal motion refining uses encapsulated T2V to enhance temporal consistency, followed by inverting to the noise distribution required by T2I. Then, spatial quality elevating harnesses inflated T2I to directly predict less noisy latent, adding more photo-realistic details. We have conducted experiments in extensive prompts under the combination of various T2V and T2I. The results show that VideoElevator not only improves the performance of T2V baselines with foundational T2I, but also facilitates stylistic video synthesis with personalized T2I. Our code is available at https://github.com/YBYBZhang/VideoElevator.
Authors: Amir M. Mansourian, Arya Jalali, Rozhan Ahmadi, Shohreh Kasaei
Abstract: In contrast to existing complex methodologies commonly employed for distilling knowledge from a teacher to a student, the pro-posed method showcases the efficacy of a simple yet powerful method for utilizing refined feature maps to transfer attention. The proposed method has proven to be effective in distilling rich information, outperforming existing methods in semantic segmentation as a dense prediction task. The proposed Attention-guided Feature Distillation (AttnFD) method, em-ploys the Convolutional Block Attention Module (CBAM), which refines feature maps by taking into account both channel-specific and spatial information content. By only using the Mean Squared Error (MSE) loss function between the refined feature maps of the teacher and the student,AttnFD demonstrates outstanding performance in semantic segmentation, achieving state-of-the-art results in terms of mean Intersection over Union (mIoU) on the PascalVoc 2012 and Cityscapes datasets. The Code is available at https://github.com/AmirMansurian/AttnFD.
Authors: Royden Wagner, \"Omer \c{S}ahin Ta\c{s}, Marvin Klemp, Carlos Fernandez
Abstract: We present JointMotion, a self-supervised learning method for joint motion prediction in autonomous driving. Our method includes a scene-level objective connecting motion and environments, and an instance-level objective to refine learned representations. Our evaluations show that these objectives are complementary and outperform recent contrastive and autoencoding methods as pre-training for joint motion prediction. Furthermore, JointMotion adapts to all common types of environment representations used for motion prediction (i.e., agent-centric, scene-centric, and pairwise relative), and enables effective transfer learning between the Waymo Open Motion and the Argoverse 2 Forecasting datasets. Notably, our method improves the joint final displacement error of Wayformer, Scene Transformer, and HPTR by 3%, 7%, and 11%, respectively.
Authors: Scott Workman, Armin Hadzic
Abstract: This work addresses the task of modeling spatiotemporal traffic patterns directly from overhead imagery, which we refer to as image-driven traffic modeling. We extend this line of work and introduce a multi-modal, multi-task transformer-based segmentation architecture that can be used to create dense city-scale traffic models. Our approach includes a geo-temporal positional encoding module for integrating geo-temporal context and a probabilistic objective function for estimating traffic speeds that naturally models temporal variations. We evaluate our method extensively using the Dynamic Traffic Speeds (DTS) benchmark dataset and significantly improve the state-of-the-art. Finally, we introduce the DTS++ dataset to support mobility-related location adaptation experiments.
Authors: Yijiang Li, Sucheng Ren, Weipeng Deng, Yuzhi Xu, Ying Gao, Edith Ngai, Haohan Wang
Abstract: Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains that help models learn an invariant representation from the spurious features. Various domain augmentation have been proposed but largely rely on interpolating existing domains and frequently face difficulties in creating truly "novel" domains. Humans, on the other hand, can easily extrapolate novel domains, thus, an intriguing question arises: How can neural networks extrapolate like humans and achieve OOD generalization? We introduce a novel approach to domain extrapolation that leverages reasoning ability and the extensive knowledge encapsulated within large language models (LLMs) to synthesize entirely new domains. Starting with the class of interest, we query the LLMs to extract relevant knowledge for these novel domains. We then bridge the gap between the text-centric knowledge derived from LLMs and the pixel input space of the model using text-to-image generation techniques. By augmenting the training set of domain generalization datasets with high-fidelity, photo-realistic images of these new domains, we achieve significant improvements over all existing methods, as demonstrated in both single and multi-domain generalization across various benchmarks. With the ability to extrapolate any domains for any class, our method has the potential to learn a generalized model for any task without any data. To illustrate, we put forth a much more difficult setting termed, data-free domain generalization, that aims to learn a generalized model in the absence of any collected data. Our empirical findings support the above argument and our methods exhibit commendable performance in this setting, even surpassing the supervised setting by approximately 1-2\% on datasets such as VLCS.
Authors: Tarun Kalluri, Bodhisattwa Prasad Majumder, Manmohan Chandraker
Abstract: We introduce LaGTran, a novel framework that utilizes readily available or easily acquired text descriptions to guide robust transfer of discriminative knowledge from labeled source to unlabeled target data with domain shifts. While unsupervised adaptation methods have been established to address this problem, they show limitations in handling challenging domain shifts due to their exclusive operation within the pixel-space. Motivated by our observation that semantically richer text modality has more favorable transfer properties, we devise a transfer mechanism to use a source-trained text-classifier to generate predictions on the target text descriptions, and utilize these predictions as supervision for the corresponding images. Our approach driven by language guidance is surprisingly easy and simple, yet significantly outperforms all prior approaches on challenging datasets like GeoNet and DomainNet, validating its extreme effectiveness. To further extend the scope of our study beyond images, we introduce a new benchmark to study ego-exo transfer in videos and find that our language-aided LaGTran yields significant gains in this highly challenging and non-trivial transfer setting. Code, models, and proposed datasets are publicly available at https://tarun005.github.io/lagtran/.
Authors: S Arut Prakash, Aditya Ganesh Kumar, Prabhu Shankar K. C., Lithicka Anandavel, Aditya Lakshmi Narayanan
Abstract: A user-centric design and resource optimization should be at the center of any technology or innovation. The user-centric perspective gives the developer the opportunity to develop with task-based optimization. The user in the medical image field is a medical professional who analyzes the medical images and gives their diagnosis results to the patient. This scheme, having the medical professional user's perspective, innovates in the area of Medical Image storage and security. The architecture is designed with three main segments, namely: Segmentation, Storage, and Retrieval. This architecture was designed owing to the fact that the number of retrieval operations done by medical professionals was toweringly higher when compared to the storage operations done for some handful number of times for a particular medical image. This gives room for our innovation to segment out the medically indispensable part of the medical image, encrypt it, and store it. By encrypting the vital parts of the image using a strong encryption algorithm like the chaotic Henon map, we are able to keep the security intact. Now retrieving the medical image demands only the computationally less stressing decryption of the segmented region of interest. The decryption of the segmented region of interest results in the full recovery of the medical image which can be viewed on demand by the medical professionals for various diagnosis purposes. In this scheme, we were able to achieve a retrieval speed improvement of around 47% when compared to a full image encryption of brain medical CT images.
Authors: Eric Easthope
Abstract: I show that a one-dimensional (1D) conditional generative adversarial network (cGAN) with an adversarial training architecture is capable of unpaired signal-to-signal ("sig2sig") translation. Using a simplified CycleGAN model with 1D layers and wider convolutional kernels, mirroring WaveGAN to reframe two-dimensional (2D) image generation as 1D audio generation, I show that recasting the 2D image-to-image translation task to a 1D signal-to-signal translation task with deep convolutional GANs is possible without substantial modification to the conventional U-Net model and adversarial architecture developed as CycleGAN. With this I show for a small tunable dataset that noisy test signals unseen by the 1D CycleGAN model and without paired training transform from the source domain to signals similar to paired test signals in the translated domain, especially in terms of frequency, and I quantify these differences in terms of correlation and error.
Authors: Gabriele Campanella, Eugene Fluder, Jennifer Zeng, Chad Vanderbilt, Thomas J. Fuchs
Abstract: Artificial Intelligence (AI) has great potential to improve health outcomes by training systems on vast digitized clinical datasets. Computational Pathology, with its massive amounts of microscopy image data and impact on diagnostics and biomarkers, is at the forefront of this development. Gigapixel pathology slides pose a unique challenge due to their enormous size and are usually divided into tens of thousands of smaller tiles for analysis. This results in a discontinuity in the machine learning process by separating the training of tile-level encoders from slide-level aggregators and the need to adopt weakly supervised learning strategies. Training models from entire pathology slides end-to-end has been largely unexplored due to its computational challenges. To overcome this problem, we propose a novel approach to jointly train both a tile encoder and a slide-aggregator fully in memory and end-to-end at high-resolution, bridging the gap between input and slide-level supervision. While more computationally expensive, detailed quantitative validation shows promise for large-scale pre-training of pathology foundation models.
Authors: Sudipta Paul, Bulent Yener, Amanda W. Lund
Abstract: Graph-based learning approaches, due to their ability to encode tissue/organ structure information, are increasingly favored for grading colorectal cancer histology images. Recent graph-based techniques involve dividing whole slide images (WSIs) into smaller or medium-sized patches, and then building graphs on each patch for direct use in training. This method, however, fails to capture the tissue structure information present in an entire WSI and relies on training from a significantly large dataset of image patches. In this paper, we propose a novel cell-to-patch graph convolutional network (C2P-GCN), which is a two-stage graph formation-based approach. In the first stage, it forms a patch-level graph based on the cell organization on each patch of a WSI. In the second stage, it forms an image-level graph based on a similarity measure between patches of a WSI considering each patch as a node of a graph. This graph representation is then fed into a multi-layer GCN-based classification network. Our approach, through its dual-phase graph construction, effectively gathers local structural details from individual patches and establishes a meaningful connection among all patches across a WSI. As C2P-GCN integrates the structural data of an entire WSI into a single graph, it allows our model to work with significantly fewer training data compared to the latest models for colorectal cancer. Experimental validation of C2P-GCN on two distinct colorectal cancer datasets demonstrates the effectiveness of our method.
Authors: Christopher D'Ambrosia, Florian Richter, Zih-Yun Chiu, Nikhil Shinde, Fei Liu, Henrik I. Christensen, Michael C. Yip
Abstract: Controlling robotic manipulators via visual feedback requires a known coordinate frame transformation between the robot and the camera. Uncertainties in mechanical systems as well as camera calibration create errors in this coordinate frame transformation. These errors result in poor localization of robotic manipulators and create a significant challenge for applications that rely on precise interactions between manipulators and the environment. In this work, we estimate the camera-to-base transform and joint angle measurement errors for surgical robotic tools using an image based insertion-shaft detection algorithm and probabilistic models. We apply our proposed approach in both a structured environment as well as an unstructured environment and measure to demonstrate the efficacy of our methods.
Authors: Jiapeng Wang, Chengyu Wang, Tingfeng Cao, Jun Huang, Lianwen Jin
Abstract: We present DiffChat, a novel method to align Large Language Models (LLMs) to "chat" with prompt-as-input Text-to-Image Synthesis (TIS) models (e.g., Stable Diffusion) for interactive image creation. Given a raw prompt/image and a user-specified instruction, DiffChat can effectively make appropriate modifications and generate the target prompt, which can be leveraged to create the target image of high quality. To achieve this, we first collect an instruction-following prompt engineering dataset named InstructPE for the supervised training of DiffChat. Next, we propose a reinforcement learning framework with the feedback of three core criteria for image creation, i.e., aesthetics, user preference, and content integrity. It involves an action-space dynamic modification technique to obtain more relevant positive samples and harder negative samples during the off-policy sampling. Content integrity is also introduced into the value estimation function for further improvement of produced images. Our method can exhibit superior performance than baseline models and strong competitors based on both automatic and human evaluations, which fully demonstrates its effectiveness.
Authors: Daniel H. Pak, Minliang Liu, Theodore Kim, Caglar Ozturk, Raymond McKay, Ellen T. Roche, Rudolph Gleason, James S. Duncan
Abstract: Calcification has significant influence over cardiovascular diseases and interventions. Detailed characterization of calcification is thus desired for predictive modeling, but calcified heart meshes for physics-driven simulations are still often reconstructed using manual operations. This poses a major bottleneck for large-scale adoption of computational simulations for research or clinical use. To address this, we propose an end-to-end automated meshing algorithm that enables robust incorporation of patient-specific calcification onto a given heart mesh. The algorithm provides a substantial speed-up from several hours of manual meshing to $\sim$1 minute of automated computation, and it solves an important problem that cannot be addressed with recent template registration-based heart meshing techniques. We validated our final calcified heart meshes with extensive simulations, demonstrating our ability to accurately model patient-specific aortic stenosis and Transcatheter Aortic Valve Replacement. Our method may serve as an important tool for accelerating the development and usage of physics-driven simulations for cardiac digital twins.
Authors: Dingkang Yang, Mingcheng Li, Dongling Xiao, Yang Liu, Kun Yang, Zhaoyu Chen, Yuzheng Wang, Peng Zhai, Ke Li, Lihua Zhang
Abstract: Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortunately, the current MSA task invariably suffers from unplanned dataset biases, particularly multimodal utterance-level label bias and word-level context bias. These harmful biases potentially mislead models to focus on statistical shortcuts and spurious correlations, causing severe performance bottlenecks. To alleviate these issues, we present a Multimodal Counterfactual Inference Sentiment (MCIS) analysis framework based on causality rather than conventional likelihood. Concretely, we first formulate a causal graph to discover harmful biases from already-trained vanilla models. In the inference phase, given a factual multimodal input, MCIS imagines two counterfactual scenarios to purify and mitigate these biases. Then, MCIS can make unbiased decisions from biased observations by comparing factual and counterfactual outcomes. We conduct extensive experiments on several standard MSA benchmarks. Qualitative and quantitative results show the effectiveness of the proposed framework.
