Authors: Kushin Mukherjee, Timothy T. Rogers, Karen B. Schloss
Abstract: Concepts, both abstract and concrete, elicit a distribution of association strengths across perceptual color space, which influence aspects of visual cognition ranging from object recognition to interpretation of information visualizations. While prior work has hypothesized that color-concept associations may be learned from the cross-modal statistical structure of experience, it has been unclear whether natural environments possess such structure or, if so, whether learning systems are capable of discovering and exploiting it without strong prior constraints. We addressed these questions by investigating the ability of GPT-4, a multimodal large language model, to estimate human-like color-concept associations without any additional training. Starting with human color-concept association ratings for 71 color set spanning perceptual color space (\texttt{UW-71}) and concepts that varied in abstractness, we assessed how well association ratings generated by GPT-4 could predict human ratings. GPT-4 ratings were correlated with human ratings, with performance comparable to state-of-the-art methods for automatically estimating color-concept associations from images. Variability in GPT-4's performance across concepts could be explained by specificity of the concept's color-concept association distribution. This study suggests that high-order covariances between language and perception, as expressed in the natural environment of the internet, contain sufficient information to support learning of human-like color-concept associations, and provides an existence proof that a learning system can encode such associations without initial constraints. The work further shows that GPT-4 can be used to efficiently estimate distributions of color associations for a broad range of concepts, potentially serving as a critical tool for designing effective and intuitive information visualizations.
Authors: Xiang Chen, Lu Wang, Beibei Wang
Abstract: Woven fabrics are widely used in applications of realistic rendering, where real-time capability is also essential. However, rendering realistic woven fabrics in real time is challenging due to their complex structure and optical appearance, which cause aliasing and noise without many samples. The core of this issue is a multi-scale representation of the fabric shading model, which allows for a fast range query. Some previous neural methods deal with the issue at the cost of training on each material, which limits their practicality. In this paper, we propose a lightweight neural network to represent different types of woven fabrics at different scales. Thanks to the regularity and repetitiveness of woven fabric patterns, our network can encode fabric patterns and parameters as a small latent vector, which is later interpreted by a small decoder, enabling the representation of different types of fabrics. By applying the pixel's footprint as input, our network achieves multi-scale representation. Moreover, our network is fast and occupies little storage because of its lightweight structure. As a result, our method achieves rendering and editing woven fabrics at nearly 60 frames per second on an RTX 3090, showing a quality close to the ground truth and being free from visible aliasing and noise.
Authors: Yuxuan Mu, Shihao Zou, Kangning Yin, Zheng Tian, Li Cheng, Weinan Zhang, Jun Wang
Abstract: In computer animation, driving a simulated character with lifelike motion is challenging. Current generative models, though able to generalize to diverse motions, often pose challenges to the responsiveness of end-user control. To address these issues, we introduce RACon: Retrieval-Augmented Simulated Character Locomotion Control. Our end-to-end hierarchical reinforcement learning method utilizes a retriever and a motion controller. The retriever searches motion experts from a user-specified database in a task-oriented fashion, which boosts the responsiveness to the user's control. The selected motion experts and the manipulation signal are then transferred to the controller to drive the simulated character. In addition, a retrieval-augmented discriminator is designed to stabilize the training process. Our method surpasses existing techniques in both quality and quantity in locomotion control, as demonstrated in our empirical study. Moreover, by switching extensive databases for retrieval, it can adapt to distinctive motion types at run time.
Authors: Alireza Hosseini, Amirhossein Kazerouni, Saeed Akhavan, Michael Brudno, Babak Taati
Abstract: Visual attention modeling, important for interpreting and prioritizing visual stimuli, plays a significant role in applications such as marketing, multimedia, and robotics. Traditional saliency prediction models, especially those based on Convolutional Neural Networks (CNNs) or Transformers, achieve notable success by leveraging large-scale annotated datasets. However, the current state-of-the-art (SOTA) models that use Transformers are computationally expensive. Additionally, separate models are often required for each image type, lacking a unified approach. In this paper, we propose Saliency Unification through Mamba (SUM), a novel approach that integrates the efficient long-range dependency modeling of Mamba with U-Net to provide a unified model for diverse image types. Using a novel Conditional Visual State Space (C-VSS) block, SUM dynamically adapts to various image types, including natural scenes, web pages, and commercial imagery, ensuring universal applicability across different data types. Our comprehensive evaluations across five benchmarks demonstrate that SUM seamlessly adapts to different visual characteristics and consistently outperforms existing models. These results position SUM as a versatile and powerful tool for advancing visual attention modeling, offering a robust solution universally applicable across different types of visual content.
Authors: Jialun Pei, Ruize Cui, Yaoqian Li, Weixin Si, Jing Qin, Pheng-Ann Heng
Abstract: Laparoscopic liver surgery poses a complex intraoperative dynamic environment for surgeons, where remains a significant challenge to distinguish critical or even hidden structures inside the liver. Liver anatomical landmarks, e.g., ridge and ligament, serve as important markers for 2D-3D alignment, which can significantly enhance the spatial perception of surgeons for precise surgery. To facilitate the detection of laparoscopic liver landmarks, we collect a novel dataset called L3D, which comprises 1,152 frames with elaborated landmark annotations from surgical videos of 39 patients across two medical sites. For benchmarking purposes, 12 mainstream detection methods are selected and comprehensively evaluated on L3D. Further, we propose a depth-driven geometric prompt learning network, namely D2GPLand. Specifically, we design a Depth-aware Prompt Embedding (DPE) module that is guided by self-supervised prompts and generates semantically relevant geometric information with the benefit of global depth cues extracted from SAM-based features. Additionally, a Semantic-specific Geometric Augmentation (SGA) scheme is introduced to efficiently merge RGB-D spatial and geometric information through reverse anatomic perception. The experimental results indicate that D2GPLand obtains state-of-the-art performance on L3D, with 63.52% DICE and 48.68% IoU scores. Together with 2D-3D fusion technology, our method can directly provide the surgeon with intuitive guidance information in laparoscopic scenarios.
Authors: Sanghyun Kim, Min Jung Lee, Woohyeok Kim, Deunsol Jung, Jaesung Rim, Sunghyun Cho, Minsu Cho
Abstract: Burst image super-resolution has been a topic of active research in recent years due to its ability to obtain a high-resolution image by using complementary information between multiple frames in the burst. In this work, we explore using burst shots with non-uniform exposures to confront real-world practical scenarios by introducing a new benchmark dataset, dubbed Non-uniformly Exposed Burst Image (NEBI), that includes the burst frames at varying exposure times to obtain a broader range of irradiance and motion characteristics within a scene. As burst shots with non-uniform exposures exhibit varying levels of degradation, fusing information of the burst shots into the first frame as a base frame may not result in optimal image quality. To address this limitation, we propose a Frame Selection Network (FSN) for non-uniform scenarios. This network seamlessly integrates into existing super-resolution methods in a plug-and-play manner with low computational costs. The comparative analysis reveals the effectiveness of the nonuniform setting for the practical scenario and our FSN on synthetic-/real- NEBI datasets.
Authors: Ye Won Byun, Cathy Jiao, Shahriar Noroozizadeh, Jimin Sun, Rosa Vitiello
Abstract: We introduce a simple method that employs pre-trained CLIP encoders to enhance model generalization in the ALFRED task. In contrast to previous literature where CLIP replaces the visual encoder, we suggest using CLIP as an additional module through an auxiliary object detection objective. We validate our method on the recently proposed Episodic Transformer architecture and demonstrate that incorporating CLIP improves task performance on the unseen validation set. Additionally, our analysis results support that CLIP especially helps with leveraging object descriptions, detecting small objects, and interpreting rare words.
Authors: Weitong Cai, Jiabo Huang, Shaogang Gong, Hailin Jin, Yang Liu
Abstract: Video Moment Retrieval (VMR) aims to localize a specific temporal segment within an untrimmed long video given a natural language query. Existing methods often suffer from inadequate training annotations, i.e., the sentence typically matches with a fraction of the prominent video content in the foreground with limited wording diversity. This intrinsic modality imbalance leaves a considerable portion of visual information remaining unaligned with text. It confines the cross-modal alignment knowledge within the scope of a limited text corpus, thereby leading to sub-optimal visual-textual modeling and poor generalizability. By leveraging the visual-textual understanding capability of multi-modal large language models (MLLM), in this work, we take an MLLM as a video narrator to generate plausible textual descriptions of the video, thereby mitigating the modality imbalance and boosting the temporal localization. To effectively maintain temporal sensibility for localization, we design to get text narratives for each certain video timestamp and construct a structured text paragraph with time information, which is temporally aligned with the visual content. Then we perform cross-modal feature merging between the temporal-aware narratives and corresponding video temporal features to produce semantic-enhanced video representation sequences for query localization. Subsequently, we introduce a uni-modal narrative-query matching mechanism, which encourages the model to extract complementary information from contextual cohesive descriptions for improved retrieval. Extensive experiments on two benchmarks show the effectiveness and generalizability of our proposed method.
Authors: Bernardo Silva, Jefferson Fontinele, Carolina Let\'icia Zilli Vieira, Jo\~ao Manuel R. S. Tavares, Patricia Ramos Cury, Luciano Oliveira
Abstract: Dental panoramic radiographs offer vast diagnostic opportunities, but training supervised deep learning networks for automatic analysis of those radiology images is hampered by a shortage of labeled data. Here, a different perspective on this problem is introduced. A semi-supervised learning framework is proposed to classify thirteen dental conditions on panoramic radiographs, with a particular emphasis on teeth. Large language models were explored to annotate the most common dental conditions based on dental reports. Additionally, a masked autoencoder was employed to pre-train the classification neural network, and a Vision Transformer was used to leverage the unlabeled data. The analyses were validated using two of the most extensive datasets in the literature, comprising 8,795 panoramic radiographs and 8,029 paired reports and images. Encouragingly, the results consistently met or surpassed the baseline metrics for the Matthews correlation coefficient. A comparison of the proposed solution with human practitioners, supported by statistical analysis, highlighted its effectiveness and performance limitations; based on the degree of agreement among specialists, the solution demonstrated an accuracy level comparable to that of a junior specialist.
Authors: Marwan Zouinkhi, Jeff L. Rhoades, Aubrey V. Weigel
Abstract: Machine learning models are only as good as the data to which they are fit. As such, it is always preferable to use as much data as possible in training models. What data can be used for fitting a model depends a lot on the formulation of the task. We introduce Hot-Distance, a novel segmentation target that incorporates the strength of signed boundary distance prediction with the flexibility of one-hot encoding, to increase the amount of usable training data for segmentation of subcellular structures in focused ion beam scanning electron microscopy (FIB-SEM).
Authors: Liuyi Wang, Zongtao He, Mengjiao Shen, Jingwei Yang, Chengju Liu, Qijun Chen
Abstract: Despite the remarkable developments of recent large models in Embodied Artificial Intelligence (E-AI), their integration into robotics is hampered by their excessive parameter sizes and computational demands. Towards the Vision-and-Language Navigation (VLN) task, a core task in E-AI, this paper reveals the great potential of using knowledge distillation for obtaining lightweight student models by proposing a Meta-Ability Guided Interactive Chain-of-distillation (MAGIC) method. Specifically, a Meta-Ability Knowledge Distillation (MAKD) framework is proposed for decoupling and refining the necessary meta-abilities of VLN agents. A Meta-Knowledge Randomization Weighting (MKRW) and a Meta-Knowledge Transferable Determination (MKTD) module are incorporated to dynamically adjust aggregation weights at the meta-ability and sample levels, respectively. Move beyond the traditional one-step unidirectional distillation, an Interactive Chain-of-Distillation (ICoD) learning strategy is proposed to allow students to give feedback to teachers, forming a new multi-step teacher-student co-evolution pipeline. Remarkably, on the R2R test unseen public leaderboard, our smallest model, MAGIC-S, with only 5% (11M) of the teacher's size, outperforms all previous methods under the same training data. Additionally, our largest model, MAGIC-L, surpasses the previous state-of-the-art by 5.84% in SPL and 3.18% in SR. Furthermore, a new dataset was collected and annotated from our living environments, where MAGIC-S demonstrated superior performance and real-time efficiency. Our code is publicly available on https://github.com/CrystalSixone/VLN-MAGIC.
Authors: Leon Suarez-Rodriguez, Roman Jacome, Henry Arguello
Abstract: Computational optical imaging (COI) systems have enabled the acquisition of high-dimensional signals through optical coding elements (OCEs). OCEs encode the high-dimensional signal in one or more snapshots, which are subsequently decoded using computational algorithms. Currently, COI systems are optimized through an end-to-end (E2E) approach, where the OCEs are modeled as a layer of a neural network and the remaining layers perform a specific imaging task. However, the performance of COI systems optimized through E2E is limited by the physical constraints imposed by these systems. This paper proposes a knowledge distillation (KD) framework for the design of highly physically constrained COI systems. This approach employs the KD methodology, which consists of a teacher-student relationship, where a high-performance, unconstrained COI system (the teacher), guides the optimization of a physically constrained system (the student) characterized by a limited number of snapshots. We validate the proposed approach, using a binary coded apertures single pixel camera for monochromatic and multispectral image reconstruction. Simulation results demonstrate the superiority of the KD scheme over traditional E2E optimization for the designing of highly physically constrained COI systems.