Authors: Xin Zhu, Hongyi Pan, Yury Velichko, Adam B. Murphy, Ashley Ross, Baris Turkbey, Ahmet Enis Cetin, Ulas Bagci
Abstract: Magnetic field inhomogeneity correction remains a challenging task in MRI analysis. Most established techniques are designed for brain MRI by supposing that image intensities in the identical tissue follow a uniform distribution. Such an assumption cannot be easily applied to other organs, especially those that are small in size and heterogeneous in texture (large variations in intensity), such as the prostate. To address this problem, this paper proposes a probabilistic Hadamard U-Net (PHU-Net) for prostate MRI bias field correction. First, a novel Hadamard U-Net (HU-Net) is introduced to extract the low-frequency scalar field, multiplied by the original input to obtain the prototypical corrected image. HU-Net converts the input image from the time domain into the frequency domain via Hadamard transform. In the frequency domain, high-frequency components are eliminated using the trainable filter (scaling layer), hard-thresholding layer, and sparsity penalty. Next, a conditional variational autoencoder is used to encode possible bias field-corrected variants into a low-dimensional latent space. Random samples drawn from latent space are then incorporated with a prototypical corrected image to generate multiple plausible images. Experimental results demonstrate the effectiveness of PHU-Net in correcting bias-field in prostate MRI with a fast inference speed. It has also been shown that prostate MRI segmentation accuracy improves with the high-quality corrected images from PHU-Net. The code will be available in the final version of this manuscript.
Authors: Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang, Xiangru Lin, Yu Zhang, Mingming Fan, Zeyu Wang
Abstract: We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We disentangle the motion and appearance of a virtual human with explicit mesh geometry and implicit appearance modeling with Gaussian Splatting. The Gaussians are defined by barycentric coordinates and displacement on a triangle mesh as Phong surfaces. We extend lifted optimization to simultaneously optimize the parameters of the Gaussians while walking on the triangle mesh. SplattingAvatar is a hybrid representation of virtual humans where the mesh represents low-frequency motion and surface deformation, while the Gaussians take over the high-frequency geometry and detailed appearance. Unlike existing deformation methods that rely on an MLP-based linear blend skinning (LBS) field for motion, we control the rotation and translation of the Gaussians directly by mesh, which empowers its compatibility with various animation techniques, e.g., skeletal animation, blend shapes, and mesh editing. Trainable from monocular videos for both full-body and head avatars, SplattingAvatar shows state-of-the-art rendering quality across multiple datasets.
Authors: Ping Guo, Cheng Gong, Xi Lin, Zhiyuan Yang, Qingfu Zhang
Abstract: The escalating threat of adversarial attacks on deep learning models, particularly in security-critical fields, has underscored the need for robust deep learning systems. Conventional robustness evaluations have relied on adversarial accuracy, which measures a model's performance under a specific perturbation intensity. However, this singular metric does not fully encapsulate the overall resilience of a model against varying degrees of perturbation. To address this gap, we propose a new metric termed adversarial hypervolume, assessing the robustness of deep learning models comprehensively over a range of perturbation intensities from a multi-objective optimization standpoint. This metric allows for an in-depth comparison of defense mechanisms and recognizes the trivial improvements in robustness afforded by less potent defensive strategies. Additionally, we adopt a novel training algorithm that enhances adversarial robustness uniformly across various perturbation intensities, in contrast to methods narrowly focused on optimizing adversarial accuracy. Our extensive empirical studies validate the effectiveness of the adversarial hypervolume metric, demonstrating its ability to reveal subtle differences in robustness that adversarial accuracy overlooks. This research contributes a new measure of robustness and establishes a standard for assessing and benchmarking the resilience of current and future defensive models against adversarial threats.
Authors: Junyu Chen, Yihao Liu, Shuwen Wei, Zhangxing Bian, Aaron Carass, Yong Du
Abstract: Understanding the uncertainty inherent in deep learning-based image registration models has been an ongoing area of research. Existing methods have been developed to quantify both transformation and appearance uncertainties related to the registration process, elucidating areas where the model may exhibit ambiguity regarding the generated deformation. However, our study reveals that neither uncertainty effectively estimates the potential errors when the registration model is used for label propagation. Here, we propose a novel framework to concurrently estimate both the epistemic and aleatoric segmentation uncertainties for image registration. To this end, we implement a compact deep neural network (DNN) designed to transform the appearance discrepancy in the warping into aleatoric segmentation uncertainty by minimizing a negative log-likelihood loss function. Furthermore, we present epistemic segmentation uncertainty within the label propagation process as the entropy of the propagated labels. By introducing segmentation uncertainty along with existing methods for estimating registration uncertainty, we offer vital insights into the potential uncertainties at different stages of image registration. We validated our proposed framework using publicly available datasets, and the results prove that the segmentation uncertainties estimated with the proposed method correlate well with errors in label propagation, all while achieving superior registration performance.
Authors: Elisabeth J. Schiessler, Roland C. Aydin, Christian J. Cyron
Abstract: We present ECToNAS, a cost-efficient evolutionary cross-topology neural architecture search algorithm that does not require any pre-trained meta controllers. Our framework is able to select suitable network architectures for different tasks and hyperparameter settings, independently performing cross-topology optimisation where required. It is a hybrid approach that fuses training and topology optimisation together into one lightweight, resource-friendly process. We demonstrate the validity and power of this approach with six standard data sets (CIFAR-10, CIFAR-100, EuroSAT, Fashion MNIST, MNIST, SVHN), showcasing the algorithm's ability to not only optimise the topology within an architectural type, but also to dynamically add and remove convolutional cells when and where required, thus crossing boundaries between different network types. This enables researchers without a background in machine learning to make use of appropriate model types and topologies and to apply machine learning methods in their domains, with a computationally cheap, easy-to-use cross-topology neural architecture search framework that fully encapsulates the topology optimisation within the training process.
Authors: Joseph Cho, Fachrina Dewi Puspitasari, Sheng Zheng, Jingyao Zheng, Lik-Hang Lee, Tae-Ho Kim, Choong Seon Hong, Chaoning Zhang
Abstract: Text-to-video generation marks a significant frontier in the rapidly evolving domain of generative AI, integrating advancements in text-to-image synthesis, video captioning, and text-guided editing. This survey critically examines the progression of text-to-video technologies, focusing on the shift from traditional generative models to the cutting-edge Sora model, highlighting developments in scalability and generalizability. Distinguishing our analysis from prior works, we offer an in-depth exploration of the technological frameworks and evolutionary pathways of these models. Additionally, we delve into practical applications and address ethical and technological challenges such as the inability to perform multiple entity handling, comprehend causal-effect learning, understand physical interaction, perceive object scaling and proportioning, and combat object hallucination which is also a long-standing problem in generative models. Our comprehensive discussion covers the topic of enablement of text-to-video generation models as human-assistive tools and world models, as well as eliciting model's shortcomings and summarizing future improvement direction that mainly centers around training datasets and evaluation metrics (both automatic and human-centered). Aimed at both newcomers and seasoned researchers, this survey seeks to catalyze further innovation and discussion in the growing field of text-to-video generation, paving the way for more reliable and practical generative artificial intelligence technologies.
Authors: Gido M. van de Ven, Nicholas Soures, Dhireesha Kudithipudi
Abstract: This book chapter delves into the dynamics of continual learning, which is the process of incrementally learning from a non-stationary stream of data. Although continual learning is a natural skill for the human brain, it is very challenging for artificial neural networks. An important reason is that, when learning something new, these networks tend to quickly and drastically forget what they had learned before, a phenomenon known as catastrophic forgetting. Especially in the last decade, continual learning has become an extensively studied topic in deep learning. This book chapter reviews the insights that this field has generated.
Authors: Eda Yilmaz, Hacer Yalim Keles
Abstract: Knowledge Distillation (KD) facilitates the transfer of discriminative capabilities from an advanced teacher model to a simpler student model, ensuring performance enhancement without compromising accuracy. It is also exploited for model stealing attacks, where adversaries use KD to mimic the functionality of a teacher model. Recent developments in this domain have been influenced by the Stingy Teacher model, which provided empirical analysis showing that sparse outputs can significantly degrade the performance of student models. Addressing the risk of intellectual property leakage, our work introduces an approach to train a teacher model that inherently protects its logits, influenced by the Nasty Teacher concept. Differing from existing methods, we incorporate sparse outputs of adversarial examples with standard training data to strengthen the teacher's defense against student distillation. Our approach carefully reduces the relative entropy between the original and adversarially perturbed outputs, allowing the model to produce adversarial logits with minimal impact on overall performance. The source codes will be made publicly available soon.
Authors: Yazhe Li, Jorg Bornschein, Ting Chen
Abstract: In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squared Error (MSE) alone leads to strong representations. To enhance the image generation ability, we replace the MSE loss with the diffusion objective by using a denoising patch decoder. We show that the learned representation can be improved by using tailored noise schedules and longer training in larger models. Notably, the optimal schedule differs significantly from the typical ones used in standard image diffusion models. Overall, despite its simple architecture, DARL delivers performance remarkably close to state-of-the-art masked prediction models under the fine-tuning protocol. This marks an important step towards a unified model capable of both visual perception and generation, effectively combining the strengths of autoregressive and denoising diffusion models.
Authors: Jinha Park, Wonguk Cho, Taesup Kim
Abstract: While there have been considerable advancements in machine learning driven by extensive datasets, a significant disparity still persists in the availability of data across various sources and populations. This inequality across domains poses challenges in modeling for those with limited data, which can lead to profound practical and ethical concerns. In this paper, we address a representative case of data inequality problem across domains termed Semi-Supervised Domain Generalization (SSDG), in which only one domain is labeled while the rest are unlabeled. We propose a novel algorithm, ProUD, which can effectively learn domain-invariant features via domain-aware prototypes along with progressive generalization via uncertainty-adaptive mixing of labeled and unlabeled domains. Our experiments on three different benchmark datasets demonstrate the effectiveness of ProUD, outperforming all baseline models including single domain generalization and semi-supervised learning. Source code will be released upon acceptance of the paper.
Authors: Hamed Hosseini, Mehdi Tale Masouleh, Ahmad Kalhor
Abstract: Robotic grasp should be carried out in a real-time manner by proper accuracy. Perception is the first and significant step in this procedure. This paper proposes an improved pipeline model trying to detect grasp as a rectangle representation for different seen or unseen objects. It helps the robot to start control procedures from nearer to the proper part of the object. The main idea consists in pre-processing, output normalization, and data augmentation to improve accuracy by 4.3 percent without making the system slow. Also, a comparison has been conducted over different pre-trained models like AlexNet, ResNet, Vgg19, which are the most famous feature extractors for image processing in object detection. Although AlexNet has less complexity than other ones, it outperformed them, which helps the real-time property.
Authors: Shoujin Huang, Guanxiong Luo, Xi Wang, Ziran Chen, Yuwan Wang, Huaishui Yang, Pheng-Ann Heng, Lingyan Zhang, Mengye Lyu
Abstract: In general, diffusion model-based MRI reconstruction methods incrementally remove artificially added noise while imposing data consistency to reconstruct the underlying images. However, real-world MRI acquisitions already contain inherent noise due to thermal fluctuations. This phenomenon is particularly notable when using ultra-fast, high-resolution imaging sequences for advanced research, or using low-field systems favored by low- and middle-income countries. These common scenarios can lead to sub-optimal performance or complete failure of existing diffusion model-based reconstruction techniques. Specifically, as the artificially added noise is gradually removed, the inherent MRI noise becomes increasingly pronounced, making the actual noise level inconsistent with the predefined denoising schedule and consequently inaccurate image reconstruction. To tackle this problem, we propose a posterior sampling strategy with a novel NoIse Level Adaptive Data Consistency (Nila-DC) operation. Extensive experiments are conducted on two public datasets and an in-house clinical dataset with field strength ranging from 0.3T to 3T, showing that our method surpasses the state-of-the-art MRI reconstruction methods, and is highly robust against various noise levels. The code will be released after review.
Authors: Weibin Liao, Yinghao Zhu, Xinyuan Wang, Cehngwei Pan, Yasha Wang, Liantao Ma
Abstract: UNet and its variants have been widely used in medical image segmentation. However, these models, especially those based on Transformer architectures, pose challenges due to their large number of parameters and computational loads, making them unsuitable for mobile health applications. Recently, State Space Models (SSMs), exemplified by Mamba, have emerged as competitive alternatives to CNN and Transformer architectures. Building upon this, we employ Mamba as a lightweight substitute for CNN and Transformer within UNet, aiming at tackling challenges stemming from computational resource limitations in real medical settings. To this end, we introduce the Lightweight Mamba UNet (LightM-UNet) that integrates Mamba and UNet in a lightweight framework. Specifically, LightM-UNet leverages the Residual Vision Mamba Layer in a pure Mamba fashion to extract deep semantic features and model long-range spatial dependencies, with linear computational complexity. Extensive experiments conducted on two real-world 2D/3D datasets demonstrate that LightM-UNet surpasses existing state-of-the-art literature. Notably, when compared to the renowned nnU-Net, LightM-UNet achieves superior segmentation performance while drastically reducing parameter and computation costs by 116x and 21x, respectively. This highlights the potential of Mamba in facilitating model lightweighting. Our code implementation is publicly available at https://github.com/MrBlankness/LightM-UNet.