Authors: Qingxuan Wu, Zhiyang Dou, Sirui Xu, Soshi Shimada, Chen Wang, Zhengming Yu, Yuan Liu, Cheng Lin, Zeyu Cao, Taku Komura, Vladislav Golyanik, Christian Theobalt, Wenping Wang, Lingjie Liu
Abstract: Reconstructing 3D hand-face interactions with deformations from a single image is a challenging yet crucial task with broad applications in AR, VR, and gaming. The challenges stem from self-occlusions during single-view hand-face interactions, diverse spatial relationships between hands and face, complex deformations, and the ambiguity of the single-view setting. The first and only method for hand-face interaction recovery, Decaf, introduces a global fitting optimization guided by contact and deformation estimation networks trained on studio-collected data with 3D annotations. However, Decaf suffers from a time-consuming optimization process and limited generalization capability due to its reliance on 3D annotations of hand-face interaction data. To address these issues, we present DICE, the first end-to-end method for Deformation-aware hand-face Interaction reCovEry from a single image. DICE estimates the poses of hands and faces, contacts, and deformations simultaneously using a Transformer-based architecture. It features disentangling the regression of local deformation fields and global mesh vertex locations into two network branches, enhancing deformation and contact estimation for precise and robust hand-face mesh recovery. To improve generalizability, we propose a weakly-supervised training approach that augments the training set using in-the-wild images without 3D ground-truth annotations, employing the depths of 2D keypoints estimated by off-the-shelf models and adversarial priors of poses for supervision. Our experiments demonstrate that DICE achieves state-of-the-art performance on a standard benchmark and in-the-wild data in terms of accuracy and physical plausibility. Additionally, our method operates at an interactive rate (20 fps) on an Nvidia 4090 GPU, whereas Decaf requires more than 15 seconds for a single image. Our code will be publicly available upon publication.
Authors: Zhuo Zheng, Stefano Ermon, Dongjun Kim, Liangpei Zhang, Yanfei Zhong
Abstract: Our understanding of the temporal dynamics of the Earth's surface has been advanced by deep vision models, which often require lots of labeled multi-temporal images for training. However, collecting, preprocessing, and annotating multi-temporal remote sensing images at scale is non-trivial since it is expensive and knowledge-intensive. In this paper, we present change data generators based on generative models, which are cheap and automatic, alleviating these data problems. Our main idea is to simulate a stochastic change process over time. We describe the stochastic change process as a probabilistic graphical model (GPCM), which factorizes the complex simulation problem into two more tractable sub-problems, i.e., change event simulation and semantic change synthesis. To solve these two problems, we present Changen2, a GPCM with a resolution-scalable diffusion transformer which can generate time series of images and their semantic and change labels from labeled or unlabeled single-temporal images. Changen2 is a generative change foundation model that can be trained at scale via self-supervision, and can produce change supervisory signals from unlabeled single-temporal images. Unlike existing foundation models, Changen2 synthesizes change data to train task-specific foundation models for change detection. The resulting model possesses inherent zero-shot change detection capabilities and excellent transferability. Experiments suggest Changen2 has superior spatiotemporal scalability, e.g., Changen2 model trained on 256$^2$ pixel single-temporal images can yield time series of any length and resolutions of 1,024$^2$ pixels. Changen2 pre-trained models exhibit superior zero-shot performance (narrowing the performance gap to 3% on LEVIR-CD and approximately 10% on both S2Looking and SECOND, compared to fully supervised counterparts) and transferability across multiple types of change tasks.
Authors: Yijie Yang, Jinlu Zhang, Jiaxu Zhang, Zhigang Tu
Abstract: In the realm of skeleton-based action recognition, the traditional methods which rely on coarse body keypoints fall short of capturing subtle human actions. In this work, we propose Expressive Keypoints that incorporates hand and foot details to form a fine-grained skeletal representation, improving the discriminative ability for existing models in discerning intricate actions. To efficiently model Expressive Keypoints, the Skeleton Transformation strategy is presented to gradually downsample the keypoints and prioritize prominent joints by allocating the importance weights. Additionally, a plug-and-play Instance Pooling module is exploited to extend our approach to multi-person scenarios without surging computation costs. Extensive experimental results over seven datasets present the superiority of our method compared to the state-of-the-art for skeleton-based human action recognition. Code is available at https://github.com/YijieYang23/SkeleT-GCN.
Authors: Subin Varghese, Vedhus Hoskere
Abstract: The inspection and monitoring of infrastructure assets typically requires identifying visual anomalies in scenes periodically photographed over time. Images collected manually or with robots such as unmanned aerial vehicles from the same scene at different instances in time are typically not perfectly aligned. Supervised segmentation methods can be applied to identify known problems, but unsupervised anomaly detection approaches are required when unknown anomalies occur. Current unsupervised pixel-level anomaly detection methods have mainly been developed for industrial settings where the camera position is known and constant. However, we find that these methods fail to generalize to the case when images are not perfectly aligned. We term the problem of unsupervised anomaly detection between two such imperfectly aligned sets of images as Scene Anomaly Detection (Scene AD). We present a novel network termed OmniAD to address the Scene AD problem posed. Specifically, we refine the anomaly detection method reverse distillation to achieve a 40% increase in pixel-level anomaly detection performance. The network's performance is further demonstrated to improve with two new data augmentation strategies proposed that leverage novel view synthesis and camera localization to improve generalization. We validate our approach with qualitative and quantitative results on a new dataset, ToyCity, the first Scene AD dataset with multiple objects, as well as on the established single object-centric dataset, MAD. https://drags99.github.io/OmniAD/
Authors: Juan David Adarve, Robert Mahony
Abstract: This article introduces the structure flow field; a flow field that can provide high-speed robo-centric motion information for motion control of highly dynamic robotic devices and autonomous vehicles. Structure flow is the angular 3D velocity of the scene at a given pixel. We show that structure flow posses an elegant evolution model in the form of a Partial Differential Equation (PDE) that enables us to create dense flow predictions forward in time. We exploit this structure to design a predictor-update algorithm to compute structure flow in real time using image and depth measurements. The prediction stage takes the previous estimate of the structure flow and propagates it forward in time using a numerical implementation of the structure flow PDE. The predicted flow is then updated using new image and depth data. The algorithm runs up to 600 Hz on a Desktop GPU machine for 512x512 images with flow values up to 8 pixels. We provide ground truth validation on high-speed synthetic image sequences as well as results on real-life video on driving scenarios.
Authors: Dunyuan Xu, Xi Wang, Jingyang Zhang, Pheng-Ann Heng
Abstract: The ability to learn sequentially from different data sites is crucial for a deep network in solving practical medical image diagnosis problems due to privacy restrictions and storage limitations. However, adapting on incoming site leads to catastrophic forgetting on past sites and decreases generalizablity on unseen sites. Existing Continual Learning (CL) and Domain Generalization (DG) methods have been proposed to solve these two challenges respectively, but none of them can address both simultaneously. Recognizing this limitation, this paper proposes a novel training paradigm, learning towards Synchronous Memorizability and Generalizability (SMG-Learning). To achieve this, we create the orientational gradient alignment to ensure memorizability on previous sites, and arbitrary gradient alignment to enhance generalizability on unseen sites. This approach is named as Parallel Gradient Alignment (PGA). Furthermore, we approximate the PGA as dual meta-objectives using the first-order Taylor expansion to reduce computational cost of aligning gradients. Considering that performing gradient alignments, especially for previous sites, is not feasible due to the privacy constraints, we design a Site-Modulated Diffusion (SMD) model to generate images with site-specific learnable prompts, replaying images have similar data distributions as previous sites. We evaluate our method on two medical image segmentation tasks, where data from different sites arrive sequentially. Experimental results show that our method efficiently enhances both memorizability and generalizablity better than other state-of-the-art methods, delivering satisfactory performance across all sites. Our code will be available at: https://github.com/dyxu-cuhkcse/SMG-Learning.
Authors: Wei Su, Peihan Miao, Huanzhang Dou, Xi Li
Abstract: Referring Expression Comprehension (REC) aims to localize the target objects specified by free-form natural language descriptions in images. While state-of-the-art methods achieve impressive performance, they perform a dense perception of images, which incorporates redundant visual regions unrelated to linguistic queries, leading to additional computational overhead. This inspires us to explore a question: can we eliminate linguistic-irrelevant redundant visual regions to improve the efficiency of the model? Existing relevant methods primarily focus on fundamental visual tasks, with limited exploration in vision-language fields. To address this, we propose a coarse-to-fine iterative perception framework, called ScanFormer. It can iteratively exploit the image scale pyramid to extract linguistic-relevant visual patches from top to bottom. In each iteration, irrelevant patches are discarded by our designed informativeness prediction. Furthermore, we propose a patch selection strategy for discarded patches to accelerate inference. Experiments on widely used datasets, namely RefCOCO, RefCOCO+, RefCOCOg, and ReferItGame, verify the effectiveness of our method, which can strike a balance between accuracy and efficiency.
Authors: Xiuen Wu, Tao Wang, Yuanzheng Cai, Lingyu Liang, George Papageorgiou
Abstract: Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method.
Authors: Zhengqing Yuan, Rong Zhou, Hongyi Wang, Lifang He, Yanfang Ye, Lichao Sun
Abstract: Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens. However, the high computational and memory demands of ViTs pose significant challenges for deployment in resource-constrained environments. This paper introduces ViT-1.58b, a novel 1.58-bit quantized ViT model designed to drastically reduce memory and computational overhead while preserving competitive performance. ViT-1.58b employs ternary quantization, which refines the balance between efficiency and accuracy by constraining weights to {-1, 0, 1} and quantizing activations to 8-bit precision. Our approach ensures efficient scaling in terms of both memory and computation. Experiments on CIFAR-10 and ImageNet-1k demonstrate that ViT-1.58b maintains comparable accuracy to full-precision Vit, with significant reductions in memory usage and computational costs. This paper highlights the potential of extreme quantization techniques in developing sustainable AI solutions and contributes to the broader discourse on efficient model deployment in practical applications. Our code and weights are available at https://github.com/DLYuanGod/ViT-1.58b.
Authors: Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha
Abstract: We present a multimodal learning-based method to simultaneously synthesize co-speech facial expressions and upper-body gestures for digital characters using RGB video data captured using commodity cameras. Our approach learns from sparse face landmarks and upper-body joints, estimated directly from video data, to generate plausible emotive character motions. Given a speech audio waveform and a token sequence of the speaker's face landmark motion and body-joint motion computed from a video, our method synthesizes the motion sequences for the speaker's face landmarks and body joints to match the content and the affect of the speech. We design a generator consisting of a set of encoders to transform all the inputs into a multimodal embedding space capturing their correlations, followed by a pair of decoders to synthesize the desired face and pose motions. To enhance the plausibility of synthesis, we use an adversarial discriminator that learns to differentiate between the face and pose motions computed from the original videos and our synthesized motions based on their affective expressions. To evaluate our approach, we extend the TED Gesture Dataset to include view-normalized, co-speech face landmarks in addition to body gestures. We demonstrate the performance of our method through thorough quantitative and qualitative experiments on multiple evaluation metrics and via a user study. We observe that our method results in low reconstruction error and produces synthesized samples with diverse facial expressions and body gestures for digital characters.
Authors: Baoqi Pei, Guo Chen, Jilan Xu, Yuping He, Yicheng Liu, Kanghua Pan, Yifei Huang, Yali Wang, Tong Lu, Limin Wang, Yu Qiao
Abstract: In this report, we present our solutions to the EgoVis Challenges in CVPR 2024, including five tracks in the Ego4D challenge and three tracks in the EPIC-Kitchens challenge. Building upon the video-language two-tower model and leveraging our meticulously organized egocentric video data, we introduce a novel foundation model called EgoVideo. This model is specifically designed to cater to the unique characteristics of egocentric videos and provides strong support for our competition submissions. In the Ego4D challenges, we tackle various tasks including Natural Language Queries, Step Grounding, Moment Queries, Short-term Object Interaction Anticipation, and Long-term Action Anticipation. In addition, we also participate in the EPIC-Kitchens challenge, where we engage in the Action Recognition, Multiple Instance Retrieval, and Domain Adaptation for Action Recognition tracks. By adapting EgoVideo to these diverse tasks, we showcase its versatility and effectiveness in different egocentric video analysis scenarios, demonstrating the powerful representation ability of EgoVideo as an egocentric foundation model. Our codebase and pretrained models are publicly available at https://github.com/OpenGVLab/EgoVideo.