Authors: Ziqi Gao, Yue Zhang, Xinwen Liu, Kaiyan Li, S. Kevin Zhou
Abstract: Multi-contrast (MC) Magnetic Resonance Imaging (MRI) reconstruction aims to incorporate a reference image of auxiliary modality to guide the reconstruction process of the target modality. Known MC reconstruction methods perform well with a fully sampled reference image, but usually exhibit inferior performance, compared to single-contrast (SC) methods, when the reference image is missing or of low quality. To address this issue, we propose DuDoUniNeXt, a unified dual-domain MRI reconstruction network that can accommodate to scenarios involving absent, low-quality, and high-quality reference images. DuDoUniNeXt adopts a hybrid backbone that combines CNN and ViT, enabling specific adjustment of image domain and k-space reconstruction. Specifically, an adaptive coarse-to-fine feature fusion module (AdaC2F) is devised to dynamically process the information from reference images of varying qualities. Besides, a partially shared shallow feature extractor (PaSS) is proposed, which uses shared and distinct parameters to handle consistent and discrepancy information among contrasts. Experimental results demonstrate that the proposed model surpasses state-of-the-art SC and MC models significantly. Ablation studies show the effectiveness of the proposed hybrid backbone, AdaC2F, PaSS, and the dual-domain unified learning scheme.
Authors: Erik Ostrowski, Muhammad Shafique
Abstract: When deploying neural networks in real-life situations, the size and computational effort are often the limiting factors. This is especially true in environments where big, expensive hardware is not affordable, like in embedded medical devices, where budgets are often tight. State-of-the-art proposed multiple different lightweight solutions for such use cases, mostly by changing the base model architecture, not taking the input and output resolution into consideration. In this paper, we propose our architecture that takes advantage of the fact that in hardware-limited environments, we often refrain from using the highest available input resolutions to guarantee a higher throughput. Although using lower-resolution input leads to a significant reduction in computing and memory requirements, it may also incur reduced prediction quality. Our architecture addresses this problem by exploiting the fact that we can still utilize high-resolution ground-truths in training. The proposed model inputs lower-resolution images and high-resolution ground truths, which can improve the prediction quality by 5.5% while adding less than 200 parameters to the model. %reducing the frames per second only from 25 to 20. We conduct an extensive analysis to illustrate that our architecture enhances existing state-of-the-art frameworks for lightweight semantic segmentation of cancer in MRI images. We also tested the deployment speed of state-of-the-art lightweight networks and our architecture on Nvidia's Jetson Nano to emulate deployment in resource-constrained embedded scenarios.
Authors: Maleka Khatun, Md Manowarul Islam, Habibur Rahman Rifat, Md. Shamim Bin Shahid, Md. Alamin Talukder, Md Ashraf Uddin
Abstract: Brain-related diseases are more sensitive than other diseases due to several factors, including the complexity of surgical procedures, high costs, and other challenges. Alzheimer's disease is a common brain disorder that causes memory loss and the shrinking of brain cells. Early detection is critical for providing proper treatment to patients. However, identifying Alzheimer's at an early stage using manual scanning of CT or MRI scans is challenging. Therefore, researchers have delved into the exploration of computer-aided systems, employing Machine Learning and Deep Learning methodologies, which entail the training of datasets to detect Alzheimer's disease. This study aims to present a hybrid model that combines a CNN model's feature extraction capabilities with an LSTM model's detection capabilities. This study has applied the transfer learning called VGG16 in the hybrid model to extract features from MRI images. The LSTM detects features between the convolution layer and the fully connected layer. The output layer of the fully connected layer uses the softmax function. The training of the hybrid model involved utilizing the ADNI dataset. The trial findings revealed that the model achieved a level of accuracy of 98.8%, a sensitivity rate of 100%, and a specificity rate of 76%. The proposed hybrid model outperforms its contemporary CNN counterparts, showcasing a superior performance.
Authors: Mahyar Gohari, Paolo Bestagini, Sergio Benini, Nicola Adami
Abstract: In the domain of music production and audio processing, the implementation of automatic pitch correction of the singing voice, also known as Auto-Tune, has significantly transformed the landscape of vocal performance. While auto-tuning technology has offered musicians the ability to tune their vocal pitches and achieve a desired level of precision, its use has also sparked debates regarding its impact on authenticity and artistic integrity. As a result, detecting and analyzing Auto-Tuned vocals in music recordings has become essential for music scholars, producers, and listeners. However, to the best of our knowledge, no prior effort has been made in this direction. This study introduces a data-driven approach leveraging triplet networks for the detection of Auto-Tuned songs, backed by the creation of a dataset composed of original and Auto-Tuned audio clips. The experimental results demonstrate the superiority of the proposed method in both accuracy and robustness compared to Rawnet2, an end-to-end model proposed for anti-spoofing and widely used for other audio forensic tasks.
Authors: Cristiana Tiago, Andrew Gilbert, Ahmed S. Beela, Svein Arne Aase, Sten Roar Snare, Jurica Sprem
Abstract: Due to privacy issues and limited amount of publicly available labeled datasets in the domain of medical imaging, we propose an image generation pipeline to synthesize 3D echocardiographic images with corresponding ground truth labels, to alleviate the need for data collection and for laborious and error-prone human labeling of images for subsequent Deep Learning (DL) tasks. The proposed method utilizes detailed anatomical segmentations of the heart as ground truth label sources. This initial dataset is combined with a second dataset made up of real 3D echocardiographic images to train a Generative Adversarial Network (GAN) to synthesize realistic 3D cardiovascular Ultrasound images paired with ground truth labels. To generate the synthetic 3D dataset, the trained GAN uses high resolution anatomical models from Computed Tomography (CT) as input. A qualitative analysis of the synthesized images showed that the main structures of the heart are well delineated and closely follow the labels obtained from the anatomical models. To assess the usability of these synthetic images for DL tasks, segmentation algorithms were trained to delineate the left ventricle, left atrium, and myocardium. A quantitative analysis of the 3D segmentations given by the models trained with the synthetic images indicated the potential use of this GAN approach to generate 3D synthetic data, use the data to train DL models for different clinical tasks, and therefore tackle the problem of scarcity of 3D labeled echocardiography datasets.
Authors: Yuxi Liu, Guibo Luo, Yuesheng Zhu
Abstract: Medical image segmentation is crucial for clinical diagnosis. The Segmentation Anything Model (SAM) serves as a powerful foundation model for visual segmentation and can be adapted for medical image segmentation. However, medical imaging data typically contain privacy-sensitive information, making it challenging to train foundation models with centralized storage and sharing. To date, there are few foundation models tailored for medical image deployment within the federated learning framework, and the segmentation performance, as well as the efficiency of communication and training, remain unexplored. In response to these issues, we developed Federated Foundation models for Medical image Segmentation (FedFMS), which includes the Federated SAM (FedSAM) and a communication and training-efficient Federated SAM with Medical SAM Adapter (FedMSA). Comprehensive experiments on diverse datasets are conducted to investigate the performance disparities between centralized training and federated learning across various configurations of FedFMS. The experiments revealed that FedFMS could achieve performance comparable to models trained via centralized training methods while maintaining privacy. Furthermore, FedMSA demonstrated the potential to enhance communication and training efficiency. Our model implementation codes are available at https://github.com/LIU-YUXI/FedFMS.
Authors: Amir Aghabiglou, Chung San Chu, Arwa Dabbech, Yves Wiaux
Abstract: Radio-interferometric (RI) imaging entails solving high-resolution high-dynamic range inverse problems from large data volumes. Recent image reconstruction techniques grounded in optimization theory have demonstrated remarkable capability for imaging precision, well beyond CLEAN's capability. These range from advanced proximal algorithms propelled by handcrafted regularization operators, such as the SARA family, to hybrid plug-and-play (PnP) algorithms propelled by learned regularization denoisers, such as AIRI. Optimization and PnP structures are however highly iterative, which hinders their ability to handle the extreme data sizes expected from future instruments. To address this scalability challenge, we introduce a novel deep learning approach, dubbed ``Residual-to-Residual DNN series for high-Dynamic range imaging'. R2D2's reconstruction is formed as a series of residual images, iteratively estimated as outputs of Deep Neural Networks (DNNs) taking the previous iteration's image estimate and associated data residual as inputs. It thus takes a hybrid structure between a PnP algorithm and a learned version of the matching pursuit algorithm that underpins CLEAN. We present a comprehensive study of our approach, featuring its multiple incarnations distinguished by their DNN architectures. We provide a detailed description of its training process, targeting a telescope-specific approach. R2D2's capability to deliver high precision is demonstrated in simulation, across a variety of image and observation settings using the Very Large Array (VLA). Its reconstruction speed is also demonstrated: with only few iterations required to clean data residuals at dynamic ranges up to 105, R2D2 opens the door to fast precision imaging. R2D2 codes are available in the BASPLib library on GitHub.
Authors: Yu Xiang, Sai Haneesh Allu, Rohith Peddi, Tyler Summers, Vibhav Gogate
Abstract: We introduce a new trajectory optimization method for robotic grasping based on a point-cloud representation of robots and task spaces. In our method, robots are represented by 3D points on their link surfaces. The task space of a robot is represented by a point cloud that can be obtained from depth sensors. Using the point-cloud representation, goal reaching in grasping can be formulated as point matching, while collision avoidance can be efficiently achieved by querying the signed distance values of the robot points in the signed distance field of the scene points. Consequently, a constrained non-linear optimization problem is formulated to solve the joint motion and grasp planning problem. The advantage of our method is that the point-cloud representation is general to be used with any robot in any environment. We demonstrate the effectiveness of our method by conducting experiments on a tabletop scene and a shelf scene for grasping with a Fetch mobile manipulator and a Franka Panda arm.
Authors: Adrian de Wynter
Abstract: We show that GPT-4's reasoning and planning capabilities extend to the 1993 first-person shooter Doom. This large language model (LLM) is able to run and play the game with only a few instructions, plus a textual description--generated by the model itself from screenshots--about the state of the game being observed. We find that GPT-4 can play the game to a passable degree: it is able to manipulate doors, combat enemies, and perform pathing. More complex prompting strategies involving multiple model calls provide better results. While further work is required to enable the LLM to play the game as well as its classical, reinforcement learning-based counterparts, we note that GPT-4 required no training, leaning instead on its own reasoning and observational capabilities. We hope our work pushes the boundaries on intelligent, LLM-based agents in video games. We conclude by discussing the ethical implications of our work.
Authors: Amitis Shidani, Devon Hjelm, Jason Ramapuram, Russ Webb, Eeshan Gunesh Dhekane, Dan Busbridge
Abstract: Contrastive learning typically matches pairs of related views among a number of unrelated negative views. Views can be generated (e.g. by augmentations) or be observed. We investigate matching when there are more than two related views which we call poly-view tasks, and derive new representation learning objectives using information maximization and sufficient statistics. We show that with unlimited computation, one should maximize the number of related views, and with a fixed compute budget, it is beneficial to decrease the number of unique samples whilst increasing the number of views of those samples. In particular, poly-view contrastive models trained for 128 epochs with batch size 256 outperform SimCLR trained for 1024 epochs at batch size 4096 on ImageNet1k, challenging the belief that contrastive models require large batch sizes and many training epochs.
Authors: Lorenzo Brigato, Stavroula Mougiakakou
Abstract: We introduce Tune without Validation (Twin), a pipeline for tuning learning rate and weight decay without validation sets. We leverage a recent theoretical framework concerning learning phases in hypothesis space to devise a heuristic that predicts what hyper-parameter (HP) combinations yield better generalization. Twin performs a grid search of trials according to an early-/non-early-stopping scheduler and then segments the region that provides the best results in terms of training loss. Among these trials, the weight norm strongly correlates with predicting generalization. To assess the effectiveness of Twin, we run extensive experiments on 20 image classification datasets and train several families of deep networks, including convolutional, transformer, and feed-forward models. We demonstrate proper HP selection when training from scratch and fine-tuning, emphasizing small-sample scenarios.
Authors: Dominik Rivoir, Isabel Funke, Stefanie Speidel
Abstract: Batch Normalization's (BN) unique property of depending on other samples in a batch is known to cause problems in several tasks, including sequence modeling. Yet, BN-related issues are hardly studied for long video understanding, despite the ubiquitous use of BN in CNNs (Convolutional Neural Networks) for feature extraction. Especially in surgical workflow analysis, where the lack of pretrained feature extractors has led to complex, multi-stage training pipelines, limited awareness of BN issues may have hidden the benefits of training CNNs and temporal models end to end. In this paper, we analyze pitfalls of BN in video learning, including issues specific to online tasks such as a 'cheating' effect in anticipation. We observe that BN's properties create major obstacles for end-to-end learning. However, using BN-free backbones, even simple CNN-LSTMs beat the state of the art {\color{\colorrevtwo}on three surgical workflow benchmarks} by utilizing adequate end-to-end training strategies which maximize temporal context. We conclude that awareness of BN's pitfalls is crucial for effective end-to-end learning in surgical tasks. By reproducing results on natural-video datasets, we hope our insights will benefit other areas of video learning as well. Code is available at: \url{https://gitlab.com/nct_tso_public/pitfalls_bn}
Authors: Yue Wang, Ran Yi, Luying Li, Ying Tai, Chengjie Wang, Lizhuang Ma
Abstract: Generating artistic portraits is a challenging problem in computer vision. Existing portrait stylization models that generate good quality results are based on Image-to-Image Translation and require abundant data from both source and target domains. However, without enough data, these methods would result in overfitting. In this work, we propose CtlGAN, a new few-shot artistic portraits generation model with a novel contrastive transfer learning strategy. We adapt a pretrained StyleGAN in the source domain to a target artistic domain with no more than 10 artistic faces. To reduce overfitting to the few training examples, we introduce a novel Cross-Domain Triplet loss which explicitly encourages the target instances generated from different latent codes to be distinguishable. We propose a new encoder which embeds real faces into Z+ space and proposes a dual-path training strategy to better cope with the adapted decoder and eliminate the artifacts. Extensive qualitative, quantitative comparisons and a user study show our method significantly outperforms state-of-the-arts under 10-shot and 1-shot settings and generates high quality artistic portraits. The code will be made publicly available.