Authors: Song Tang, Shaxu Yan, Xiaozhi Qi, Jianxin Gao, Mao Ye, Jianwei Zhang, Xiatian Zhu
Abstract: Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are limited to the imaging scenarios with considerably distinct objects and not highly complex background, e.g., natural images. This makes such models suboptimal for medical imaging with both conditions invalid. To address this problem, we propose a novel Detail Self-refined Prototype Network (DSPNet) to constructing high-fidelity prototypes representing the object foreground and the background more comprehensively. Specifically, to construct global semantics while maintaining the captured detail semantics, we learn the foreground prototypes by modelling the multi-modal structures with clustering and then fusing each in a channel-wise manner. Considering that the background often has no apparent semantic relation in the spatial dimensions, we integrate channel-specific structural information under sparse channel-aware regulation. Extensive experiments on three challenging medical image benchmarks show the superiority of DSPNet over previous state-of-the-art methods.
Authors: Yiguo Jiang, Xuhang Chen, Chi-Man Pun, Shuqiang Wang, Wei Feng
Abstract: When light is scattered or reflected accidentally in the lens, flare artifacts may appear in the captured photos, affecting the photos' visual quality. The main challenge in flare removal is to eliminate various flare artifacts while preserving the original content of the image. To address this challenge, we propose a lightweight Multi-Frequency Deflare Network (MFDNet) based on the Laplacian Pyramid. Our network decomposes the flare-corrupted image into low and high-frequency bands, effectively separating the illumination and content information in the image. The low-frequency part typically contains illumination information, while the high-frequency part contains detailed content information. So our MFDNet consists of two main modules: the Low-Frequency Flare Perception Module (LFFPM) to remove flare in the low-frequency part and the Hierarchical Fusion Reconstruction Module (HFRM) to reconstruct the flare-free image. Specifically, to perceive flare from a global perspective while retaining detailed information for image restoration, LFFPM utilizes Transformer to extract global information while utilizing a convolutional neural network to capture detailed local features. Then HFRM gradually fuses the outputs of LFFPM with the high-frequency component of the image through feature aggregation. Moreover, our MFDNet can reduce the computational cost by processing in multiple frequency bands instead of directly removing the flare on the input image. Experimental results demonstrate that our approach outperforms state-of-the-art methods in removing nighttime flare on real-world and synthetic images from the Flare7K dataset. Furthermore, the computational complexity of our model is remarkably low.
Authors: Meinardus Boris, Batra Anil, Rohrbach Anna, Rohrbach Marcus
Abstract: Recent studies have shown promising results in utilizing multimodal large language models (MLLMs) for computer vision tasks such as object detection and semantic segmentation. However, many challenging video tasks remain under-explored. Video-language tasks necessitate spatial and temporal comprehension and require significant compute. Therefore, prior works have developed complex, highly specialized architectures or leveraged additional input signals such as video transcripts to best encode contextual and temporal information, which limits their generality and can be impractical. One particularly challenging task is video moment retrieval, which requires precise temporal and contextual grounding. This work demonstrates the surprising effectiveness of leveraging image-text pretrained MLLMs for moment retrieval. We introduce Mr. BLIP (Mr. as in Moment Retrieval), a multimodal, single-stage model that requires no expensive video-language pretraining, no additional input signal (e.g., no transcript or audio), and has a simpler and more versatile design than prior state-of-the-art methods. We achieve a new state-of-the-art in moment retrieval on the widely used benchmarks Charades-STA, QVHighlights, and ActivityNet Captions and illustrate our method's versatility with a new state-of-the-art in temporal action localization on ActivityNet. Notably, we attain over 9% (absolute) higher Recall (at 0.5 and 0.7 IoU) on the challenging long-video multi-moment QVHighlights benchmark. Our code is publicly available.
Authors: Meiying Zhang, Weiyuan Peng, Guangyao Ding, Chenyang Lei, Chunlin Ji, Qi Hao
Abstract: Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality (sim-to-real), cross-domain object detection algorithms usually suffer from dramatic performance drops. While numerous unsupervised domain adaptation (UDA) methods have been developed to address cross-domain tasks between real-world datasets, progress in sim-to-real remains limited. This paper presents a novel Complex-to-Simple (CTS) framework to transfer models from labeled simulation (source) to unlabeled reality (target) domains. Based on a two-stage detector, the novelty of this work is threefold: 1) developing fixed-size anchor heads and RoI augmentation to address size bias and feature diversity between two domains, thereby improving the quality of pseudo-label; 2) developing a novel corner-format representation of aleatoric uncertainty (AU) for the bounding box, to uniformly quantify pseudo-label quality; 3) developing a noise-aware mean teacher domain adaptation method based on AU, as well as object-level and frame-level sampling strategies, to migrate the impact of noisy labels. Experimental results demonstrate that our proposed approach significantly enhances the sim-to-real domain adaptation capability of 3D object detection models, outperforming state-of-the-art cross-domain algorithms, which are usually developed for real-to-real UDA tasks.
Authors: Yicheng Wang, Feng Liu, Junmin Liu, Zhen Fang, Kai Sun
Abstract: As a promising field in open-world learning, \textit{Novel Class Discovery} (NCD) is usually a task to cluster unseen novel classes in an unlabeled set based on the prior knowledge of labeled data within the same domain. However, the performance of existing NCD methods could be severely compromised when novel classes are sampled from a different distribution with the labeled ones. In this paper, we explore and establish the solvability of NCD in cross domain setting with the necessary condition that style information must be removed. Based on the theoretical analysis, we introduce an exclusive style removal module for extracting style information that is distinctive from the baseline features, thereby facilitating inference. Moreover, this module is easy to integrate with other NCD methods, acting as a plug-in to improve performance on novel classes with different distributions compared to the seen labeled set. Additionally, recognizing the non-negligible influence of different backbones and pre-training strategies on the performance of the NCD methods, we build a fair benchmark for future NCD research. Extensive experiments on three common datasets demonstrate the effectiveness of our proposed module.
Authors: Min Ren, Yunlong Wang, Yuhao Zhu, Yongzhen Huang, Zhenan Sun, Qi Li, Tieniu Tan
Abstract: Insect production for food and feed presents a promising supplement to ensure food safety and address the adverse impacts of agriculture on climate and environment in the future. However, optimisation is required for insect production to realise its full potential. This can be by targeted improvement of traits of interest through selective breeding, an approach which has so far been underexplored and underutilised in insect farming. Here we present a comprehensive review of the selective breeding framework in the context of insect production. We systematically evaluate adjustments of selective breeding techniques to the realm of insects and highlight the essential components integral to the breeding process. The discussion covers every step of a conventional breeding scheme, such as formulation of breeding objectives, phenotyping, estimation of genetic parameters and breeding values, selection of appropriate breeding strategies, and mitigation of issues associated with genetic diversity depletion and inbreeding. This review combines knowledge from diverse disciplines, bridging the gap between animal breeding, quantitative genetics, evolutionary biology, and entomology, offering an integrated view of the insect breeding research area and uniting knowledge which has previously remained scattered across diverse fields of expertise.
Authors: Xiaoshuang Huang, Haifeng Huang, Lingdong Shen, Yehui Yang, Fangxin Shang, Junwei Liu, Jia Liu
Abstract: With the rapid development of multimodal large language models (MLLMs), especially their capabilities in visual chat through refer and ground functionalities, their significance is increasingly recognized. However, the biomedical field currently exhibits a substantial gap in this area, primarily due to the absence of a dedicated refer and ground dataset for biomedical images. To address this challenge, we devised the Med-GRIT-270k dataset. It comprises 270k question-and-answer pairs and spans eight distinct medical imaging modalities. Most importantly, it is the first dedicated to the biomedical domain and integrating refer and ground conversations. The key idea is to sample large-scale biomedical image-mask pairs from medical segmentation datasets and generate instruction datasets from text using chatGPT. Additionally, we introduce a Refer-and-Ground Multimodal Large Language Model for Biomedicine (BiRD) by using this dataset and multi-task instruction learning. Extensive experiments have corroborated the efficacy of the Med-GRIT-270k dataset and the multi-modal, fine-grained interactive capabilities of the BiRD model. This holds significant reference value for the exploration and development of intelligent biomedical assistants.
Authors: Jian Song, Hongruixuan Chen, Weihao Xuan, Junshi Xia, Naoto Yokoya
Abstract: Global semantic 3D understanding from single-view high-resolution remote sensing (RS) imagery is crucial for Earth Observation (EO). However, this task faces significant challenges due to the high costs of annotations and data collection, as well as geographically restricted data availability. To address these challenges, synthetic data offer a promising solution by being easily accessible and thus enabling the provision of large and diverse datasets. We develop a specialized synthetic data generation pipeline for EO and introduce SynRS3D, the largest synthetic RS 3D dataset. SynRS3D comprises 69,667 high-resolution optical images that cover six different city styles worldwide and feature eight land cover types, precise height information, and building change masks. To further enhance its utility, we develop a novel multi-task unsupervised domain adaptation (UDA) method, RS3DAda, coupled with our synthetic dataset, which facilitates the RS-specific transition from synthetic to real scenarios for land cover mapping and height estimation tasks, ultimately enabling global monocular 3D semantic understanding based on synthetic data. Extensive experiments on various real-world datasets demonstrate the adaptability and effectiveness of our synthetic dataset and proposed RS3DAda method. SynRS3D and related codes will be available.
Authors: Xiaolin Hong, Hongwei Yi, Fazhi He, Qiong Cao
Abstract: Generating 3D scenes from human motion sequences supports numerous applications, including virtual reality and architectural design. However, previous auto-regression-based human-aware 3D scene generation methods have struggled to accurately capture the joint distribution of multiple objects and input humans, often resulting in overlapping object generation in the same space. To address this limitation, we explore the potential of diffusion models that simultaneously consider all input humans and the floor plan to generate plausible 3D scenes. Our approach not only satisfies all input human interactions but also adheres to spatial constraints with the floor plan. Furthermore, we introduce two spatial collision guidance mechanisms: human-object collision avoidance and object-room boundary constraints. These mechanisms help avoid generating scenes that conflict with human motions while respecting layout constraints. To enhance the diversity and accuracy of human-guided scene generation, we have developed an automated pipeline that improves the variety and plausibility of human-object interactions in the existing 3D FRONT HUMAN dataset. Extensive experiments on both synthetic and real-world datasets demonstrate that our framework can generate more natural and plausible 3D scenes with precise human-scene interactions, while significantly reducing human-object collisions compared to previous state-of-the-art methods. Our code and data will be made publicly available upon publication of this work.
Authors: Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios, Osman Semih Kayhan, Davide Zambrano, Nergis Tomen, Jan van Gemert
Abstract: The fourth edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" workshop features two data-impaired challenges. These challenges address the problem of training deep learning models for computer vision tasks with limited data. Participants are limited to training models from scratch using a low number of training samples and are not allowed to use any form of transfer learning. We aim to stimulate the development of novel approaches that incorporate inductive biases to improve the data efficiency of deep learning models. Significant advancements are made compared to the provided baselines, where winning solutions surpass the baselines by a considerable margin in both tasks. As in previous editions, these achievements are primarily attributed to heavy use of data augmentation policies and large model ensembles, though novel prior-based methods seem to contribute more to successful solutions compared to last year. This report highlights the key aspects of the challenges and their outcomes.
Authors: Qi She, Junwen Pan, Xin Wan, Rui Zhang, Dawei Lu, Kai Huang
Abstract: In this report, we introduce MammothModa, yet another multi-modal large language model (MLLM) designed to achieve state-of-the-art performance starting from an elementary baseline. We focus on three key design insights: (i) Integrating Visual Capabilities while Maintaining Complex Language Understanding: In addition to the vision encoder, we incorporated the Visual Attention Experts into the LLM to enhance its visual capabilities. (ii) Extending Context Window for High-Resolution and Long-Duration Visual Feature: We explore the Visual Merger Module to effectively reduce the token number of high-resolution images and incorporated frame position ids to avoid position interpolation. (iii) High-Quality Bilingual Datasets: We meticulously curated and filtered a high-quality bilingual multimodal dataset to reduce visual hallucinations. With above recipe we build MammothModa that consistently outperforms the state-of-the-art models, e.g., LLaVA-series, across main real-world visual language benchmarks without bells and whistles.