Authors: Zhangyang Xiong, Dong Du, Yushuang Wu, Jingqi Dong, Di Kang, Linchao Bao, Xiaoguang Han
Abstract: It is very challenging to accurately reconstruct sophisticated human geometry caused by various poses and garments from a single image. Recently, works based on pixel-aligned implicit function (PIFu) have made a big step and achieved state-of-the-art fidelity on image-based 3D human digitization. However, the training of PIFu relies heavily on expensive and limited 3D ground truth data (i.e. synthetic data), thus hindering its generalization to more diverse real world images. In this work, we propose an end-to-end self-supervised network named SelfPIFu to utilize abundant and diverse in-the-wild images, resulting in largely improved reconstructions when tested on unconstrained in-the-wild images. At the core of SelfPIFu is the depth-guided volume-/surface-aware signed distance fields (SDF) learning, which enables self-supervised learning of a PIFu without access to GT mesh. The whole framework consists of a normal estimator, a depth estimator, and a SDF-based PIFu and better utilizes extra depth GT during training. Extensive experiments demonstrate the effectiveness of our self-supervised framework and the superiority of using depth as input. On synthetic data, our Intersection-Over-Union (IoU) achieves to 93.5%, 18% higher compared with PIFuHD. For in-the-wild images, we conduct user studies on the reconstructed results, the selection rate of our results is over 68% compared with other state-of-the-art methods.
Authors: Yuzhen Liu, Qiulei Dong
Abstract: Learning a fast and discriminative patch descriptor is a challenging topic in computer vision. Recently, many existing works focus on training various descriptor learning networks by minimizing a triplet loss (or its variants), which is expected to decrease the distance between each positive pair and increase the distance between each negative pair. However, such an expectation has to be lowered due to the non-perfect convergence of network optimizer to a local solution. Addressing this problem and the open computational speed problem, we propose a Descriptor Distillation framework for local descriptor learning, called DesDis, where a student model gains knowledge from a pre-trained teacher model, and it is further enhanced via a designed teacher-student regularizer. This teacher-student regularizer is to constrain the difference between the positive (also negative) pair similarity from the teacher model and that from the student model, and we theoretically prove that a more effective student model could be trained by minimizing a weighted combination of the triplet loss and this regularizer, than its teacher which is trained by minimizing the triplet loss singly. Under the proposed DesDis, many existing descriptor networks could be embedded as the teacher model, and accordingly, both equal-weight and light-weight student models could be derived, which outperform their teacher in either accuracy or speed. Experimental results on 3 public datasets demonstrate that the equal-weight student models, derived from the proposed DesDis framework by utilizing three typical descriptor learning networks as teacher models, could achieve significantly better performances than their teachers and several other comparative methods. In addition, the derived light-weight models could achieve 8 times or even faster speeds than the comparative methods under similar patch verification performances
Authors: Pavlo Melnyk, Andreas Robinson, Michael Felsberg, M{\aa}rten Wadenb\"ack
Abstract: In many practical applications, 3D point cloud analysis requires rotation invariance. In this paper, we present a learnable descriptor invariant under 3D rotations and reflections, i.e., the O(3) actions, utilizing the recently introduced steerable 3D spherical neurons and vector neurons. Specifically, we propose an embedding of the 3D spherical neurons into 4D vector neurons, which leverages end-to-end training of the model. In our approach, we perform TetraTransform--an equivariant embedding of the 3D input into 4D, constructed from the steerable neurons--and extract deeper O(3)-equivariant features using vector neurons. This integration of the TetraTransform into the VN-DGCNN framework, termed TetraSphere, negligibly increases the number of parameters by less than 0.0002%. TetraSphere sets a new state-of-the-art performance classifying randomly rotated real-world object scans of the challenging subsets of ScanObjectNN. Additionally, TetraSphere outperforms all equivariant methods on randomly rotated synthetic data: classifying objects from ModelNet40 and segmenting parts of the ShapeNet shapes. Thus, our results reveal the practical value of steerable 3D spherical neurons for learning in 3D Euclidean space. The code is available at \url{https://github.com/pavlo-melnyk/tetrasphere}.
Authors: Guanfang Dong, Chenqiu Zhao, Xichen Pan, Anup Basu
Abstract: The goal of moving object segmentation is separating moving objects from stationary backgrounds in videos. One major challenge in this problem is how to develop a universal model for videos from various natural scenes since previous methods are often effective only in specific scenes. In this paper, we propose a method called Learning Temporal Distribution and Spatial Correlation (LTS) that has the potential to be a general solution for universal moving object segmentation. In the proposed approach, the distribution from temporal pixels is first learned by our Defect Iterative Distribution Learning (DIDL) network for a scene-independent segmentation. Notably, the DIDL network incorporates the use of an improved product distribution layer that we have newly derived. Then, the Stochastic Bayesian Refinement (SBR) Network, which learns the spatial correlation, is proposed to improve the binary mask generated by the DIDL network. Benefiting from the scene independence of the temporal distribution and the accuracy improvement resulting from the spatial correlation, the proposed approach performs well for almost all videos from diverse and complex natural scenes with fixed parameters. Comprehensive experiments on standard datasets including LASIESTA, CDNet2014, BMC, SBMI2015 and 128 real world videos demonstrate the superiority of proposed approach compared to state-of-the-art methods with or without the use of deep learning networks. To the best of our knowledge, this work has high potential to be a general solution for moving object segmentation in real world environments. The code and real-world videos can be found on GitHub https://github.com/guanfangdong/LTS-UniverisalMOS.
Authors: Muhammed Korkmaz, T. Metin Sezgin
Abstract: Instance segmentation is a form of image detection which has a range of applications, such as object refinement, medical image analysis, and image/video editing, all of which demand a high degree of accuracy. However, this precision is often beyond the reach of what even state-of-the-art, fully automated instance segmentation algorithms can deliver. The performance gap becomes particularly prohibitive for small and complex objects. Practitioners typically resort to fully manual annotation, which can be a laborious process. In order to overcome this problem, we propose a novel approach to enable more precise predictions and generate higher-quality segmentation masks for high-curvature, complex and small-scale objects. Our human-assisted segmentation model, HAISTA-NET, augments the existing Strong Mask R-CNN network to incorporate human-specified partial boundaries. We also present a dataset of hand-drawn partial object boundaries, which we refer to as human attention maps. In addition, the Partial Sketch Object Boundaries (PSOB) dataset contains hand-drawn partial object boundaries which represent curvatures of an object's ground truth mask with several pixels. Through extensive evaluation using the PSOB dataset, we show that HAISTA-NET outperforms state-of-the art methods such as Mask R-CNN, Strong Mask R-CNN, and Mask2Former, achieving respective increases of +36.7, +29.6, and +26.5 points in AP-Mask metrics for these three models. We hope that our novel approach will set a baseline for future human-aided deep learning models by combining fully automated and interactive instance segmentation architectures.
Authors: Xiuwei Xu, Zhihao Sun, Ziwei Wang, Hongmin Liu, Jie Zhou, Jiwen Lu
Abstract: In this paper, we propose an efficient feature pruning strategy for 3D small object detection. Conventional 3D object detection methods struggle on small objects due to the weak geometric information from a small number of points. Although increasing the spatial resolution of feature representations can improve the detection performance on small objects, the additional computational overhead is unaffordable. With in-depth study, we observe the growth of computation mainly comes from the upsampling operation in the decoder of 3D detector. Motivated by this, we present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution to achieves high accuracy on small object detection, while reducing redundant computation by only focusing on small object areas. Specifically, we theoretically derive a dynamic spatial pruning (DSP) strategy to prune the redundant spatial representation of 3D scene in a cascade manner according to the distribution of objects. Then we design DSP module following this strategy and construct DSPDet3D with this efficient module. On ScanNet and TO-SCENE dataset, our method achieves leading performance on small object detection. Moreover, DSPDet3D trained with only ScanNet rooms can generalize well to scenes in larger scale. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects, ranging from cups to beds, on a single RTX 3090 GPU. Project page: https://xuxw98.github.io/DSPDet3D/.
Authors: Cristina Menghini, Andrew Delworth, Stephen H. Bach
Abstract: Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e., heuristic labels for unlabeled data, to enhance CLIP via prompt tuning. Conventional pseudolabeling trains a model on labeled data and then generates labels for unlabeled data. VLMs' zero-shot capabilities enable a "second generation" of pseudolabeling approaches that do not require task-specific training on labeled data. By using zero-shot pseudolabels as a source of supervision, we observe that learning paradigms such as semi-supervised, transductive zero-shot, and unsupervised learning can all be seen as optimizing the same loss function. This unified view enables the development of versatile training strategies that are applicable across learning paradigms. We investigate them on image classification tasks where CLIP exhibits limitations, by varying prompt modalities, e.g., textual or visual prompts, and learning paradigms. We find that (1) unexplored prompt tuning strategies that iteratively refine pseudolabels consistently improve CLIP accuracy, by 19.5 points in semi-supervised learning, by 28.4 points in transductive zero-shot learning, and by 15.2 points in unsupervised learning, and (2) unlike conventional semi-supervised pseudolabeling, which exacerbates model biases toward classes with higher-quality pseudolabels, prompt tuning leads to a more equitable distribution of per-class accuracy. The code to reproduce the experiments is at https://github.com/BatsResearch/menghini-neurips23-code.
URLs: https://github.com/BatsResearch/menghini-neurips23-code.
Authors: Miles Everett, Mingjun Zhong, Georgios Leontidis
Abstract: Capsule Networks have emerged as a powerful class of deep learning architectures, known for robust performance with relatively few parameters compared to Convolutional Neural Networks (CNNs). However, their inherent efficiency is often overshadowed by their slow, iterative routing mechanisms which establish connections between Capsule layers, posing computational challenges resulting in an inability to scale. In this paper, we introduce a novel, non-iterative routing mechanism, inspired by trainable prototype clustering. This innovative approach aims to mitigate computational complexity, while retaining, if not enhancing, performance efficacy. Furthermore, we harness a shared Capsule subspace, negating the need to project each lower-level Capsule to each higher-level Capsule, thereby significantly reducing memory requisites during training. Our approach demonstrates superior results compared to the current best non-iterative Capsule Network and tests on the Imagewoof dataset, which is too computationally demanding to handle efficiently by iterative approaches. Our findings underscore the potential of our proposed methodology in enhancing the operational efficiency and performance of Capsule Networks, paving the way for their application in increasingly complex computational scenarios. Code is available at https://github.com/mileseverett/ProtoCaps.
Authors: Jiazhou Zhou, Xu Zheng, Yuanhuiyi Lyu, Lin Wang
Abstract: In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular, due to the distinct modality gap with the image-text data and the lack of large-scale datasets, learning a common representation space for images, texts, and events is non-trivial.Intuitively, we need to address two key challenges: 1) how to generalize CLIP's visual encoder to event data while fully leveraging events' unique properties, e.g., sparsity and high temporal resolution; 2) how to effectively align the multi-modal embeddings, i.e., image, text, and events. Accordingly, we first introduce a novel event encoder that subtly models the temporal information from events and meanwhile, generates event prompts for modality bridging. We then design a text encoder that generates content prompts and utilizes hybrid text prompts to enhance EventBind's generalization ability across diverse datasets.With the proposed event encoder, text encoder, and image encoder, a novel Hierarchical Triple Contrastive Alignment (HTCA) module is introduced to jointly optimize the correlation and enable efficient knowledge transfer among the three modalities. We evaluate various settings, including fine-tuning and few-shot on three benchmarks, and our EventBind achieves new state-of-the-art accuracy compared with the previous methods, such as on N-Caltech 101 +5.34% and +1.70%) and N-Imagenet(+5.65% and +1.99%) with fine-tuning and 20-shot settings, respectively. Moreover, our EventBind can be flexibly extended to the event retrieval task using text or image queries, showing plausible performance. Our project code will be made publicly available.
Authors: Brian B. Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel
Abstract: Diffusion models in image Super-Resolution (SR) treat all image regions with uniform intensity, which risks compromising the overall image quality. To address this, we introduce "You Only Diffuse Areas" (YODA), a dynamic attention-guided diffusion method for image SR. YODA selectively focuses on spatial regions using attention maps derived from the low-resolution image and the current time step in the diffusion process. This time-dependent targeting enables a more efficient conversion to high-resolution outputs by focusing on areas that benefit the most from the iterative refinement process, i.e., detail-rich objects. We empirically validate YODA by extending leading diffusion-based methods SR3 and SRDiff. Our experiments demonstrate new state-of-the-art performance in face and general SR across PSNR, SSIM, and LPIPS metrics. A notable finding is YODA's stabilization effect by reducing color shifts, especially when training with small batch sizes.