Authors: Pi-Wei Chen, Jerry Chun-Wei Lin, Jia Ji, Feng-Hao Yeh, Chao-Chun Chen
Abstract: Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning, making prompt-based anomaly detection a promising approach. Traditional methods depend on human-crafted prompts that require prior knowledge of specific anomaly types. Our goal is to develop a human-free prompt-based anomaly detection framework that optimally learns prompts through data-driven methods, eliminating the need for human intervention. The primary challenge in this approach is the lack of anomalous samples during the training phase. Additionally, the Vision Transformer (ViT)-based image encoder in VLMs is not ideal for pixel-wise anomaly segmentation due to a locality feature mismatch between the original image and the output feature map. To tackle the first challenge, we have developed the Object-Attention Anomaly Generation Module (OAGM) to synthesize anomaly samples for training. Furthermore, our Meta-Guiding Prompt-Tuning Scheme (MPTS) iteratively adjusts the gradient-based optimization direction of learnable prompts to avoid overfitting to the synthesized anomalies. For the second challenge, we propose Locality-Aware Attention, which ensures that each local patch feature attends only to nearby patch features, preserving the locality features corresponding to their original locations. This framework allows for the optimal prompt embeddings by searching in the continuous latent space via backpropagation, free from human semantic constraints. Additionally, the modified locality-aware attention improves the precision of pixel-wise anomaly segmentation.
Authors: Hao Li, Jingfeng Li, Dingwen Zhang, Chenming Wu, Jieqi Shi, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Junwei Han
Abstract: Dynamic Gaussian splatting has led to impressive scene reconstruction and image synthesis advances in novel views. Existing methods, however, heavily rely on pre-computed poses and Gaussian initialization by Structure from Motion (SfM) algorithms or expensive sensors. For the first time, this paper addresses this issue by integrating self-supervised VO into our pose-free dynamic Gaussian method (VDG) to boost pose and depth initialization and static-dynamic decomposition. Moreover, VDG can work with only RGB image input and construct dynamic scenes at a faster speed and larger scenes compared with the pose-free dynamic view-synthesis method. We demonstrate the robustness of our approach via extensive quantitative and qualitative experiments. Our results show favorable performance over the state-of-the-art dynamic view synthesis methods. Additional video and source code will be posted on our project page at https://3d-aigc.github.io/VDG.
Authors: Jiaze Li, Zhengyu Wen, Luo Zhang, Jiangbei Hu, Fei Hou, Zhebin Zhang, Ying He
Abstract: The 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi-view images, enabling real-time rendering. While point-based rasterization effectively reduces computational demands for rendering, it often struggles to accurately reconstruct the geometry of the target object, especially under strong lighting. To address this challenge, we introduce a novel approach that combines octree-based implicit surface representations with Gaussian splatting. Our method consists of four stages. Initially, it reconstructs a signed distance field (SDF) and a radiance field through volume rendering, encoding them in a low-resolution octree. The initial SDF represents the coarse geometry of the target object. Subsequently, it introduces 3D Gaussians as additional degrees of freedom, which are guided by the SDF. In the third stage, the optimized Gaussians further improve the accuracy of the SDF, allowing it to recover finer geometric details compared to the initial SDF obtained in the first stage. Finally, it adopts the refined SDF to further optimize the 3D Gaussians via splatting, eliminating those that contribute little to visual appearance. Experimental results show that our method, which leverages the distribution of 3D Gaussians with SDFs, reconstructs more accurate geometry, particularly in images with specular highlights caused by strong lighting.
Authors: Muhammad Salman Ali, Maryam Qamar, Sung-Ho Bae, Enzo Tartaglione
Abstract: In recent times, the utilization of 3D models has gained traction, owing to the capacity for end-to-end training initially offered by Neural Radiance Fields and more recently by 3D Gaussian Splatting (3DGS) models. The latter holds a significant advantage by inherently easing rapid convergence during training and offering extensive editability. However, despite rapid advancements, the literature still lives in its infancy regarding the scalability of these models. In this study, we take some initial steps in addressing this gap, showing an approach that enables both the memory and computational scalability of such models. Specifically, we propose "Trimming the fat", a post-hoc gradient-informed iterative pruning technique to eliminate redundant information encoded in the model. Our experimental findings on widely acknowledged benchmarks attest to the effectiveness of our approach, revealing that up to 75% of the Gaussians can be removed while maintaining or even improving upon baseline performance. Our approach achieves around 50$\times$ compression while preserving performance similar to the baseline model, and is able to speed-up computation up to 600~FPS.
Authors: Max Kahl, Sebastian Stricker, Lisa Hutschenreiter, Florian Bernard, Bogdan Savchynskyy
Abstract: We consider the incomplete multi-graph matching problem, which is a generalization of the NP-hard quadratic assignment problem for matching multiple finite sets. Multi-graph matching plays a central role in computer vision, e.g., for matching images or shapes, so that a number of dedicated optimization techniques have been proposed. While the closely related NP-hard multi-dimensional assignment problem (MDAP) has been studied for decades in the operations research community, it only considers complete matchings and has a different cost structure. We bridge this gap and transfer well-known approximation algorithms for the MDAP to incomplete multi-graph matching. To this end, we revisit respective algorithms, adapt them to incomplete multi-graph matching, and propose their extended and parallelized versions. Our experimental validation shows that our new method substantially outperforms the previous state of the art in terms of objective and runtime. Our algorithm matches, for example, 29 images with more than 500 keypoints each in less than two minutes, whereas the fastest considered competitor requires at least half an hour while producing far worse results.
Authors: Patrick Takenaka, Johannes Maucher, Marco F. Huber
Abstract: We propose a general way to integrate procedural knowledge of a domain into deep learning models. We apply it to the case of video prediction, building on top of object-centric deep models and show that this leads to a better performance than using data-driven models alone. We develop an architecture that facilitates latent space disentanglement in order to use the integrated procedural knowledge, and establish a setup that allows the model to learn the procedural interface in the latent space using the downstream task of video prediction. We contrast the performance to a state-of-the-art data-driven approach and show that problems where purely data-driven approaches struggle can be handled by using knowledge about the domain, providing an alternative to simply collecting more data.
Authors: Jiafeng Liang, Shixin Jiang, Zekun Wang, Haojie Pan, Zerui Chen, Zheng Chu, Ming Liu, Ruiji Fu, Zhongyuan Wang, Bing Qin
Abstract: There are substantial instructional videos on the Internet, which provide us tutorials for completing various tasks. Existing instructional video datasets only focus on specific steps at the video level, lacking experiential guidelines at the task level, which can lead to beginners struggling to learn new tasks due to the lack of relevant experience. Moreover, the specific steps without guidelines are trivial and unsystematic, making it difficult to provide a clear tutorial. To address these problems, we present the GUIDE (Guideline-Guided) dataset, which contains 3.5K videos of 560 instructional tasks in 8 domains related to our daily life. Specifically, we annotate each instructional task with a guideline, representing a common pattern shared by all task-related videos. On this basis, we annotate systematic specific steps, including their associated guideline steps, specific step descriptions and timestamps. Our proposed benchmark consists of three sub-tasks to evaluate comprehension ability of models: (1) Step Captioning: models have to generate captions for specific steps from videos. (2) Guideline Summarization: models have to mine the common pattern in task-related videos and summarize a guideline from them. (3) Guideline-Guided Captioning: models have to generate captions for specific steps under the guide of guideline. We evaluate plenty of foundation models with GUIDE and perform in-depth analysis. Given the diversity and practicality of GUIDE, we believe that it can be used as a better benchmark for instructional video comprehension.
Authors: Kira Schmitt, J\"urgen Titschack, Daniel Baum
Abstract: Herein, we present CoDA, the Coral Dendroid structure Analyzer, a visual analytics suite that allows for the first time to investigate the ontogenetic morphological development of complex dendroid coral colonies, exemplified on three important framework-forming dendroid cold-water corals: Lophelia pertusa (Linnaeus, 1758), Madrepora oculata (Linnaeus, 1758), and Goniocorella dumosa (Alcock, 1902). Input to CoDA is an initial instance segmentation of the coral polyp cavities (calices), from which it estimates the skeleton tree of the colony and extracts classical morphological measurements and advanced shape features of the individual corallites. CoDA also works as a proofreading and error correction tool by helping to identify wrong parts in the skeleton tree and providing tools to quickly correct these errors. The final skeleton tree enables the derivation of additional information about the calices/corallite instances that otherwise could not be obtained, including their ontogenetic generation and branching patterns - the basis of a fully quantitative statistical analysis of the coral colony morphology. Part of CoDA is CoDAGraph, a feature-rich link-and-brush user interface for visualizing the extracted features and 2D graph layouts of the skeleton tree, enabling the real-time exploration of complex coral colonies and their building blocks, the individual corallites and branches. In the future, we expect CoDA to greatly facilitate the analysis of large stony corals of different species and morphotypes, as well as other dendroid structures, enabling new insights into the influence of genetic and environmental factors on their ontogenetic morphological development.
Authors: Dongqi Fan, Junhao Zhang, Liang Chang
Abstract: This paper introduces ConStyle v2, a strong plug-and-play prompter designed to output clean visual prompts and assist U-Net Image Restoration models in handling multiple degradations. The joint training process of IRConStyle, an Image Restoration framework consisting of ConStyle and a general restoration network, is divided into two stages: first, pre-training ConStyle alone, and then freezing its weights to guide the training of the general restoration network. Three improvements are proposed in the pre-training stage to train ConStyle: unsupervised pre-training, adding a pretext task (i.e. classification), and adopting knowledge distillation. Without bells and whistles, we can get ConStyle v2, a strong prompter for all-in-one Image Restoration, in less than two GPU days and doesn't require any fine-tuning. Extensive experiments on Restormer (transformer-based), NAFNet (CNN-based), MAXIM-1S (MLP-based), and a vanilla CNN network demonstrate that ConStyle v2 can enhance any U-Net style Image Restoration models to all-in-one Image Restoration models. Furthermore, models guided by the well-trained ConStyle v2 exhibit superior performance in some specific degradation compared to ConStyle.
Authors: Daniel Reich, Tanja Schultz
Abstract: Visual Grounding (VG) in VQA refers to a model's proclivity to infer answers based on question-relevant image regions. Conceptually, VG identifies as an axiomatic requirement of the VQA task. In practice, however, DNN-based VQA models are notorious for bypassing VG by way of shortcut (SC) learning without suffering obvious performance losses in standard benchmarks. To uncover the impact of SC learning, Out-of-Distribution (OOD) tests have been proposed that expose a lack of VG with low accuracy. These tests have since been at the center of VG research and served as basis for various investigations into VG's impact on accuracy. However, the role of VG in VQA still remains not fully understood and has not yet been properly formalized. In this work, we seek to clarify VG's role in VQA by formalizing it on a conceptual level. We propose a novel theoretical framework called "Visually Grounded Reasoning" (VGR) that uses the concepts of VG and Reasoning to describe VQA inference in ideal OOD testing. By consolidating fundamental insights into VG's role in VQA, VGR helps to reveal rampant VG-related SC exploitation in OOD testing, which explains why the relationship between VG and OOD accuracy has been difficult to define. Finally, we propose an approach to create OOD tests that properly emphasize a requirement for VG, and show how to improve performance on them.
Authors: Sowdagar Mahammad Shahid, Sudev Kumar Padhi, Umesh Kashyap, Sk. Subidh Ali
Abstract: The landscape of fake media creation changed with the introduction of Generative Adversarial Networks (GAN s). Fake media creation has been on the rise with the rapid advances in generation technology, leading to new challenges in Detecting fake media. A fundamental characteristic of GAN s is their sensitivity to parameter initialization, known as seeds. Each distinct seed utilized during training leads to the creation of unique model instances, resulting in divergent image outputs despite employing the same architecture. This means that even if we have one GAN architecture, it can produce countless variations of GAN models depending on the seed used. Existing methods for attributing deepfakes work well only if they have seen the specific GAN model during training. If the GAN architectures are retrained with a different seed, these methods struggle to attribute the fakes. This seed dependency issue made it difficult to attribute deepfakes with existing methods. We proposed a generalized deepfake attribution network (GDA-N et) to attribute fake images to their respective GAN architectures, even if they are generated from a retrained version of the GAN architecture with a different seed (cross-seed) or from the fine-tuned version of the existing GAN model. Extensive experiments on cross-seed and fine-tuned data of GAN models show that our method is highly effective compared to existing methods. We have provided the source code to validate our results.
Authors: Nikolaos Dionelis, Nicolas Longepe
Abstract: Confidence assessments of semantic segmentation algorithms in remote sensing are important. It is a desirable property of models to a priori know if they produce an incorrect output. Evaluations of the confidence assigned to the estimates of models for the task of classification in Earth Observation (EO) are crucial as they can be used to achieve improved semantic segmentation performance and prevent high error rates during inference and deployment. The model we develop, the Confidence Assessments of classification algorithms for Semantic segmentation (CAS) model, performs confidence evaluations at both the segment and pixel levels, and outputs both labels and confidence. The outcome of this work has important applications. The main application is the evaluation of EO Foundation Models on semantic segmentation downstream tasks, in particular land cover classification using satellite Copernicus Sentinel-2 data. The evaluation shows that the proposed model is effective and outperforms other alternative baseline models.
Authors: Xiaozhong Ji, Chuming Lin, Zhonggan Ding, Ying Tai, Jian Yang, Junwei Zhu, Xiaobin Hu, Jiangning Zhang, Donghao Luo, Chengjie Wang
Abstract: Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual synchronization, but there is still a significant gap between current results and practical applications. The challenges are two-fold: 1) Preserving unique individual traits for achieving high-precision lip synchronization. 2) Generating high-quality facial renderings in real-time performance. In this paper, we propose a novel generalized audio-driven framework RealTalk, which consists of an audio-to-expression transformer and a high-fidelity expression-to-face renderer. In the first component, we consider both identity and intra-personal variation features related to speaking lip movements. By incorporating cross-modal attention on the enriched facial priors, we can effectively align lip movements with audio, thus attaining greater precision in expression prediction. In the second component, we design a lightweight facial identity alignment (FIA) module which includes a lip-shape control structure and a face texture reference structure. This novel design allows us to generate fine details in real-time, without depending on sophisticated and inefficient feature alignment modules. Our experimental results, both quantitative and qualitative, on public datasets demonstrate the clear advantages of our method in terms of lip-speech synchronization and generation quality. Furthermore, our method is efficient and requires fewer computational resources, making it well-suited to meet the needs of practical applications.
Authors: Nikolaos Dionelis, Casper Fibaek, Luke Camilleri, Andreas Luyts, Jente Bosmans, Bertrand Le Saux
Abstract: When we are primarily interested in solving several problems jointly with a given prescribed high performance accuracy for each target application, then Foundation Models should for most cases be used rather than problem-specific models. We focus on the specific Computer Vision application of Foundation Models for Earth Observation (EO) and geospatial AI. These models can solve important problems we are tackling, including for example land cover classification, crop type mapping, flood segmentation, building density estimation, and road regression segmentation. In this paper, we show that for a limited number of labelled data, Foundation Models achieve improved performance compared to problem-specific models. In this work, we also present our proposed evaluation benchmark for Foundation Models for EO. Benchmarking the generalization performance of Foundation Models is important as it has become difficult to standardize a fair comparison across the many different models that have been proposed recently. We present the results using our evaluation benchmark for EO Foundation Models and show that Foundation Models are label efficient in the downstream tasks and help us solve problems we are tackling in EO and remote sensing.
Authors: Wenting Chen, Jie Liu, Tommy W. S. Chow, Yixuan Yuan
Abstract: Pathology image are essential for accurately interpreting lesion cells in cytopathology screening, but acquiring high-resolution digital slides requires specialized equipment and long scanning times. Though super-resolution (SR) techniques can alleviate this problem, existing deep learning models recover pathology image in a black-box manner, which can lead to untruthful biological details and misdiagnosis. Additionally, current methods allocate the same computational resources to recover each pixel of pathology image, leading to the sub-optimal recovery issue due to the large variation of pathology image. In this paper, we propose the first hierarchical reinforcement learning framework named Spatial-Temporal hierARchical Reinforcement Learning (STAR-RL), mainly for addressing the aforementioned issues in pathology image super-resolution problem. We reformulate the SR problem as a Markov decision process of interpretable operations and adopt the hierarchical recovery mechanism in patch level, to avoid sub-optimal recovery. Specifically, the higher-level spatial manager is proposed to pick out the most corrupted patch for the lower-level patch worker. Moreover, the higher-level temporal manager is advanced to evaluate the selected patch and determine whether the optimization should be stopped earlier, thereby avoiding the over-processed problem. Under the guidance of spatial-temporal managers, the lower-level patch worker processes the selected patch with pixel-wise interpretable actions at each time step. Experimental results on medical images degraded by different kernels show the effectiveness of STAR-RL. Furthermore, STAR-RL validates the promotion in tumor diagnosis with a large margin and shows generalizability under various degradations. The source code is available at https://github.com/CUHK-AIM-Group/STAR-RL.
Authors: Hossein Ranjbar, Alireza Taheri
Abstract: Many continuous sign language recognition (CSLR) studies adopt transformer-based architectures for sequence modeling due to their powerful capacity for capturing global contexts. Nevertheless, vanilla self-attention, which serves as the core module of the transformer, calculates a weighted average over all time steps; therefore, the local temporal semantics of sign videos may not be fully exploited. In this study, we introduce a novel module in sign language recognition studies, called intra-inter gloss attention module, to leverage the relationships among frames within glosses and the semantic and grammatical dependencies between glosses in the video. In the intra-gloss attention module, the video is divided into equally sized chunks and a self-attention mechanism is applied within each chunk. This localized self-attention significantly reduces complexity and eliminates noise introduced by considering non-relative frames. In the inter-gloss attention module, we first aggregate the chunk-level features within each gloss chunk by average pooling along the temporal dimension. Subsequently, multi-head self-attention is applied to all chunk-level features. Given the non-significance of the signer-environment interaction, we utilize segmentation to remove the background of the videos. This enables the proposed model to direct its focus toward the signer. Experimental results on the PHOENIX-2014 benchmark dataset demonstrate that our method can effectively extract sign language features in an end-to-end manner without any prior knowledge, improve the accuracy of CSLR, and achieve the word error rate (WER) of 20.4 on the test set which is a competitive result compare to the state-of-the-art which uses additional supervisions.
Authors: Huzheng Yang, James Gee, Jianbo Shi
Abstract: We study the intriguing connection between visual data, deep networks, and the brain. Our method creates a universal channel alignment by using brain voxel fMRI response prediction as the training objective. We discover that deep networks, trained with different objectives, share common feature channels across various models. These channels can be clustered into recurring sets, corresponding to distinct brain regions, indicating the formation of visual concepts. Tracing the clusters of channel responses onto the images, we see semantically meaningful object segments emerge, even without any supervised decoder. Furthermore, the universal feature alignment and the clustering of channels produce a picture and quantification of how visual information is processed through the different network layers, which produces precise comparisons between the networks.
Authors: Thomas Louis, Benoit Miramond, Alain Pegatoquet, Adrien Girard
Abstract: Interest in spiking neural networks (SNNs) has been growing steadily, promising an energy-efficient alternative to formal neural networks (FNNs), commonly known as artificial neural networks (ANNs). Despite increasing interest, especially for Edge applications, these event-driven neural networks suffered from their difficulty to be trained compared to FNNs. To alleviate this problem, a number of innovative methods have been developed to provide performance more or less equivalent to that of FNNs. However, the spiking activity of a network during inference is usually not considered. While SNNs may usually have performance comparable to that of FNNs, it is often at the cost of an increase of the network's activity, thus limiting the benefit of using them as a more energy-efficient solution. In this paper, we propose to leverage Knowledge Distillation (KD) for SNNs training with surrogate gradient descent in order to optimize the trade-off between performance and spiking activity. Then, after understanding why KD led to an increase in sparsity, we also explored Activations regularization and proposed a novel method with Logits Regularization. These approaches, validated on several datasets, clearly show a reduction in network spiking activity (-26.73% on GSC and -14.32% on CIFAR-10) while preserving accuracy.
Authors: Hao Li, Ming Yuan, Yan Zhang, Chenming Wu, Chen Zhao, Chunyu Song, Haocheng Feng, Errui Ding, Dingwen Zhang, Jingdong Wang
Abstract: Thoroughly testing autonomy systems is crucial in the pursuit of safe autonomous driving vehicles. It necessitates creating safety-critical scenarios that go beyond what can be safely collected from real-world data, as many of these scenarios occur infrequently on public roads. However, the evaluation of most existing NVS methods relies on sporadic sampling of image frames from the training data, comparing the rendered images with ground truth images using metrics. Unfortunately, this evaluation protocol falls short of meeting the actual requirements in closed-loop simulations. Specifically, the true application demands the capability to render novel views that extend beyond the original trajectory (such as cross-lane views), which are challenging to capture in the real world. To address this, this paper presents a novel driving view synthesis dataset and benchmark specifically designed for autonomous driving simulations. This dataset is unique as it includes testing images captured by deviating from the training trajectory by 1-4 meters. It comprises six sequences encompassing various time and weather conditions. Each sequence contains 450 training images, 150 testing images, and their corresponding camera poses and intrinsic parameters. Leveraging this novel dataset, we establish the first realistic benchmark for evaluating existing NVS approaches under front-only and multi-camera settings. The experimental findings underscore the significant gap that exists in current approaches, revealing their inadequate ability to fulfill the demanding prerequisites of cross-lane or closed-loop simulation. Our dataset is released publicly at the project page: https://3d-aigc.github.io/XLD/.
Authors: Tianyu Lin, Zhiguang Chen, Zhonghao Yan, Fudan Zheng, Weijiang Yu
Abstract: Diffusion models have demonstrated their effectiveness across various generative tasks. However, when applied to medical image segmentation, these models encounter several challenges, including significant resource and time requirements. They also necessitate a multi-step reverse process and multiple samples to produce reliable predictions. To address these challenges, we introduce the first latent diffusion segmentation model, named SDSeg, built upon stable diffusion (SD). SDSeg incorporates a straightforward latent estimation strategy to facilitate a single-step reverse process and utilizes latent fusion concatenation to remove the necessity for multiple samples. Extensive experiments indicate that SDSeg surpasses existing state-of-the-art methods on five benchmark datasets featuring diverse imaging modalities. Remarkably, SDSeg is capable of generating stable predictions with a solitary reverse step and sample, epitomizing the model's stability as implied by its name. The code is available at https://github.com/lin-tianyu/Stable-Diffusion-Seg
Authors: Janet Wang, Yunsung Chung, Zhengming Ding, Jihun Hamm
Abstract: AI-based diagnoses have demonstrated dermatologist-level performance in classifying skin cancer. However, such systems are prone to under-performing when tested on data from minority groups that lack sufficient representation in the training sets. Although data collection and annotation offer the best means for promoting minority groups, these processes are costly and time-consuming. Prior works have suggested that data from majority groups may serve as a valuable information source to supplement the training of diagnosis tools for minority groups. In this work, we propose an effective diffusion-based augmentation framework that maximizes the use of rich information from majority groups to benefit minority groups. Using groups with different skin types as a case study, our results show that the proposed framework can generate synthetic images that improve diagnostic results for the minority groups, even when there is little or no reference data from these target groups. The practical value of our work is evident in medical imaging analysis, where under-diagnosis persists as a problem for certain groups due to insufficient representation.
Authors: Mohamed Sayed, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel Brostow, Sara Vicente, Michael Firman
Abstract: Estimating depth from a sequence of posed RGB images is a fundamental computer vision task, with applications in augmented reality, path planning etc. Prior work typically makes use of previous frames in a multi view stereo framework, relying on matching textures in a local neighborhood. In contrast, our model leverages historical predictions by giving the latest 3D geometry data as an extra input to our network. This self-generated geometric hint can encode information from areas of the scene not covered by the keyframes and it is more regularized when compared to individual predicted depth maps for previous frames. We introduce a Hint MLP which combines cost volume features with a hint of the prior geometry, rendered as a depth map from the current camera location, together with a measure of the confidence in the prior geometry. We demonstrate that our method, which can run at interactive speeds, achieves state-of-the-art estimates of depth and 3D scene reconstruction in both offline and incremental evaluation scenarios.
Authors: Kemiao Huang, Meiying Zhang, Qi Hao
Abstract: Compared with real-time multi-object tracking (MOT), offline multi-object tracking (OMOT) has the advantages to perform 2D-3D detection fusion, erroneous link correction, and full track optimization but has to deal with the challenges from bounding box misalignment and track evaluation, editing, and refinement. This paper proposes "BiTrack", a 3D OMOT framework that includes modules of 2D-3D detection fusion, initial trajectory generation, and bidirectional trajectory re-optimization to achieve optimal tracking results from camera-LiDAR data. The novelty of this paper includes threefold: (1) development of a point-level object registration technique that employs a density-based similarity metric to achieve accurate fusion of 2D-3D detection results; (2) development of a set of data association and track management skills that utilizes a vertex-based similarity metric as well as false alarm rejection and track recovery mechanisms to generate reliable bidirectional object trajectories; (3) development of a trajectory re-optimization scheme that re-organizes track fragments of different fidelities in a greedy fashion, as well as refines each trajectory with completion and smoothing techniques. The experiment results on the KITTI dataset demonstrate that BiTrack achieves the state-of-the-art performance for 3D OMOT tasks in terms of accuracy and efficiency.
Authors: Abril Corona-Figueroa, Hubert P. H. Shum, Chris G. Willcocks
Abstract: This paper investigates a 2D to 3D image translation method with a straightforward technique, enabling correlated 2D X-ray to 3D CT-like reconstruction. We observe that existing approaches, which integrate information across multiple 2D views in the latent space, lose valuable signal information during latent encoding. Instead, we simply repeat and concatenate the 2D views into higher-channel 3D volumes and approach the 3D reconstruction challenge as a straightforward 3D to 3D generative modeling problem, sidestepping several complex modeling issues. This method enables the reconstructed 3D volume to retain valuable information from the 2D inputs, which are passed between channel states in a Swin UNETR backbone. Our approach applies neural optimal transport, which is fast and stable to train, effectively integrating signal information across multiple views without the requirement for precise alignment; it produces non-collapsed reconstructions that are highly faithful to the 2D views, even after limited training. We demonstrate correlated results, both qualitatively and quantitatively, having trained our model on a single dataset and evaluated its generalization ability across six datasets, including out-of-distribution samples.