Authors: Aristotelis Ballas, Christos Diou
Abstract: During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification approaches fail to generalize well in previously unseen visual contexts, as required by many real-world applications. In this paper, we focus on this domain generalization (DG) problem and argue that the generalization ability of deep convolutional neural networks can be improved by taking advantage of multi-layer and multi-scaled representations of the network. We introduce a framework that aims at improving domain generalization of image classifiers by combining both low-level and high-level features at multiple scales, enabling the network to implicitly disentangle representations in its latent space and learn domain-invariant attributes of the depicted objects. Additionally, to further facilitate robust representation learning, we propose a novel objective function, inspired by contrastive learning, which aims at constraining the extracted representations to remain invariant under distribution shifts. We demonstrate the effectiveness of our method by evaluating on the domain generalization datasets of PACS, VLCS, Office-Home and NICO. Through extensive experimentation, we show that our model is able to surpass the performance of previous DG methods and consistently produce competitive and state-of-the-art results in all datasets
Authors: Luca Morreale, Noam Aigerman, Vladimir G. Kim, Niloy J. Mitra
Abstract: We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Lack of annotated data prohibits direct inference of 3D semantic priors; instead, current State-of-the-art methods predominantly optimize geometric properties or require varying amounts of manual annotation. To overcome the lack of annotated training data, we distill semantic matches from pre-trained vision models: our method renders the pair of 3D shapes from multiple viewpoints; the resulting renders are then fed into an off-the-shelf image-matching method which leverages a pretrained visual model to produce feature points. This yields semantic correspondences, which can be projected back to the 3D shapes, producing a raw matching that is inaccurate and inconsistent between different viewpoints. These correspondences are refined and distilled into an inter-surface map by a dedicated optimization scheme, which promotes bijectivity and continuity of the output map. We illustrate that our approach can generate semantic surface-to-surface maps, eliminating manual annotations or any 3D training data requirement. Furthermore, it proves effective in scenarios with high semantic complexity, where objects are non-isometrically related, as well as in situations where they are nearly isometric.
Authors: Fulong Ma, Xiaoyang Yan, Guoyang Zhao, Xiaojie Xu, Yuxuan Liu, Ming Liu
Abstract: Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datasets and challenging to deploy in novel environments. Specifically, this study investigates the pipeline for training a monocular 3D object detection model on a diverse collection of 3D and 2D datasets. The proposed framework comprises three components: (1) a robust monocular 3D model capable of functioning across various camera settings, (2) a selective-training strategy to accommodate datasets with differing class annotations, and (3) a pseudo 3D training approach using 2D labels to enhance detection performance in scenes containing only 2D labels. With this framework, we could train models on a joint set of various open 3D/2D datasets to obtain models with significantly stronger generalization capability and enhanced performance on new dataset with only 2D labels. We conduct extensive experiments on KITTI/nuScenes/ONCE/Cityscapes/BDD100K datasets to demonstrate the scaling ability of the proposed method.
Authors: Guanlin Li, Yifei Chen, Jie Zhang, Jiwei Li, Shangwei Guo, Tianwei Zhang
Abstract: AI-Generated Content (AIGC) is gaining great popularity, with many emerging commercial services and applications. These services leverage advanced generative models, such as latent diffusion models and large language models, to generate creative content (e.g., realistic images and fluent sentences) for users. The usage of such generated content needs to be highly regulated, as the service providers need to ensure the users do not violate the usage policies (e.g., abuse for commercialization, generating and distributing unsafe content). A promising solution to achieve this goal is watermarking, which adds unique and imperceptible watermarks on the content for service verification and attribution. Numerous watermarking approaches have been proposed recently. However, in this paper, we show that an adversary can easily break these watermarking mechanisms. Specifically, we consider two possible attacks. (1) Watermark removal: the adversary can easily erase the embedded watermark from the generated content and then use it freely bypassing the regulation of the service provider. (2) Watermark forging: the adversary can create illegal content with forged watermarks from another user, causing the service provider to make wrong attributions. We propose Warfare, a unified methodology to achieve both attacks in a holistic way. The key idea is to leverage a pre-trained diffusion model for content processing and a generative adversarial network for watermark removal or forging. We evaluate Warfare on different datasets and embedding setups. The results prove that it can achieve high success rates while maintaining the quality of the generated content. Compared to existing diffusion model-based attacks, Warfare is 5,050~11,000x faster.
Authors: Dongsheng Jiang, Yuchen Liu, Songlin Liu, Jin'e Zhao, Hao Zhang, Zhen Gao, Xiaopeng Zhang, Jin Li, Hongkai Xiong
Abstract: Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications and the availability of diverse instruction tuning data, existing approaches often rely on CLIP or its variants as the visual branch, and merely extract features from the deep layers. However, these methods lack a comprehensive analysis of the visual encoders in MLLMs. In this paper, we conduct an extensive investigation into the effectiveness of different vision encoders within MLLMs. Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. Surprisingly, the vision-only model DINO, which is not pretrained with text-image alignment, demonstrates promising performance as a visual branch within MLLMs. By simply equipping it with an MLP layer for alignment, DINO surpasses CLIP in fine-grained related perception tasks. Building upon these observations, we propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging, to enhance the visual capabilities of MLLMs. We evaluate COMM through comprehensive experiments on a wide range of benchmarks, including image captioning, visual question answering, visual grounding, and object hallucination. Experimental results demonstrate the superior performance of COMM compared to existing methods, showcasing its enhanced visual capabilities within MLLMs.
Authors: Yuzhen Liu, Qiulei Dong
Abstract: Absolute rotation estimation is an important topic in 3D computer vision. Existing works in literature generally employ a multi-stage (at least two-stage) estimation strategy where multiple independent operations (feature matching, two-view rotation estimation, and rotation averaging) are implemented sequentially. However, such a multi-stage strategy inevitably leads to the accumulation of the errors caused by each involved operation, and degrades its final estimation on global rotations accordingly. To address this problem, we propose an End-to-end method for estimating Absolution Rotations from multi-view images based on deep neural Networks, called EAR-Net. The proposed EAR-Net consists of an epipolar confidence graph construction module and a confidence-aware rotation averaging module. The epipolar confidence graph construction module is explored to simultaneously predict pairwise relative rotations among the input images and their corresponding confidences, resulting in a weighted graph (called epipolar confidence graph). Based on this graph, the confidence-aware rotation averaging module, which is differentiable, is explored to predict the absolute rotations. Thanks to the introduced confidences of the relative rotations, the proposed EAR-Net could effectively handle outlier cases. Experimental results on three public datasets demonstrate that EAR-Net outperforms the state-of-the-art methods by a large margin in terms of accuracy and speed.
Authors: Shaobo Wang, Xiangdong Zhang, Dongrui Liu, Junchi Yan
Abstract: Batch Normalization (BN) has become an essential technique in contemporary neural network design, enhancing training stability. Specifically, BN employs centering and scaling operations to standardize features along the batch dimension and uses an affine transformation to recover features. Although standard BN has shown its capability to improve deep neural network training and convergence, it still exhibits inherent limitations in certain cases. Current enhancements to BN typically address only isolated aspects of its mechanism. In this work, we critically examine BN from a feature perspective, identifying feature condensation during BN as a detrimental factor to test performance. To tackle this problem, we propose a two-stage unified framework called Unified Batch Normalization (UBN). In the first stage, we employ a straightforward feature condensation threshold to mitigate condensation effects, thereby preventing improper updates of statistical norms. In the second stage, we unify various normalization variants to boost each component of BN. Our experimental results reveal that UBN significantly enhances performance across different visual backbones and different vision tasks, and notably expedites network training convergence, particularly in early training stages. Notably, our method improved about 3% in accuracy on ImageNet classification and 4% in mean average precision on both Object Detection and Instance Segmentation on COCO dataset, showing the effectiveness of our approach in real-world scenarios.
Authors: Xianda Guo, Juntao Lu, Chenming Zhang, Yiqi Wang, Yiqun Duan, Tian Yang, Zheng Zhu, Long Chen
Abstract: Stereo matching aims to estimate the disparity between matching pixels in a stereo image pair, which is of great importance to robotics, autonomous driving, and other computer vision tasks. Despite the development of numerous impressive methods in recent years, replicating their results and determining the most suitable architecture for practical application remains challenging. Addressing this gap, our paper introduces a comprehensive benchmark focusing on practical applicability rather than solely on performance enhancement. Specifically, we develop a flexible and efficient stereo matching codebase, called OpenStereo. OpenStereo includes training and inference codes of more than 10 network models, making it, to our knowledge, the most complete stereo matching toolbox available. Based on OpenStereo, we conducted experiments and have achieved or surpassed the performance metrics reported in the original paper. Additionally, we carry out an exhaustive analysis and deconstruction of recent developments in stereo matching through comprehensive ablative experiments. These investigations inspired the creation of StereoBase, a strong baseline model. Our StereoBase ranks 1st on SceneFlow, KITTI 2015, 2012 (Reflective) among published methods and achieves the best performance across all metrics. In addition, StereoBase has strong cross-dataset generalization.Code is available at \url{https://github.com/XiandaGuo/OpenStereo}.
Authors: Hanjung Kim, Jaehyun Kang, Miran Heo, Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim
Abstract: In recent years, online Video Instance Segmentation (VIS) methods have shown remarkable advancement with their powerful query-based detectors. Utilizing the output queries of the detector at the frame-level, these methods achieve high accuracy on challenging benchmarks. However, our observations demonstrate that these methods heavily rely on location information, which often causes incorrect associations between objects. This paper presents that a key axis of object matching in trackers is appearance information, which becomes greatly instructive under conditions where positional cues are insufficient for distinguishing their identities. Therefore, we suggest a simple yet powerful extension to object decoders that explicitly extract embeddings from backbone features and drive queries to capture the appearances of objects, which greatly enhances instance association accuracy. Furthermore, recognizing the limitations of existing benchmarks in fully evaluating appearance awareness, we have constructed a synthetic dataset to rigorously validate our method. By effectively resolving the over-reliance on location information, we achieve state-of-the-art results on YouTube-VIS 2019/2021 and Occluded VIS (OVIS). Code is available at https://github.com/KimHanjung/VISAGE.
Authors: Youjia Zhang, Zikai Song, Junqing Yu, Yawei Luo, Wei Yang
Abstract: Generating multi-view images from a single input view using image-conditioned diffusion models is a recent advancement and has shown considerable potential. However, issues such as the lack of consistency in synthesized views and over-smoothing in extracted geometry persist. Previous methods integrate multi-view consistency modules or impose additional supervisory to enhance view consistency while compromising on the flexibility of camera positioning and limiting the versatility of view synthesis. In this study, we consider the radiance field optimized during geometry extraction as a more rigid consistency prior, compared to volume and ray aggregation used in previous works. We further identify and rectify a critical bias in the traditional radiance field optimization process through score distillation from a multi-view diffuser. We introduce an Unbiased Score Distillation (USD) that utilizes unconditioned noises from a 2D diffusion model, greatly refining the radiance field fidelity. We leverage the rendered views from the optimized radiance field as the basis and develop a two-step specialization process of a 2D diffusion model, which is adept at conducting object-specific denoising and generating high-quality multi-view images. Finally, we recover faithful geometry and texture directly from the refined multi-view images. Empirical evaluations demonstrate that our optimized geometry and view distillation technique generates comparable results to the state-of-the-art models trained on extensive datasets, all while maintaining freedom in camera positioning. Please see our project page at https://youjiazhang.github.io/USD/.
Authors: Thomas Tanay, Matteo Maggioni
Abstract: A recent trend among generalizable novel view synthesis methods is to learn a rendering operator acting over single camera rays. This approach is promising because it removes the need for explicit volumetric rendering, but it effectively treats target images as collections of independent pixels. Here, we propose to learn a global rendering operator acting over all camera rays jointly. We show that the right representation to enable such rendering is a 5-dimensional plane sweep volume consisting of the projection of the input images on a set of planes facing the target camera. Based on this understanding, we introduce our Convolutional Global Latent Renderer (ConvGLR), an efficient convolutional architecture that performs the rendering operation globally in a low-resolution latent space. Experiments on various datasets under sparse and generalizable setups show that our approach consistently outperforms existing methods by significant margins.
Authors: Shutong Jin, Ruiyu Wang, Florian T. Pokorny
Abstract: Even though large-scale text-to-image generative models show promising performance in synthesizing high-quality images, applying these models directly to image editing remains a significant challenge. This challenge is further amplified in video editing due to the additional dimension of time. This is especially the case for editing real-world videos as it necessitates maintaining a stable structural layout across frames while executing localized edits without disrupting the existing content. In this paper, we propose RealCraft, an attention-control-based method for zero-shot real-world video editing. By swapping cross-attention for new feature injection and relaxing spatial-temporal attention of the editing object, we achieve localized shape-wise edit along with enhanced temporal consistency. Our model directly uses Stable Diffusion and operates without the need for additional information. We showcase the proposed zero-shot attention-control-based method across a range of videos, demonstrating shape-wise, time-consistent and parameter-free editing in videos of up to 64 frames.
Authors: Wei Zhang, Miaoxin Cai, Tong Zhang, Yin Zhuang, Xuerui Mao
Abstract: Multi-modal large language models (MLLMs) have demonstrated remarkable success in vision and visual-language tasks within the natural image domain. Owing to the significant diversities between the natural and remote sensing (RS) images, the development of MLLMs in the RS domain is still in the infant stage. To fill the gap, a pioneer MLLM named EarthGPT integrating various multi-sensor RS interpretation tasks uniformly is proposed in this paper for universal RS image comprehension. In EarthGPT, three key techniques are developed including a visual-enhanced perception mechanism, a cross-modal mutual comprehension approach, and a unified instruction tuning method for multi-sensor multi-task in the RS domain. More importantly, a dataset named MMRS-1M featuring large-scale multi-sensor multi-modal RS instruction-following is constructed, comprising over 1M image-text pairs based on 34 existing diverse RS datasets and including multi-sensor images such as optical, synthetic aperture radar (SAR), and infrared. The MMRS-1M dataset addresses the drawback of MLLMs on RS expert knowledge and stimulates the development of MLLMs in the RS domain. Extensive experiments are conducted, demonstrating the EarthGPT's superior performance in various RS visual interpretation tasks compared with the other specialist models and MLLMs, proving the effectiveness of the proposed EarthGPT and offering a versatile paradigm for open-set reasoning tasks.