Authors: Doruk Cetin, Benedikt Schesch, Petar Stamenkovic, Niko Benjamin Huber, Fabio Z\"und, Majed El Helou
Abstract: Assessing distances between images and image datasets is a fundamental task in vision-based research. It is a challenging open problem in the literature and despite the criticism it receives, the most ubiquitous method remains the Fr\'echet Inception Distance. The Inception network is trained on a specific labeled dataset, ImageNet, which has caused the core of its criticism in the most recent research. Improvements were shown by moving to self-supervision learning over ImageNet, leaving the training data domain as an open question. We make that last leap and provide the first analysis on domain-specific feature training and its effects on feature distance, on the widely-researched facial image domain. We provide our findings and insights on this domain specialization for Fr\'echet distance and image neighborhoods, supported by extensive experiments and in-depth user studies.
Authors: Zhaowei Wu, Binyi Su, Hua Zhang, Zhong Zhou
Abstract: In this paper, we focus on training an open-set object detector under the condition of scarce training samples, which should distinguish the known and unknown categories. Under this challenging scenario, the decision boundaries of unknowns are difficult to learn and often ambiguous. To mitigate this issue, we develop a novel open-set object detection framework, which delves into conditional evidence decoupling for the unknown rejection. Specifically, we select pseudo-unknown samples by leveraging the discrepancy in attribution gradients between known and unknown classes, alleviating the inadequate unknown distribution coverage of training data. Subsequently, we propose a Conditional Evidence Decoupling Loss (CEDL) based on Evidential Deep Learning (EDL) theory, which decouples known and unknown properties in pseudo-unknown samples to learn distinct knowledge, enhancing separability between knowns and unknowns. Additionally, we propose an Abnormality Calibration Loss (ACL), which serves as a regularization term to adjust the output probability distribution, establishing robust decision boundaries for the unknown rejection. Our method has achieved the superiority performance over previous state-of-the-art approaches, improving the mean recall of unknown class by 7.24% across all shots in VOC10-5-5 dataset settings and 1.38% in VOC-COCO dataset settings. The code is available via https://github.com/zjzwzw/CED-FOOD.
Authors: Yuan Gao, Yajing Luo, Junhong Wang, Kui Jia, Gui-Song Xia
Abstract: Humans can easily deduce the relative pose of an unseen object, without label/training, given only a single query-reference image pair. This is arguably achieved by incorporating (i) 3D/2.5D shape perception from a single image, (ii) render-and-compare simulation, and (iii) rich semantic cue awareness to furnish (coarse) reference-query correspondence. Existing methods implement (i) by a 3D CAD model or well-calibrated multiple images and (ii) by training a network on specific objects, which necessitate laborious ground-truth labeling and tedious training, potentially leading to challenges in generalization. Moreover, (iii) was less exploited in the paradigm of (ii), despite that the coarse correspondence from (iii) enhances the compare process by filtering out non-overlapped parts under substantial pose differences/occlusions. Motivated by this, we propose a novel 3D generalizable relative pose estimation method by elaborating (i) with a 2.5D shape from an RGB-D reference, (ii) with an off-the-shelf differentiable renderer, and (iii) with semantic cues from a pretrained model like DINOv2. Specifically, our differentiable renderer takes the 2.5D rotatable mesh textured by the RGB and the semantic maps (obtained by DINOv2 from the RGB input), then renders new RGB and semantic maps (with back-surface culling) under a novel rotated view. The refinement loss comes from comparing the rendered RGB and semantic maps with the query ones, back-propagating the gradients through the differentiable renderer to refine the 3D relative pose. As a result, our method can be readily applied to unseen objects, given only a single RGB-D reference, without label/training. Extensive experiments on LineMOD, LM-O, and YCB-V show that our training-free method significantly outperforms the SOTA supervised methods, especially under the rigorous Acc@5/10/15{\deg} metrics and the challenging cross-dataset settings.
Authors: Younghyun Kim, Geunmin Hwang, Eunbyung Park
Abstract: Recent surge in large-scale generative models has spurred the development of vast fields in computer vision. In particular, text-to-image diffusion models have garnered widespread adoption across diverse domain due to their potential for high-fidelity image generation. Nonetheless, existing large-scale diffusion models are confined to generate images of up to 1K resolution, which is far from meeting the demands of contemporary commercial applications. Directly sampling higher-resolution images often yields results marred by artifacts such as object repetition and distorted shapes. Addressing the aforementioned issues typically necessitates training or fine-tuning models on higher resolution datasets. However, this undertaking poses a formidable challenge due to the difficulty in collecting large-scale high-resolution contents and substantial computational resources. While several preceding works have proposed alternatives, they often fail to produce convincing results. In this work, we probe the generative ability of diffusion models at higher resolution beyond its original capability and propose a novel progressive approach that fully utilizes generated low-resolution image to guide the generation of higher resolution image. Our method obviates the need for additional training or fine-tuning which significantly lowers the burden of computational costs. Extensive experiments and results validate the efficiency and efficacy of our method.
Authors: Taoran Yi, Jiemin Fang, Zanwei Zhou, Junjie Wang, Guanjun Wu, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Xinggang Wang, Qi Tian
Abstract: Recently, 3D Gaussian splatting (3D-GS) has achieved great success in reconstructing and rendering real-world scenes. To transfer the high rendering quality to generation tasks, a series of research works attempt to generate 3D-Gaussian assets from text. However, the generated assets have not achieved the same quality as those in reconstruction tasks. We observe that Gaussians tend to grow without control as the generation process may cause indeterminacy. Aiming at highly enhancing the generation quality, we propose a novel framework named GaussianDreamerPro. The main idea is to bind Gaussians to reasonable geometry, which evolves over the whole generation process. Along different stages of our framework, both the geometry and appearance can be enriched progressively. The final output asset is constructed with 3D Gaussians bound to mesh, which shows significantly enhanced details and quality compared with previous methods. Notably, the generated asset can also be seamlessly integrated into downstream manipulation pipelines, e.g. animation, composition, and simulation etc., greatly promoting its potential in wide applications. Demos are available at https://taoranyi.com/gaussiandreamerpro/.
Authors: Or Rubin, Shlomi Laufer
Abstract: Surgical phase recognition is a key task in computer-assisted surgery, aiming to automatically identify and categorize the different phases within a surgical procedure. Despite substantial advancements, most current approaches rely on fully supervised training, requiring expensive and time-consuming frame-level annotations. Timestamp supervision has recently emerged as a promising alternative, significantly reducing annotation costs while maintaining competitive performance. However, models trained on timestamp annotations can be negatively impacted by missing phase annotations, leading to a potential drawback in real-world scenarios. In this work, we address this issue by proposing a robust method for surgical phase recognition that can handle missing phase annotations effectively. Furthermore, we introduce the SkipTag@K annotation approach to the surgical domain, enabling a flexible balance between annotation effort and model performance. Our method achieves competitive results on two challenging datasets, demonstrating its efficacy in handling missing phase annotations and its potential for reducing annotation costs. Specifically, we achieve an accuracy of 85.1\% on the MultiBypass140 dataset using only 3 annotated frames per video, showcasing the effectiveness of our method and the potential of the SkipTag@K setup. We perform extensive experiments to validate the robustness of our method and provide valuable insights to guide future research in surgical phase recognition. Our work contributes to the advancement of surgical workflow recognition and paves the way for more efficient and reliable surgical phase recognition systems.
Authors: Kang Liao, Zongsheng Yue, Zhouxia Wang, Chen Change Loy
Abstract: Although deep learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing methods address this issue by improving data synthesis pipelines, estimating degradation kernels, employing deep internal learning, and performing domain adaptation and regularization. Previous domain adaptation methods have sought to bridge the domain gap by learning domain-invariant knowledge in either feature or pixel space. However, these techniques often struggle to extend to low-level vision tasks within a stable and compact framework. In this paper, we show that it is possible to perform domain adaptation via the noise-space using diffusion models. In particular, by leveraging the unique property of how the multi-step denoising process is influenced by auxiliary conditional inputs, we obtain meaningful gradients from noise prediction to gradually align the restored results of both synthetic and real-world data to a common clean distribution. We refer to this method as denoising as adaptation. To prevent shortcuts during training, we present useful techniques such as channel shuffling and residual-swapping contrastive learning. Experimental results on three classical image restoration tasks, namely denoising, deblurring, and deraining, demonstrate the effectiveness of the proposed method. Code will be released at: https://github.com/KangLiao929/Noise-DA/.
Authors: Shenghai Yuan, Jinfa Huang, Yongqi Xu, Yaoyang Liu, Shaofeng Zhang, Yujun Shi, Ruijie Zhu, Xinhua Cheng, Jiebo Luo, Li Yuan
Abstract: We propose a novel text-to-video (T2V) generation benchmark, ChronoMagic-Bench, to evaluate the temporal and metamorphic capabilities of the T2V models (e.g. Sora and Lumiere) in time-lapse video generation. In contrast to existing benchmarks that focus on the visual quality and textual relevance of generated videos, ChronoMagic-Bench focuses on the model's ability to generate time-lapse videos with significant metamorphic amplitude and temporal coherence. The benchmark probes T2V models for their physics, biology, and chemistry capabilities, in a free-form text query. For these purposes, ChronoMagic-Bench introduces 1,649 prompts and real-world videos as references, categorized into four major types of time-lapse videos: biological, human-created, meteorological, and physical phenomena, which are further divided into 75 subcategories. This categorization comprehensively evaluates the model's capacity to handle diverse and complex transformations. To accurately align human preference with the benchmark, we introduce two new automatic metrics, MTScore and CHScore, to evaluate the videos' metamorphic attributes and temporal coherence. MTScore measures the metamorphic amplitude, reflecting the degree of change over time, while CHScore assesses the temporal coherence, ensuring the generated videos maintain logical progression and continuity. Based on the ChronoMagic-Bench, we conduct comprehensive manual evaluations of ten representative T2V models, revealing their strengths and weaknesses across different categories of prompts, and providing a thorough evaluation framework that addresses current gaps in video generation research. Moreover, we create a large-scale ChronoMagic-Pro dataset, containing 460k high-quality pairs of 720p time-lapse videos and detailed captions ensuring high physical pertinence and large metamorphic amplitude.
Authors: Norman M\"uller, Katja Schwarz, Barbara Roessle, Lorenzo Porzi, Samuel Rota Bul\`o, Matthias Nie{\ss}ner, Peter Kontschieder
Abstract: We introduce MultiDiff, a novel approach for consistent novel view synthesis of scenes from a single RGB image. The task of synthesizing novel views from a single reference image is highly ill-posed by nature, as there exist multiple, plausible explanations for unobserved areas. To address this issue, we incorporate strong priors in form of monocular depth predictors and video-diffusion models. Monocular depth enables us to condition our model on warped reference images for the target views, increasing geometric stability. The video-diffusion prior provides a strong proxy for 3D scenes, allowing the model to learn continuous and pixel-accurate correspondences across generated images. In contrast to approaches relying on autoregressive image generation that are prone to drifts and error accumulation, MultiDiff jointly synthesizes a sequence of frames yielding high-quality and multi-view consistent results -- even for long-term scene generation with large camera movements, while reducing inference time by an order of magnitude. For additional consistency and image quality improvements, we introduce a novel, structured noise distribution. Our experimental results demonstrate that MultiDiff outperforms state-of-the-art methods on the challenging, real-world datasets RealEstate10K and ScanNet. Finally, our model naturally supports multi-view consistent editing without the need for further tuning.
Authors: Jiayuan Rao, Haoning Wu, Chang Liu, Yanfeng Wang, Weidi Xie
Abstract: Soccer is a globally popular sport with a vast audience, in this paper, we consider constructing an automatic soccer game commentary model to improve the audiences' viewing experience. In general, we make the following contributions: First, observing the prevalent video-text misalignment in existing datasets, we manually annotate timestamps for 49 matches, establishing a more robust benchmark for soccer game commentary generation, termed as SN-Caption-test-align; Second, we propose a multi-modal temporal alignment pipeline to automatically correct and filter the existing dataset at scale, creating a higher-quality soccer game commentary dataset for training, denoted as MatchTime; Third, based on our curated dataset, we train an automatic commentary generation model, named MatchVoice. Extensive experiments and ablation studies have demonstrated the effectiveness of our alignment pipeline, and training model on the curated datasets achieves state-of-the-art performance for commentary generation, showcasing that better alignment can lead to significant performance improvements in downstream tasks.
Authors: Hexu Zhao, Haoyang Weng, Daohan Lu, Ang Li, Jinyang Li, Aurojit Panda, Saining Xie
Abstract: 3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a single GPU, limiting its ability to handle high-resolution and large-scale 3D reconstruction tasks due to memory constraints. We introduce Grendel, a distributed system designed to partition 3DGS parameters and parallelize computation across multiple GPUs. As each Gaussian affects a small, dynamic subset of rendered pixels, Grendel employs sparse all-to-all communication to transfer the necessary Gaussians to pixel partitions and performs dynamic load balancing. Unlike existing 3DGS systems that train using one camera view image at a time, Grendel supports batched training with multiple views. We explore various optimization hyperparameter scaling strategies and find that a simple sqrt(batch size) scaling rule is highly effective. Evaluations using large-scale, high-resolution scenes show that Grendel enhances rendering quality by scaling up 3DGS parameters across multiple GPUs. On the Rubble dataset, we achieve a test PSNR of 27.28 by distributing 40.4 million Gaussians across 16 GPUs, compared to a PSNR of 26.28 using 11.2 million Gaussians on a single GPU. Grendel is an open-source project available at: https://github.com/nyu-systems/Grendel-GS
Authors: Lindsay Munroe, Mariana da Silva, Faezeh Heidari, Irina Grigorescu, Simon Dahan, Emma C. Robinson, Maria Deprez, Po-Wah So
Abstract: Clinical adoption of deep learning models has been hindered, in part, because the black-box nature of neural networks leads to concerns regarding their trustworthiness and reliability. These concerns are particularly relevant in the field of neuroimaging due to the complex brain phenotypes and inter-subject heterogeneity often encountered. The challenge can be addressed by interpretable deep learning (iDL) methods that enable the visualisation and interpretation of the inner workings of deep learning models. This study systematically reviewed the literature on neuroimaging applications of iDL methods and critically analysed how iDL explanation properties were evaluated. Seventy-five studies were included, and ten categories of iDL methods were identified. We also reviewed five properties of iDL explanations that were analysed in the included studies: biological validity, robustness, continuity, selectivity, and downstream task performance. We found that the most popular iDL approaches used in the literature may be sub-optimal for neuroimaging data, and we discussed possible future directions for the field.
Authors: Wanyu Bian
Abstract: This paper presents a comprehensive analysis of both conventional and deep learning methods for eliminating electromagnetic interference (EMI) in MRI systems. We explore the underlying principles and implementation of traditional analytical and adaptive EMI elimination techniques, as well as cutting-edge deep learning approaches. Through a detailed comparison, the strengths and limitations of each method are highlighted. Recent advancements in active EMI elimination utilizing multiple external EMI receiver coils and analytical techniques are discussed alongside the superior performance of deep learning methods, which leverage neural networks trained on extensive MRI data. While deep learning methods demonstrate significant improvements in EMI suppression, enhancing diagnostic capabilities and accessibility of MRI technology, they also introduce potential security and safety concerns, especially in production and commercial applications. This study underscores the need to address these challenges to fully realize the benefits of deep learning in EMI elimination. The findings suggest a balanced approach, combining the reliability of conventional methods with the advanced capabilities of deep learning, to develop more robust and effective EMI suppression strategies in MRI systems.
Authors: Xirui Li, Hengguang Zhou, Ruochen Wang, Tianyi Zhou, Minhao Cheng, Cho-Jui Hsieh
Abstract: Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstrates that advanced Multimodal Large Language Models (MLLMs) exhibit similar tendencies. While these models are designed to respond queries under safety mechanism, they sometimes reject harmless queries in the presence of certain visual stimuli, disregarding the benign nature of their contexts. As the initial step in investigating this behavior, we identify three types of stimuli that trigger the oversensitivity of existing MLLMs: Exaggerated Risk, Negated Harm, and Counterintuitive Interpretation. To systematically evaluate MLLMs' oversensitivity to these stimuli, we propose the Multimodal OverSenSitivity Benchmark (MOSSBench). This toolkit consists of 300 manually collected benign multimodal queries, cross-verified by third-party reviewers (AMT). Empirical studies using MOSSBench on 20 MLLMs reveal several insights: (1). Oversensitivity is prevalent among SOTA MLLMs, with refusal rates reaching up to 76% for harmless queries. (2). Safer models are more oversensitive: increasing safety may inadvertently raise caution and conservatism in the model's responses. (3). Different types of stimuli tend to cause errors at specific stages -- perception, intent reasoning, and safety judgement -- in the response process of MLLMs. These findings highlight the need for refined safety mechanisms that balance caution with contextually appropriate responses, improving the reliability of MLLMs in real-world applications. We make our project available at https://turningpoint-ai.github.io/MOSSBench/.
Authors: Zhen Wu, Jiaman Li, C. Karen Liu
Abstract: Intelligent agents need to autonomously navigate and interact within contextual environments to perform a wide range of daily tasks based on human-level instructions. These agents require a foundational understanding of the world, incorporating common sense and knowledge, to interpret such instructions. Moreover, they must possess precise low-level skills for movement and interaction to execute the detailed task plans derived from these instructions. In this work, we address the task of synthesizing continuous human-object interactions for manipulating large objects within contextual environments, guided by human-level instructions. Our goal is to generate synchronized object motion, full-body human motion, and detailed finger motion, all essential for realistic interactions. Our framework consists of a large language model (LLM) planning module and a low-level motion generator. We use LLMs to deduce spatial object relationships and devise a method for accurately determining their positions and orientations in target scene layouts. Additionally, the LLM planner outlines a detailed task plan specifying a sequence of sub-tasks. This task plan, along with the target object poses, serves as input for our low-level motion generator, which seamlessly alternates between navigation and interaction modules. We present the first complete system that can synthesize object motion, full-body motion, and finger motion simultaneously from human-level instructions. Our experiments demonstrate the effectiveness of our high-level planner in generating plausible target layouts and our low-level motion generator in synthesizing realistic interactions for diverse objects. Please refer to our project page for more results: https://hoifhli.github.io/.
Authors: Avi Amalanshu, Viswesh Nagaswamy, G. V. S. S. Prudhvi, Yash Sirvi, Debashish Chakravarty
Abstract: Vertical Federated Learning (VFL) is a machine learning paradigm for learning from vertically partitioned data (i.e. features for each input are distributed across multiple "guest" clients and an aggregating "host" server owns labels) without communicating raw data. Traditionally, VFL involves an "entity resolution" phase where the host identifies and serializes the unique entities known to all guests. This is followed by private set intersection to find common entities, and an "entity alignment" step to ensure all guests are always processing the same entity's data. However, using only data of entities from the intersection means guests discard potentially useful data. Besides, the effect on privacy is dubious and these operations are computationally expensive. We propose a novel approach that eliminates the need for set intersection and entity alignment in categorical tasks. Our Entity Augmentation technique generates meaningful labels for activations sent to the host, regardless of their originating entity, enabling efficient VFL without explicit entity alignment. With limited overlap between training data, this approach performs substantially better (e.g. with 5% overlap, 48.1% vs 69.48% test accuracy on CIFAR-10). In fact, thanks to the regularizing effect, our model performs marginally better even with 100% overlap.
Authors: Arnaud Judge, Thierry Judge, Nicolas Duchateau, Roman A. Sandler, Joseph Z. Sokol, Olivier Bernard, Pierre-Marc Jodoin
Abstract: Performance of deep learning segmentation models is significantly challenged in its transferability across different medical imaging domains, particularly when aiming to adapt these models to a target domain with insufficient annotated data for effective fine-tuning. While existing domain adaptation (DA) methods propose strategies to alleviate this problem, these methods do not explicitly incorporate human-verified segmentation priors, compromising the potential of a model to produce anatomically plausible segmentations. We introduce RL4Seg, an innovative reinforcement learning framework that reduces the need to otherwise incorporate large expertly annotated datasets in the target domain, and eliminates the need for lengthy manual human review. Using a target dataset of 10,000 unannotated 2D echocardiographic images, RL4Seg not only outperforms existing state-of-the-art DA methods in accuracy but also achieves 99% anatomical validity on a subset of 220 expert-validated subjects from the target domain. Furthermore, our framework's reward network offers uncertainty estimates comparable with dedicated state-of-the-art uncertainty methods, demonstrating the utility and effectiveness of RL4Seg in overcoming domain adaptation challenges in medical image segmentation.
Authors: Joao Morais, Gouranga Charan, Nikhil Srinivas, Ahmed Alkhateeb
Abstract: High data rate and low-latency vehicle-to-vehicle (V2V) communication are essential for future intelligent transport systems to enable coordination, enhance safety, and support distributed computing and intelligence requirements. Developing effective communication strategies, however, demands realistic test scenarios and datasets. This is important at the high-frequency bands where more spectrum is available, yet harvesting this bandwidth is challenged by the need for direction transmission and the sensitivity of signal propagation to blockages. This work presents the first large-scale multi-modal dataset for studying mmWave vehicle-to-vehicle communications. It presents a two-vehicle testbed that comprises data from a 360-degree camera, four radars, four 60 GHz phased arrays, a 3D lidar, and two precise GPSs. The dataset contains vehicles driving during the day and night for 120 km in intercity and rural settings, with speeds up to 100 km per hour. More than one million objects were detected across all images, from trucks to bicycles. This work further includes detailed dataset statistics that prove the coverage of various situations and highlights how this dataset can enable novel machine-learning applications.
Authors: Xuyang Wu, Yuan Wang, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang
Abstract: Large vision-language models (LVLMs) have recently achieved significant progress, demonstrating strong capabilities in open-world visual understanding. However, it is not yet clear how LVLMs address demographic biases in real life, especially the disparities across attributes such as gender, skin tone, and age. In this paper, we empirically investigate \emph{visual fairness} in several mainstream LVLMs and audit their performance disparities across sensitive demographic attributes, based on public fairness benchmark datasets (e.g., FACET). To disclose the visual bias in LVLMs, we design a fairness evaluation framework with direct questions and single-choice question-instructed prompts on visual question-answering/classification tasks. The zero-shot prompting results indicate that, despite enhancements in visual understanding, both open-source and closed-source LVLMs exhibit prevalent fairness issues across different instruct prompts and demographic attributes.
Authors: Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Aaron Courville, Sai Rajeswar
Abstract: Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning (RL) is hard to scale up as it requires a complex reward design for each task. In contrast, language can specify tasks in a more natural way. Current foundation vision-language models (VLMs) generally require fine-tuning or other adaptations to be functional, due to the significant domain gap. However, the lack of multimodal data in such domains represents an obstacle toward developing foundation models for embodied applications. In this work, we overcome these problems by presenting multimodal foundation world models, able to connect and align the representation of foundation VLMs with the latent space of generative world models for RL, without any language annotations. The resulting agent learning framework, GenRL, allows one to specify tasks through vision and/or language prompts, ground them in the embodied domain's dynamics, and learns the corresponding behaviors in imagination. As assessed through large-scale multi-task benchmarking, GenRL exhibits strong multi-task generalization performance in several locomotion and manipulation domains. Furthermore, by introducing a data-free RL strategy, it lays the groundwork for foundation model-based RL for generalist embodied agents.
Authors: Qilai Zhang, Jiawen Li, Peiran Liao, Jiali Hu, Tian Guan, Anjia Han, Yonghong He
Abstract: The two primary types of Hematoxylin and Eosin (H&E) slides in histopathology are Formalin-Fixed Paraffin-Embedded (FFPE) and Fresh Frozen (FF). FFPE slides offer high quality histopathological images but require a labor-intensive acquisition process. In contrast, FF slides can be prepared quickly, but the image quality is relatively poor. Our task is to translate FF images into FFPE style, thereby improving the image quality for diagnostic purposes. In this paper, we propose Diffusion-FFPE, a method for FF-to-FFPE histopathological image translation using a pre-trained diffusion model. Specifically, we employ a one-step diffusion model as the generator and fine-tune it with LoRA adapters using adversarial learning objectives. To ensure that the model effectively captures both global structural information and local details, we propose a multi-scale feature fusion (MFF) module. This module utilizes two VAE encoders to extract features of varying image sizes and performs feature fusion before feeding them into the UNet. Furthermore, we utilize a pre-trained vision-language model for histopathology as the backbone for the discriminator to further improve performance We conducted FF-to-FFPE translation experiments on the TCGA-NSCLC datasets, and our method achieved better performance compared to other methods. The code and models are released at https://github.com/QilaiZhang/Diffusion-FFPE.