Authors: Lei Xu, Moncef Gabbouj
Abstract: Anomalous crack region detection is a typical binary semantic segmentation task, which aims to detect pixels representing cracks on pavement surface images automatically by algorithms. Although existing deep learning-based methods have achieved outcoming results on specific public pavement datasets, the performance would deteriorate dramatically on imbalanced datasets. The input datasets used in such tasks suffer from severely between-class imbalanced problems, hence, it is a core challenge to obtain a robust performance on diverse pavement datasets with generic deep learning models. To address this problem, in this work, we propose a deep learning framework based on conditional Generative Adversarial Networks (cGANs) for the anomalous crack region detection tasks at the pixel level. In particular, the proposed framework containing a cGANs and a novel auxiliary network is developed to enhance and stabilize the generator's performance under two alternative training stages, when estimating a multiscale probability feature map from heterogeneous and imbalanced inputs iteratively. Moreover, several attention mechanisms and entropy strategies are incorporated into the cGANs architecture and the auxiliary network separately to mitigate further the performance deterioration of model training on severely imbalanced datasets. We implement extensive experiments on six accessible pavement datasets. The experimental results from both visual and quantitative evaluation show that the proposed framework can achieve state-of-the-art results on these datasets efficiently and robustly without acceleration of computation complexity.
Authors: Heng Zhou, Zhetao Guo, Shuhong Liu, Lechen Zhang, Qihao Wang, Yuxiang Ren, Mingrui Li
Abstract: Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applicability of SLAM systems. To address this limitation, we propose MoD-SLAM, the first monocular NeRF-based dense mapping method that allows 3D reconstruction in real-time in unbounded scenes. Specifically, we introduce a Gaussian-based unbounded scene representation approach to solve the challenge of mapping scenes without boundaries. This strategy is essential to extend the SLAM application. Moreover, a depth estimation module in the front-end is designed to extract accurate priori depth values to supervise mapping and tracking processes. By introducing a robust depth loss term into the tracking process, our SLAM system achieves more precise pose estimation in large-scale scenes. Our experiments on two standard datasets show that MoD-SLAM achieves competitive performance, improving the accuracy of the 3D reconstruction and localization by up to 30% and 15% respectively compared with existing state-of-the-art monocular SLAM systems.
Authors: Minyoung Park, Mirae Do, YeonJae Shin, Jaeseok Yoo, Jongkwang Hong, Joongrock Kim, Chul Lee
Abstract: Advanced techniques using Neural Radiance Fields (NeRF), Signed Distance Fields (SDF), and Occupancy Fields have recently emerged as solutions for 3D indoor scene reconstruction. We introduce a novel two-phase learning approach, H2O-SDF, that discriminates between object and non-object regions within indoor environments. This method achieves a nuanced balance, carefully preserving the geometric integrity of room layouts while also capturing intricate surface details of specific objects. A cornerstone of our two-phase learning framework is the introduction of the Object Surface Field (OSF), a novel concept designed to mitigate the persistent vanishing gradient problem that has previously hindered the capture of high-frequency details in other methods. Our proposed approach is validated through several experiments that include ablation studies.
Authors: Huayi Zhou, Mukun Luo, Fei Jiang, Yue Ding, Hongtao Lu
Abstract: The 2D human pose estimation (HPE) is a basic visual problem. However, its supervised learning requires massive keypoint labels, which is labor-intensive to collect. Thus, we aim at boosting a pose estimator by excavating extra unlabeled data with semi-supervised learning (SSL). Most previous SSHPE methods are consistency-based and strive to maintain consistent outputs for differently augmented inputs. Under this genre, we find that SSHPE can be boosted from two cores: advanced data augmentations and concise consistency training ways. Specifically, for the first core, we discover the synergistic effects of existing augmentations, and reveal novel paradigms for conveniently producing new superior HPE-oriented augmentations which can more effectively add noise on unlabeled samples. We can therefore establish paired easy-hard augmentations with larger difficulty gaps. For the second core, we propose to repeatedly augment unlabeled images with diverse hard augmentations, and generate multi-path predictions sequentially for optimizing multi-losses in a single network. This simple and compact design is interpretable, and easily benefits from newly found augmentations. Comparing to SOTA approaches, our method brings substantial improvements on public datasets. Code is in \url{https://github.com/hnuzhy/MultiAugs}
Authors: Yuyue Zhou, Banafshe Felfeliyan, Shrimanti Ghosh, Jessica Knight, Fatima Alves-Pereira, Christopher Keen, Jessica K\"upper, Abhilash Rakkunedeth Hareendranathan, Jacob L. Jaremko
Abstract: Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction limits model generalizability. Visual in-context learning (ICL) is a new and exciting area of research in computer vision. Unlike conventional deep learning, ICL emphasizes the model's ability to adapt to new tasks based on given examples quickly. Inspired by MAE-VQGAN, we proposed a new simple visual ICL method called SimICL, combining visual ICL pairing images with masked image modeling (MIM) designed for self-supervised learning. We validated our method on bony structures segmentation in a wrist ultrasound (US) dataset with limited annotations, where the clinical objective was to segment bony structures to help with further fracture detection. We used a test set containing 3822 images from 18 patients for bony region segmentation. SimICL achieved an remarkably high Dice coeffient (DC) of 0.96 and Jaccard Index (IoU) of 0.92, surpassing state-of-the-art segmentation and visual ICL models (a maximum DC 0.86 and IoU 0.76), with SimICL DC and IoU increasing up to 0.10 and 0.16. This remarkably high agreement with limited manual annotations indicates SimICL could be used for training AI models even on small US datasets. This could dramatically decrease the human expert time required for image labeling compared to conventional approaches, and enhance the real-world use of AI assistance in US image analysis.
Authors: Ekansh Chauhan, Amit Sharma, Megha S Uppin, C. V. Jawahar, P. K. Vinod
Abstract: The effective management of brain tumors relies on precise typing, subtyping, and grading. This study advances patient care with findings from rigorous multiple instance learning experimentations across various feature extractors and aggregators in brain tumor histopathology. It establishes new performance benchmarks in glioma subtype classification across multiple datasets, including a novel dataset focused on the Indian demographic (IPD- Brain), providing a valuable resource for existing research. Using a ResNet-50, pretrained on histopathology datasets for feature extraction, combined with the Double-Tier Feature Distillation (DTFD) feature aggregator, our approach achieves state-of-the-art AUCs of 88.08 on IPD-Brain and 95.81 on the TCGA-Brain dataset, respectively, for three-way glioma subtype classification. Moreover, it establishes new benchmarks in grading and detecting IHC molecular biomarkers (IDH1R132H, TP53, ATRX, Ki-67) through H&E stained whole slide images for the IPD-Brain dataset. The work also highlights a significant correlation between the model decision-making processes and the diagnostic reasoning of pathologists, underscoring its capability to mimic professional diagnostic procedures.
Authors: Karen Efremyan, Elizaveta Petrova, Evgeny Kaskov, Alexander Kapitanov
Abstract: A common problem for composite images is the incompatibility of their foreground and background components. Image harmonization aims to solve this problem, making the whole image look more authentic and coherent. Most existing solutions predict lookup tables (LUTs) or reconstruct images, utilizing various attributes of composite images. Recent approaches have primarily focused on employing global transformations like normalization and color curve rendering to achieve visual consistency, and they often overlook the importance of local visual coherence. We present a patch-based harmonization network consisting of novel Patch-based normalization (PN) blocks and a feature extractor based on statistical color transfer. Extensive experiments demonstrate the network's high generalization capability for different domains. Our network achieves state-of-the-art results on the iHarmony4 dataset. Also, we created a new human portrait harmonization dataset based on FFHQ and checked the proposed method to show the generalization ability by achieving the best metrics on it. The benchmark experiments confirm that the suggested patch-based normalization block and feature extractor effectively improve the network's capability to harmonize portraits. Our code and model baselines are publicly available.
Authors: Deshan Gong, Ningtao Mao, He Wang
Abstract: We propose a new method for cloth digitalization. Deviating from existing methods which learn from data captured under relatively casual settings, we propose to learn from data captured in strictly tested measuring protocols, and find plausible physical parameters of the cloths. However, such data is currently absent, so we first propose a new dataset with accurate cloth measurements. Further, the data size is considerably smaller than the ones in current deep learning, due to the nature of the data capture process. To learn from small data, we propose a new Bayesian differentiable cloth model to estimate the complex material heterogeneity of real cloths. It can provide highly accurate digitalization from very limited data samples. Through exhaustive evaluation and comparison, we show our method is accurate in cloth digitalization, efficient in learning from limited data samples, and general in capturing material variations. Code and data are available https://github.com/realcrane/Bayesian-Differentiable-Physics-for-Cloth-Digitalization
URLs: https://github.com/realcrane/Bayesian-Differentiable-Physics-for-Cloth-Digitalization
Authors: Mincheol Park, Dongjin Kim, Cheonjun Park, Yuna Park, Gyeong Eun Gong, Won Woo Ro, Suhyun Kim
Abstract: Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning granularity, specifically at the unit of a convolution filter, often leads to undesirable accuracy drops due to the inflexibility of deciding how and where to introduce sparsity to the CNNs. In this paper, we propose REPrune, a novel channel pruning technique that emulates kernel pruning, fully exploiting the finer but structured granularity. REPrune identifies similar kernels within each channel using agglomerative clustering. Then, it selects filters that maximize the incorporation of kernel representatives while optimizing the maximum cluster coverage problem. By integrating with a simultaneous training-pruning paradigm, REPrune promotes efficient, progressive pruning throughout training CNNs, avoiding the conventional train-prune-finetune sequence. Experimental results highlight that REPrune performs better in computer vision tasks than existing methods, effectively achieving a balance between acceleration ratio and performance retention.
Authors: Huiyuan Xiong, Jun Shen, Taohong Zhu, Yuelong Pan
Abstract: High-definition (HD) map is crucial for autonomous driving systems. Most existing works design map elements detection heads based on the DETR decoder. However, the initial queries lack explicit incorporation of physical positional information, and vanilla self-attention entails high computational complexity. Therefore, we propose EAN-MapNet for Efficiently constructing HD map using Anchor Neighborhoods. Firstly, we design query units based on the anchor neighborhoods, allowing non-neighborhood central anchors to effectively assist in fitting the neighborhood central anchors to the target points representing map elements. Then, we propose grouped local self-attention (GL-SA) by leveraging the relative instance relationship among the queries. This facilitates direct feature interaction among queries of the same instances, while innovatively employing local queries as intermediaries for interaction among queries from different instances. Consequently, GL-SA significantly reduces the computational complexity of self-attention while ensuring ample feature interaction among queries. On the nuScenes dataset, EAN-MapNet achieves a state-of-the-art performance with 63.0 mAP after training for 24 epochs, surpassing MapTR by 12.7 mAP. Furthermore, it considerably reduces memory consumption by 8198M compared to MapTRv2.
Authors: Dongliang Cao, Marvin Eisenberger, Nafie El Amrani, Daniel Cremers, Florian Bernard
Abstract: Although 3D shape matching and interpolation are highly interrelated, they are often studied separately and applied sequentially to relate different 3D shapes, thus resulting in sub-optimal performance. In this work we present a unified framework to predict both point-wise correspondences and shape interpolation between 3D shapes. To this end, we combine the deep functional map framework with classical surface deformation models to map shapes in both spectral and spatial domains. On the one hand, by incorporating spatial maps, our method obtains more accurate and smooth point-wise correspondences compared to previous functional map methods for shape matching. On the other hand, by introducing spectral maps, our method gets rid of commonly used but computationally expensive geodesic distance constraints that are only valid for near-isometric shape deformations. Furthermore, we propose a novel test-time adaptation scheme to capture both pose-dominant and shape-dominant deformations. Using different challenging datasets, we demonstrate that our method outperforms previous state-of-the-art methods for both shape matching and interpolation, even compared to supervised approaches.
Authors: Pradyumna Reddy, Ismail Elezi, Jiankang Deng
Abstract: We introduce a novel 3D generative method, Generative 3D Reconstruction (G3DR) in ImageNet, capable of generating diverse and high-quality 3D objects from single images, addressing the limitations of existing methods. At the heart of our framework is a novel depth regularization technique that enables the generation of scenes with high-geometric fidelity. G3DR also leverages a pretrained language-vision model, such as CLIP, to enable reconstruction in novel views and improve the visual realism of generations. Additionally, G3DR designs a simple but effective sampling procedure to further improve the quality of generations. G3DR offers diverse and efficient 3D asset generation based on class or text conditioning. Despite its simplicity, G3DR is able to beat state-of-theart methods, improving over them by up to 22% in perceptual metrics and 90% in geometry scores, while needing only half of the training time. Code is available at https://github.com/preddy5/G3DR
Authors: Jisong Kim, Geonho Bang, Kwangjin Choi, Minjae Seong, Jaechang Yoo, Eunjong Pyo, Jun Won Choi
Abstract: In this paper, we present a novel point generation model, referred to as Pillar-based Point Generation Network (PillarGen), which facilitates the transformation of point clouds from one domain into another. PillarGen can produce synthetic point clouds with enhanced density and quality based on the provided input point clouds. The PillarGen model performs the following three steps: 1) pillar encoding, 2) Occupied Pillar Prediction (OPP), and 3) Pillar to Point Generation (PPG). The input point clouds are encoded using a pillar grid structure to generate pillar features. Then, OPP determines the active pillars used for point generation and predicts the center of points and the number of points to be generated for each active pillar. PPG generates the synthetic points for each active pillar based on the information provided by OPP. We evaluate the performance of PillarGen using our proprietary radar dataset, focusing on enhancing the density and quality of short-range radar data using the long-range radar data as supervision. Our experiments demonstrate that PillarGen outperforms traditional point upsampling methods in quantitative and qualitative measures. We also confirm that when PillarGen is incorporated into bird's eye view object detection, a significant improvement in detection accuracy is achieved.
Authors: Zhengqi Xu, Ke Yuan, Huiqiong Wang, Yong Wang, Mingli Song, Jie Song
Abstract: Recently, model merging techniques have surfaced as a solution to combine multiple single-talent models into a single multi-talent model. However, previous endeavors in this field have either necessitated additional training or fine-tuning processes, or require that the models possess the same pre-trained initialization. In this work, we identify a common drawback in prior works w.r.t. the inconsistency of unit similarity in the weight space and the activation space. To address this inconsistency, we propose an innovative model merging framework, coined as merging under dual-space constraints (MuDSC). Specifically, instead of solely maximizing the objective of a single space, we advocate for the exploration of permutation matrices situated in a region with a unified high similarity in the dual space, achieved through the linear combination of activation and weight similarity matrices. In order to enhance usability, we have also incorporated adaptations for group structure, including Multi-Head Attention and Group Normalization. Comprehensive experimental comparisons demonstrate that MuDSC can significantly boost the performance of merged models with various task combinations and architectures. Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task. Our code is publicly available at https://github.com/zju-vipa/training_free_model_merging.
URLs: https://github.com/zju-vipa/training_free_model_merging.
Authors: Tianxiang Chen, Zhentao Tan, Tao Gong, Qi Chu, Yue Wu, Bin Liu, Jieping Ye, Nenghai Yu
Abstract: Recently, infrared small target detection (ISTD) has made significant progress, thanks to the development of basic models. Specifically, the structures combining convolutional networks with transformers can successfully extract both local and global features. However, the disadvantage of the transformer is also inherited, i.e., the quadratic computational complexity to the length of the sequence. Inspired by the recent basic model with linear complexity for long-distance modeling, called Mamba, we explore the potential of this state space model for ISTD task in terms of effectiveness and efficiency in the paper. However, directly applying Mamba achieves poor performance since local features, which are critical to detecting small targets, cannot be fully exploited. Instead, we tailor a Mamba-in-Mamba (MiM-ISTD) structure for efficient ISTD. Specifically, we treat the local patches as "visual sentences" and use the Outer Mamba to explore the global information. We then decompose each visual sentence into sub-patches as "visual words" and use the Inner Mamba to further explore the local information among words in the visual sentence with negligible computational costs. By aggregating the word and sentence features, the MiM-ISTD can effectively explore both global and local information. Experiments on NUAA-SIRST and IRSTD-1k show the superior accuracy and efficiency of our method. Specifically, MiM-ISTD is $10 \times$ faster than the SOTA method and reduces GPU memory usage by 73.4$\%$ when testing on $2048 \times 2048$ image, overcoming the computation and memory constraints on high-resolution infrared images. Source code is available at https://github.com/txchen-USTC/MiM-ISTD.
Authors: Zhuohong Li, Wei He, Jiepan Li, Fangxiao Lu, Hongyan Zhang
Abstract: Large-scale high-resolution (HR) land-cover mapping is a vital task to survey the Earth's surface and resolve many challenges facing humanity. However, it is still a non-trivial task hindered by complex ground details, various landforms, and the scarcity of accurate training labels over a wide-span geographic area. In this paper, we propose an efficient, weakly supervised framework (Paraformer) to guide large-scale HR land-cover mapping with easy-access historical land-cover data of low resolution (LR). Specifically, existing land-cover mapping approaches reveal the dominance of CNNs in preserving local ground details but still suffer from insufficient global modeling in various landforms. Therefore, we design a parallel CNN-Transformer feature extractor in Paraformer, consisting of a downsampling-free CNN branch and a Transformer branch, to jointly capture local and global contextual information. Besides, facing the spatial mismatch of training data, a pseudo-label-assisted training (PLAT) module is adopted to reasonably refine LR labels for weakly supervised semantic segmentation of HR images. Experiments on two large-scale datasets demonstrate the superiority of Paraformer over other state-of-the-art methods for automatically updating HR land-cover maps from LR historical labels.
Authors: Yufan Chen, Ching Ting Leung, Yong Huang, Jianwei Sun, Hao Chen, Hanyu Gao
Abstract: In the field of chemical structure recognition, the task of converting molecular images into graph structures and SMILES string stands as a significant challenge, primarily due to the varied drawing styles and conventions prevalent in chemical literature. To bridge this gap, we proposed MolNexTR, a novel image-to-graph deep learning model that collaborates to fuse the strengths of ConvNext, a powerful Convolutional Neural Network variant, and Vision-TRansformer. This integration facilitates a more nuanced extraction of both local and global features from molecular images. MolNexTR can predict atoms and bonds simultaneously and understand their layout rules. It also excels at flexibly integrating symbolic chemistry principles to discern chirality and decipher abbreviated structures. We further incorporate a series of advanced algorithms, including improved data augmentation module, image contamination module, and a post-processing module to get the final SMILES output. These modules synergistically enhance the model's robustness against the diverse styles of molecular imagery found in real literature. In our test sets, MolNexTR has demonstrated superior performance, achieving an accuracy rate of 81-97%, marking a significant advancement in the domain of molecular structure recognition. Scientific contribution: MolNexTR is a novel image-to-graph model that incorporates a unique dual-stream encoder to extract complex molecular image features, and combines chemical rules to predict atoms and bonds while understanding atom and bond layout rules. In addition, it employs a series of novel augmentation algorithms to significantly enhance the robustness and performance of the model.
Authors: Rashindrie Perera, Saman Halgamuge
Abstract: In this paper, we look at cross-domain few-shot classification which presents the challenging task of learning new classes in unseen domains with few labelled examples. Existing methods, though somewhat effective, encounter several limitations, which we address in this work through two significant improvements. First, to address overfitting associated with fine-tuning a large number of parameters on small datasets, we introduce a lightweight parameter-efficient adaptation strategy. This strategy employs a linear transformation of pre-trained features, significantly reducing the trainable parameter count. Second, we replace the traditional nearest centroid classifier with a variance-aware loss function, enhancing the model's sensitivity to the inter- and intra-class variances within the training set for improved clustering in feature space. Empirical evaluations on the Meta-Dataset benchmark showcase that our approach not only improves accuracy up to 7.7% and 5.3% on seen and unseen datasets respectively but also achieves this performance while being at least ~3x more parameter-efficient than existing methods, establishing a new state-of-the-art in cross-domain few-shot learning. Our code can be found at https://github.com/rashindrie/DIPA.
Authors: Evangelos Skartados, Mehmet Kerim Yucel, Bruno Manganelli, Anastasios Drosou, Albert Sa\`a-Garriga
Abstract: Neural Radiance Fields (NeRF) have quickly become the primary approach for 3D reconstruction and novel view synthesis in recent years due to their remarkable performance. Despite the huge interest in NeRF methods, a practical use case of NeRFs has largely been ignored; the exploration of the scene space modelled by a NeRF. In this paper, for the first time in the literature, we propose and formally define the scene exploration framework as the efficient discovery of NeRF model inputs (i.e. coordinates and viewing angles), using which one can render novel views that adhere to user-selected criteria. To remedy the lack of approaches addressing scene exploration, we first propose two baseline methods called Guided-Random Search (GRS) and Pose Interpolation-based Search (PIBS). We then cast scene exploration as an optimization problem, and propose the criteria-agnostic Evolution-Guided Pose Search (EGPS) for efficient exploration. We test all three approaches with various criteria (e.g. saliency maximization, image quality maximization, photo-composition quality improvement) and show that our EGPS performs more favourably than other baselines. We finally highlight key points and limitations, and outline directions for future research in scene exploration.
Authors: Hitesh Kandala, Jianfeng Gao, Jianwei Yang
Abstract: We present Pix2Gif, a motion-guided diffusion model for image-to-GIF (video) generation. We tackle this problem differently by formulating the task as an image translation problem steered by text and motion magnitude prompts, as shown in teaser fig. To ensure that the model adheres to motion guidance, we propose a new motion-guided warping module to spatially transform the features of the source image conditioned on the two types of prompts. Furthermore, we introduce a perceptual loss to ensure the transformed feature map remains within the same space as the target image, ensuring content consistency and coherence. In preparation for the model training, we meticulously curated data by extracting coherent image frames from the TGIF video-caption dataset, which provides rich information about the temporal changes of subjects. After pretraining, we apply our model in a zero-shot manner to a number of video datasets. Extensive qualitative and quantitative experiments demonstrate the effectiveness of our model -- it not only captures the semantic prompt from text but also the spatial ones from motion guidance. We train all our models using a single node of 16xV100 GPUs. Code, dataset and models are made public at: https://hiteshk03.github.io/Pix2Gif/.
Authors: Sukjin Han, Eric H. Schulman, Kristen Grauman, Santhosh Ramakrishnan
Abstract: Many differentiated products have key attributes that are unstructured and thus high-dimensional (e.g., design, text). Instead of treating unstructured attributes as unobservables in economic models, quantifying them can be important to answer interesting economic questions. To propose an analytical framework for these types of products, this paper considers one of the simplest design products-fonts-and investigates merger and product differentiation using an original dataset from the world's largest online marketplace for fonts. We quantify font shapes by constructing embeddings from a deep convolutional neural network. Each embedding maps a font's shape onto a low-dimensional vector. In the resulting product space, designers are assumed to engage in Hotelling-type spatial competition. From the image embeddings, we construct two alternative measures that capture the degree of design differentiation. We then study the causal effects of a merger on the merging firm's creative decisions using the constructed measures in a synthetic control method. We find that the merger causes the merging firm to increase the visual variety of font design. Notably, such effects are not captured when using traditional measures for product offerings (e.g., specifications and the number of products) constructed from structured data.
Authors: Antonio Emanuele Cin\`a, Kathrin Grosse, Ambra Demontis, Battista Biggio, Fabio Roli, Marcello Pelillo
Abstract: The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised when such data is maliciously manipulated to mislead the learning process. In this article, we first review poisoning attacks that compromise the training data used to learn ML models, including attacks that aim to reduce the overall performance, manipulate the predictions on specific test samples, and even implant backdoors in the model. We then discuss how to mitigate these attacks using basic security principles, or by deploying ML-oriented defensive mechanisms. We conclude our article by formulating some relevant open challenges which are hindering the development of testing methods and benchmarks suitable for assessing and improving the trustworthiness of ML models against data poisoning attacks
Authors: Emiel Hoogeboom, Eirikur Agustsson, Fabian Mentzer, Luca Versari, George Toderici, Lucas Theis
Abstract: Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by a further score-based decoder. However, as we will show, implementation details matter and the optimal design decisions can differ greatly from typical text-to-image models.
Authors: Tan H. Nguyen, Dinkar Juyal, Jin Li, Aaditya Prakash, Shima Nofallah, Chintan Shah, Sai Chowdary Gullapally, Limin Yu, Michael Griffin, Anand Sampat, John Abel, Justin Lee, Amaro Taylor-Weiner
Abstract: Differences in staining and imaging procedures can cause significant color variations in histopathology images, leading to poor generalization when deploying deep-learning models trained from a different data source. Various color augmentation methods have been proposed to generate synthetic images during training to make models more robust, eliminating the need for stain normalization during test time. Many color augmentation methods leverage domain labels to generate synthetic images. This approach causes three significant challenges to scaling such a model. Firstly, incorporating data from a new domain into deep-learning models trained on existing domain labels is not straightforward. Secondly, dependency on domain labels prevents the use of pathology images without domain labels to improve model performance. Finally, implementation of these methods becomes complicated when multiple domain labels (e.g., patient identification, medical center, etc) are associated with a single image. We introduce ContriMix, a novel domain label free stain color augmentation method based on DRIT++, a style-transfer method. Contrimix leverages sample stain color variation within a training minibatch and random mixing to extract content and attribute information from pathology images. This information can be used by a trained ContriMix model to create synthetic images to improve the performance of existing classifiers. ContriMix outperforms competing methods on the Camelyon17-WILDS dataset. Its performance is consistent across different slides in the test set while being robust to the color variation from rare substances in pathology images. We make our code and trained ContriMix models available for research use. The code for ContriMix can be found at https://gitlab.com/huutan86/contrimix
Authors: Yixuan Huang, Jialin Yuan, Chanho Kim, Pupul Pradhan, Bryan Chen, Li Fuxin, Tucker Hermans
Abstract: Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments. We investigate the problem of encoding object-oriented memory into a multi-object manipulation reasoning and planning framework. We propose DOOM and LOOM, which leverage transformer relational dynamics to encode the history of trajectories given partial-view point clouds and an object discovery and tracking engine. Our approaches can perform multiple challenging tasks including reasoning with occluded objects, novel objects appearance, and object reappearance. Throughout our extensive simulation and real-world experiments, we find that our approaches perform well in terms of different numbers of objects and different numbers of distractor actions. Furthermore, we show our approaches outperform an implicit memory baseline.
Authors: Khaled ELKarazle, Valliappan Raman, Caslon Chua, Patrick Then
Abstract: Vision Transformers (ViTs) have revolutionized medical imaging analysis, showcasing superior efficacy compared to conventional Convolutional Neural Networks (CNNs) in vital tasks such as polyp classification, detection, and segmentation. Leveraging attention mechanisms to focus on specific image regions, ViTs exhibit contextual awareness in processing visual data, culminating in robust and precise predictions, even for intricate medical images. Moreover, the inherent self-attention mechanism in Transformers accommodates varying input sizes and resolutions, granting an unprecedented flexibility absent in traditional CNNs. However, Transformers grapple with challenges like excessive memory usage and limited training parallelism due to self-attention, rendering them impractical for real-time disease detection on resource-constrained devices. In this study, we address these hurdles by investigating the integration of the recently introduced retention mechanism into polyp segmentation, introducing RetSeg, an encoder-decoder network featuring multi-head retention blocks. Drawing inspiration from Retentive Networks (RetNet), RetSeg is designed to bridge the gap between precise polyp segmentation and resource utilization, particularly tailored for colonoscopy images. We train and validate RetSeg for polyp segmentation employing two publicly available datasets: Kvasir-SEG and CVC-ClinicDB. Additionally, we showcase RetSeg's promising performance across diverse public datasets, including CVC-ColonDB, ETIS-LaribPolypDB, CVC-300, and BKAI-IGH NeoPolyp. While our work represents an early-stage exploration, further in-depth studies are imperative to advance these promising findings.
Authors: Lukas Struppek, Dominik Hintersdorf, Kristian Kersting
Abstract: Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration. Its implications for preserving model privacy, however, have remained unexplored. To fill this gap, we investigate the impact of label smoothing on model inversion attacks (MIAs), which aim to generate class-representative samples by exploiting the knowledge encoded in a classifier, thereby inferring sensitive information about its training data. Through extensive analyses, we uncover that traditional label smoothing fosters MIAs, thereby increasing a model's privacy leakage. Even more, we reveal that smoothing with negative factors counters this trend, impeding the extraction of class-related information and leading to privacy preservation, beating state-of-the-art defenses. This establishes a practical and powerful novel way for enhancing model resilience against MIAs.
Authors: Changwoo Lee, Hun-Seok Kim
Abstract: This paper investigates efficient deep neural networks (DNNs) to replace dense unstructured weight matrices with structured ones that possess desired properties. The challenge arises because the optimal weight matrix structure in popular neural network models is obscure in most cases and may vary from layer to layer even in the same network. Prior structured matrices proposed for efficient DNNs were mostly hand-crafted without a generalized framework to systematically learn them. To address this issue, we propose a generalized and differentiable framework to learn efficient structures of weight matrices by gradient descent. We first define a new class of structured matrices that covers a wide range of structured matrices in the literature by adjusting the structural parameters. Then, the frequency-domain differentiable parameterization scheme based on the Gaussian-Dirichlet kernel is adopted to learn the structural parameters by proximal gradient descent. On the image and language tasks, our method learns efficient DNNs with structured matrices, achieving lower complexity and/or higher performance than prior approaches that employ low-rank, block-sparse, or block-low-rank matrices.
Authors: Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, Tat-Seng Chua
Abstract: Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction. However, existing MLLMs prevalently suffer from serious hallucination problems, generating text that is not factually grounded in associated images. The problem makes existing MLLMs untrustworthy and thus impractical in real-world (especially high-stakes) applications. To address the challenge, we present RLHF-V, which enhances MLLM trustworthiness via behavior alignment from fine-grained correctional human feedback. Specifically, RLHF-V collects human preference in the form of segment-level corrections on hallucinations, and performs dense direct preference optimization over the human feedback. Comprehensive experiments on five benchmarks in both automatic and human evaluation show that, RLHF-V can enable substantially more trustworthy MLLM behaviors with promising data and computation efficiency. Remarkably, using 1.4k annotated data samples, RLHF-V significantly reduces the hallucination rate of the base MLLM by 34.8%, outperforming the concurrent LLaVA-RLHF trained on 10k annotated data. The final model achieves state-of-the-art performance in trustworthiness among open-source MLLMs, and shows better robustness than GPT-4V in preventing hallucinations aroused from over-generalization. We open-source our code, model, and data at https://github.com/RLHF-V/RLHF-V.
Authors: Joshua Wang
Abstract: We propose a PnP algorithm for a camera constrained to two-dimensional motion (applicable, for instance, to many wheeled robotics platforms). Leveraging this assumption allows accuracy and performance improvements over 3D PnP algorithms due to the reduction in search space dimensionality. It also reduces the incidence of ambiguous pose estimates (as, in most cases, the spurious solutions fall outside the plane of movement). Our algorithm finds an approximate solution by solving a polynomial system and refines its prediction iteratively to minimize the reprojection error. The algorithm compares favorably to existing 3D PnP algorithms in terms of accuracy, performance, and robustness to noise.
Authors: Linfeng Ye, Shayan Mohajer Hamidi, Renhao Tan, En-Hui Yang
Abstract: It is believed that in knowledge distillation (KD), the role of the teacher is to provide an estimate for the unknown Bayes conditional probability distribution (BCPD) to be used in the student training process. Conventionally, this estimate is obtained by training the teacher using maximum log-likelihood (MLL) method. To improve this estimate for KD, in this paper we introduce the concept of conditional mutual information (CMI) into the estimation of BCPD and propose a novel estimator called the maximum CMI (MCMI) method. Specifically, in MCMI estimation, both the log-likelihood and CMI of the teacher are simultaneously maximized when the teacher is trained. Through Eigen-CAM, it is further shown that maximizing the teacher's CMI value allows the teacher to capture more contextual information in an image cluster. Via conducting a thorough set of experiments, we show that by employing a teacher trained via MCMI estimation rather than one trained via MLL estimation in various state-of-the-art KD frameworks, the student's classification accuracy consistently increases, with the gain of up to 3.32\%. This suggests that the teacher's BCPD estimate provided by MCMI method is more accurate than that provided by MLL method. In addition, we show that such improvements in the student's accuracy are more drastic in zero-shot and few-shot settings. Notably, the student's accuracy increases with the gain of up to 5.72\% when 5\% of the training samples are available to the student (few-shot), and increases from 0\% to as high as 84\% for an omitted class (zero-shot). The code is available at \url{https://github.com/iclr2024mcmi/ICLRMCMI}.
Authors: Kaixiang Zheng, En-Hui Yang
Abstract: As a technique to bridge logit matching and probability distribution matching, temperature scaling plays a pivotal role in knowledge distillation (KD). Conventionally, temperature scaling is applied to both teacher's logits and student's logits in KD. Motivated by some recent works, in this paper, we drop instead temperature scaling on the student side, and systematically study the resulting variant of KD, dubbed transformed teacher matching (TTM). By reinterpreting temperature scaling as a power transform of probability distribution, we show that in comparison with the original KD, TTM has an inherent R\'enyi entropy term in its objective function, which serves as an extra regularization term. Extensive experiment results demonstrate that thanks to this inherent regularization, TTM leads to trained students with better generalization than the original KD. To further enhance student's capability to match teacher's power transformed probability distribution, we introduce a sample-adaptive weighting coefficient into TTM, yielding a novel distillation approach dubbed weighted TTM (WTTM). It is shown, by comprehensive experiments, that although WTTM is simple, it is effective, improves upon TTM, and achieves state-of-the-art accuracy performance. Our source code is available at https://github.com/zkxufo/TTM.
Authors: Michael Potter, Murat Akcakaya, Marius Necsoiu, Gunar Schirner, Deniz Erdogmus, Tales Imbiriba
Abstract: Radar Automated Target Recognition (RATR) for Unmanned Aerial Vehicles (UAVs) involves transmitting Electromagnetic Waves (EMWs) and performing target type recognition on the received radar echo, crucial for defense and aerospace applications. Previous studies highlighted the advantages of multistatic radar configurations over monostatic ones in RATR. However, fusion methods in multistatic radar configurations often suboptimally combine classification vectors from individual radars probabilistically. To address this, we propose a fully Bayesian RATR framework employing Optimal Bayesian Fusion (OBF) to aggregate classification probability vectors from multiple radars. OBF, based on expected 0-1 loss, updates a Recursive Bayesian Classification (RBC) posterior distribution for target UAV type, conditioned on historical observations across multiple time steps. We evaluate the approach using simulated random walk trajectories for seven drones, correlating target aspect angles to Radar Cross Section (RCS) measurements in an anechoic chamber. Comparing against single radar Automated Target Recognition (ATR) systems and suboptimal fusion methods, our empirical results demonstrate that the OBF method integrated with RBC significantly enhances classification accuracy compared to other fusion methods and single radar configurations.
Authors: Xinjie Zhang, Ren Yang, Dailan He, Xingtong Ge, Tongda Xu, Yan Wang, Hongwei Qin, Jun Zhang
Abstract: Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their representation capabilities, primarily due to inadequate alignment of intermediate features during target frame decoding. This paper introduces a universal boosting framework for current implicit video representation approaches. Specifically, we utilize a conditional decoder with a temporal-aware affine transform module, which uses the frame index as a prior condition to effectively align intermediate features with target frames. Besides, we introduce a sinusoidal NeRV-like block to generate diverse intermediate features and achieve a more balanced parameter distribution, thereby enhancing the model's capacity. With a high-frequency information-preserving reconstruction loss, our approach successfully boosts multiple baseline INRs in the reconstruction quality and convergence speed for video regression, and exhibits superior inpainting and interpolation results. Further, we integrate a consistent entropy minimization technique and develop video codecs based on these boosted INRs. Experiments on the UVG dataset confirm that our enhanced codecs significantly outperform baseline INRs and offer competitive rate-distortion performance compared to traditional and learning-based codecs.
Authors: Yue Yang, Yuqi lin, Hong Liu, Wenqi Shao, Runjian Chen, Hailong Shang, Yu Wang, Yu Qiao, Kaipeng Zhang, Ping Luo
Abstract: Recent text-to-image (T2I) models have had great success, and many benchmarks have been proposed to evaluate their performance and safety. However, they only consider explicit prompts while neglecting implicit prompts (hint at a target without explicitly mentioning it). These prompts may get rid of safety constraints and pose potential threats to the applications of these models. This position paper highlights the current state of T2I models toward implicit prompts. We present a benchmark named ImplicitBench and conduct an investigation on the performance and impacts of implicit prompts with popular T2I models. Specifically, we design and collect more than 2,000 implicit prompts of three aspects: General Symbols, Celebrity Privacy, and Not-Safe-For-Work (NSFW) Issues, and evaluate six well-known T2I models' capabilities under these implicit prompts. Experiment results show that (1) T2I models are able to accurately create various target symbols indicated by implicit prompts; (2) Implicit prompts bring potential risks of privacy leakage for T2I models. (3) Constraints of NSFW in most of the evaluated T2I models can be bypassed with implicit prompts. We call for increased attention to the potential and risks of implicit prompts in the T2I community and further investigation into the capabilities and impacts of implicit prompts, advocating for a balanced approach that harnesses their benefits while mitigating their risks.
Authors: Ge Yan, Yueh-Hua Wu, Xiaolong Wang
Abstract: This paper presents DNAct, a language-conditioned multi-task policy framework that integrates neural rendering pre-training and diffusion training to enforce multi-modality learning in action sequence spaces. To learn a generalizable multi-task policy with few demonstrations, the pre-training phase of DNAct leverages neural rendering to distill 2D semantic features from foundation models such as Stable Diffusion to a 3D space, which provides a comprehensive semantic understanding regarding the scene. Consequently, it allows various applications to challenging robotic tasks requiring rich 3D semantics and accurate geometry. Furthermore, we introduce a novel approach utilizing diffusion training to learn a vision and language feature that encapsulates the inherent multi-modality in the multi-task demonstrations. By reconstructing the action sequences from different tasks via the diffusion process, the model is capable of distinguishing different modalities and thus improving the robustness and the generalizability of the learned representation. DNAct significantly surpasses SOTA NeRF-based multi-task manipulation approaches with over 30% improvement in success rate. Project website: dnact.github.io.
Authors: Yizhe Zhang, He Bai, Ruixiang Zhang, Jiatao Gu, Shuangfei Zhai, Josh Susskind, Navdeep Jaitly
Abstract: Vision-Language Models (VLMs) such as GPT-4V have recently demonstrated incredible strides on diverse vision language tasks. We dig into vision-based deductive reasoning, a more sophisticated but less explored realm, and find previously unexposed blindspots in the current SOTA VLMs. Specifically, we leverage Raven's Progressive Matrices (RPMs), to assess VLMs' abilities to perform multi-hop relational and deductive reasoning relying solely on visual clues. We perform comprehensive evaluations of several popular VLMs employing standard strategies such as in-context learning, self-consistency, and Chain-of-thoughts (CoT) on three diverse datasets, including the Mensa IQ test, IntelligenceTest, and RAVEN. The results reveal that despite the impressive capabilities of LLMs in text-based reasoning, we are still far from achieving comparable proficiency in visual deductive reasoning. We found that certain standard strategies that are effective when applied to LLMs do not seamlessly translate to the challenges presented by visual reasoning tasks. Moreover, a detailed analysis reveals that VLMs struggle to solve these tasks mainly because they are unable to perceive and comprehend multiple, confounding abstract patterns in RPM examples.