Authors: Muwei Jian, Hongyu Chen, Zaiyong Zhang, Nan Yang, Haorang Zhang, Lifu Ma, Wenjing Xu, Huixiang Zhi
Abstract: Recently, Computer-Aided Diagnosis (CAD) systems have emerged as indispensable tools in clinical diagnostic workflows, significantly alleviating the burden on radiologists. Nevertheless, despite their integration into clinical settings, CAD systems encounter limitations. Specifically, while CAD systems can achieve high performance in the detection of lung nodules, they face challenges in accurately predicting multiple cancer types. This limitation can be attributed to the scarcity of publicly available datasets annotated with expert-level cancer type information. This research aims to bridge this gap by providing publicly accessible datasets and reliable tools for medical diagnosis, facilitating a finer categorization of different types of lung diseases so as to offer precise treatment recommendations. To achieve this objective, we curated a diverse dataset of lung Computed Tomography (CT) images, comprising 330 annotated nodules (nodules are labeled as bounding boxes) from 95 distinct patients. The quality of the dataset was evaluated using a variety of classical classification and detection models, and these promising results demonstrate that the dataset has a feasible application and further facilitate intelligent auxiliary diagnosis.
Authors: Dicong Qiu, Wenzong Ma, Zhenfu Pan, Hui Xiong, Junwei Liang
Abstract: Open-Vocabulary Mobile Manipulation (OVMM) is a crucial capability for autonomous robots, especially when faced with the challenges posed by unknown and dynamic environments. This task requires robots to explore and build a semantic understanding of their surroundings, generate feasible plans to achieve manipulation goals, adapt to environmental changes, and comprehend natural language instructions from humans. To address these challenges, we propose a novel framework that leverages the zero-shot detection and grounded recognition capabilities of pretraining visual-language models (VLMs) combined with dense 3D entity reconstruction to build 3D semantic maps. Additionally, we utilize large language models (LLMs) for spatial region abstraction and online planning, incorporating human instructions and spatial semantic context. We have built a 10-DoF mobile manipulation robotic platform JSR-1 and demonstrated in real-world robot experiments that our proposed framework can effectively capture spatial semantics and process natural language user instructions for zero-shot OVMM tasks under dynamic environment settings, with an overall navigation and task success rate of 80.95% and 73.33% over 105 episodes, and better SFT and SPL by 157.18% and 19.53% respectively compared to the baseline. Furthermore, the framework is capable of replanning towards the next most probable candidate location based on the spatial semantic context derived from the 3D semantic map when initial plans fail, keeping an average success rate of 76.67%.
Authors: Zhongwei Wan, Ziang Wu, Che Liu, Jinfa Huang, Zhihong Zhu, Peng Jin, Longyue Wang, Li Yuan
Abstract: Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time efficiency. Unlike single-modality LLMs that manage only textual contexts, the KV cache of long-context MLLMs includes representations from multiple images with temporal and spatial relationships and related textual contexts. The predominance of image tokens means traditional optimizations for LLMs' KV caches are unsuitable for multimodal long-context settings, and no prior works have addressed this challenge. In this work, we introduce LOOK-M, a pioneering, fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache. We observe that during prompt prefill, the model prioritizes more textual attention over image features, and based on the multimodal interaction observation, a new proposed text-prior method is explored to compress the KV cache. Furthermore, to mitigate the degradation of image contextual information, we propose several compensatory strategies using KV pairs merging. LOOK-M demonstrates that with a significant reduction in KV Cache memory usage, such as reducing it by 80% in some cases, it not only achieves up to 1.5x faster decoding but also maintains or even enhances performance across a variety of long context multimodal tasks.
Authors: Shengyi Qian, Kaichun Mo, Valts Blukis, David F. Fouhey, Dieter Fox, Ankit Goyal
Abstract: Recent works have shown that visual pretraining on egocentric datasets using masked autoencoders (MAE) can improve generalization for downstream robotics tasks. However, these approaches pretrain only on 2D images, while many robotics applications require 3D scene understanding. In this work, we propose 3D-MVP, a novel approach for 3D multi-view pretraining using masked autoencoders. We leverage Robotic View Transformer (RVT), which uses a multi-view transformer to understand the 3D scene and predict gripper pose actions. We split RVT's multi-view transformer into visual encoder and action decoder, and pretrain its visual encoder using masked autoencoding on large-scale 3D datasets such as Objaverse. We evaluate 3D-MVP on a suite of virtual robot manipulation tasks and demonstrate improved performance over baselines. We also show promising results on a real robot platform with minimal finetuning. Our results suggest that 3D-aware pretraining is a promising approach to improve sample efficiency and generalization of vision-based robotic manipulation policies. We will release code and pretrained models for 3D-MVP to facilitate future research. Project site: https://jasonqsy.github.io/3DMVP
Authors: Lingjie Kong, Qiaoling Wei, Chengming Xu, Han Chen, Yanwei Fu
Abstract: This paper explores the segmentation of very small medical objects with significant clinical value. While Convolutional Neural Networks (CNNs), particularly UNet-like models, and recent Transformers have shown substantial progress in image segmentation, our empirical findings reveal their poor performance in segmenting the small medical objects and lesions concerned in this paper. This limitation may be attributed to information loss during their encoding and decoding process. In response to this challenge, we propose a novel model named EFCNet for small object segmentation in medical images. Our model incorporates two modules: the Cross-Stage Axial Attention Module (CSAA) and the Multi-Precision Supervision Module (MPS). These modules address information loss during encoding and decoding procedures, respectively. Specifically, CSAA integrates features from all stages of the encoder to adaptively learn suitable information needed in different decoding stages, thereby reducing information loss in the encoder. On the other hand, MPS introduces a novel multi-precision supervision mechanism to the decoder. This mechanism prioritizes attention to low-resolution features in the initial stages of the decoder, mitigating information loss caused by subsequent convolution and sampling processes and enhancing the model's global perception. We evaluate our model on two benchmark medical image datasets. The results demonstrate that EFCNet significantly outperforms previous segmentation methods designed for both medical and normal images.
Authors: Abdul Rehman, Sarfaraz Hussein, Waqas Sultani
Abstract: Early diagnosis of breast cancer (BC) significantly contributes to reducing the mortality rate worldwide. The detection of different factors and biomarkers such as Estrogen receptor (ER), Progesterone receptor (PR), Human epidermal growth factor receptor 2 (HER2) gene, Histological grade (HG), Auxiliary lymph node (ALN) status, and Molecular subtype (MS) can play a significant role in improved BC diagnosis. However, the existing methods predict only a single factor which makes them less suitable to use in diagnosis and designing a strategy for treatment. In this paper, we propose to classify the six essential indicating factors (ER, PR, HER2, ALN, HG, MS) for early BC diagnosis using H\&E stained WSI's. To precisely capture local neighboring relationships, we use spatial and frequency domain information from the large patch size of WSI's malignant regions. Furthermore, to cater the variable number of regions of interest sizes and give due attention to each region, we propose a malignant region learning attention network. Our experimental results demonstrate that combining spatial and frequency information using the malignant region learning module significantly improves multi-factor and single-factor classification performance on publicly available datasets.
Authors: Francisca Silva-Claver\'ia, Carmen Serrano, Iv\'an Matas, Amalia Serrano, Tom\'as Toledo-Pastrana, David Moreno-Ram\'irez, Bego\~na Acha
Abstract: Background: The existence of different basal cell carcinoma (BCC) clinical criteria cannot be objectively validated. An adequate ground-truth is needed to train an artificial intelligence (AI) tool that explains the BCC diagnosis by providing its dermoscopic features. Objectives: To determine the consensus among dermatologists on dermoscopic criteria of 204 BCC. To analyze the performance of an AI tool when the ground-truth is inferred. Methods: A single center, diagnostic and prospective study was conducted to analyze the agreement in dermoscopic criteria by four dermatologists and then derive a reference standard. 1434 dermoscopic images have been used, that were taken by a primary health physician, sent via teledermatology, and diagnosed by a dermatologist. They were randomly selected from the teledermatology platform (2019-2021). 204 of them were tested with an AI tool; the remainder trained it. The performance of the AI tool trained using the ground-truth of one dermatologist versus the ground-truth statistically inferred from the consensus of four dermatologists was analyzed using McNemar's test and Hamming distance. Results: Dermatologists achieve perfect agreement in the diagnosis of BCC (Fleiss-Kappa=0.9079), and a high correlation with the biopsy (PPV=0.9670). However, there is low agreement in detecting some dermoscopic criteria. Statistical differences were found in the performance of the AI tool trained using the ground-truth of one dermatologist versus the ground-truth statistically inferred from the consensus of four dermatologists. Conclusions: Care should be taken when training an AI tool to determine the BCC patterns present in a lesion. Ground-truth should be established from multiple dermatologists.
Authors: I. R. Slootweg, M. Thach, K. R. Curro-Tafili, F. D. Verbraak, F. H. Bouwman, Y. A. L. Pijnenburg, J. F. Boer, J. H. P. de Kwisthout, L. Bagheriye, P. J. Gonz\'alez
Abstract: Background/Aim. This study aims to predict Amyloid Positron Emission Tomography (AmyloidPET) status with multimodal retinal imaging and convolutional neural networks (CNNs) and to improve the performance through pretraining with synthetic data. Methods. Fundus autofluorescence, optical coherence tomography (OCT), and OCT angiography images from 328 eyes of 59 AmyloidPET positive subjects and 108 AmyloidPET negative subjects were used for classification. Denoising Diffusion Probabilistic Models (DDPMs) were trained to generate synthetic images and unimodal CNNs were pretrained on synthetic data and finetuned on real data or trained solely on real data. Multimodal classifiers were developed to combine predictions of the four unimodal CNNs with patient metadata. Class activation maps of the unimodal classifiers provided insight into the network's attention to inputs. Results. DDPMs generated diverse, realistic images without memorization. Pretraining unimodal CNNs with synthetic data improved AUPR at most from 0.350 to 0.579. Integration of metadata in multimodal CNNs improved AUPR from 0.486 to 0.634, which was the best overall best classifier. Class activation maps highlighted relevant retinal regions which correlated with AD. Conclusion. Our method for generating and leveraging synthetic data has the potential to improve AmyloidPET prediction from multimodal retinal imaging. A DDPM can generate realistic and unique multimodal synthetic retinal images. Our best performing unimodal and multimodal classifiers were not pretrained on synthetic data, however pretraining with synthetic data slightly improved classification performance for two out of the four modalities.
Authors: Hamideh Kerdegari, Kyle Higgins, Dennis Veselkov, Ivan Laponogov, Inese Polaka, Miguel Coimbra, Junior Andrea Pescino, Marcis Leja, Mario Dinis-Ribeiro, Tania Fleitas Kanonnikoff, Kirill Veselkov
Abstract: The integration of artificial intelligence (AI) in medical diagnostics represents a significant advancement in managing upper gastrointestinal (GI) cancer, a major cause of global cancer mortality. Specifically for gastric cancer (GC), chronic inflammation causes changes in the mucosa such as atrophy, intestinal metaplasia (IM), dysplasia and ultimately cancer. Early detection through endoscopic regular surveillance is essential for better outcomes. Foundation models (FM), which are machine or deep learning models trained on diverse data and applicable to broad use cases, offer a promising solution to enhance the accuracy of endoscopy and its subsequent pathology image analysis. This review explores the recent advancements, applications, and challenges associated with FM in endoscopy and pathology imaging. We started by elucidating the core principles and architectures underlying these models, including their training methodologies and the pivotal role of large-scale data in developing their predictive capabilities. Moreover, this work discusses emerging trends and future research directions, emphasizing the integration of multimodal data, the development of more robust and equitable models, and the potential for real-time diagnostic support. This review aims to provide a roadmap for researchers and practitioners in navigating the complexities of incorporating FM into clinical practice for prevention/management of GC cases, thereby improving patient outcomes.
Authors: Yuxuan Qi, Li Lin, Jiajun Wang, Jingya Zhang, Bin Zhang
Abstract: Accurate segmentation of tumors in PET/CT images is important in computer-aided diagnosis and treatment of cancer. The key issue of such a segmentation problem lies in the effective integration of complementary information from PET and CT images. However, the quality of PET and CT images varies widely in clinical settings, which leads to uncertainty in the modality information extracted by networks. To take the uncertainty into account in multi-modal information fusion, this paper proposes a novel Multi-modal Evidential Fusion Network (MEFN) comprising a Cross-Modal Feature Learning (CFL) module and a Multi-modal Trusted Fusion (MTF) module. The CFL module reduces the domain gap upon modality conversion and highlights common tumor features, thereby alleviating the needs of the segmentation module to handle modality specificity. The MTF module utilizes mutual attention mechanisms and an uncertainty calibrator to fuse modality features based on modality uncertainty and then fuse the segmentation results under the guidance of Dempster-Shafer Theory. Besides, a new uncertainty perceptual loss is introduced to force the model focusing on uncertain features and hence improve its ability to extract trusted modality information. Extensive comparative experiments are conducted on two publicly available PET/CT datasets to evaluate the performance of our proposed method whose results demonstrate that our MEFN significantly outperforms state-of-the-art methods with improvements of 2.15% and 3.23% in DSC scores on the AutoPET dataset and the Hecktor dataset, respectively. More importantly, our model can provide radiologists with credible uncertainty of the segmentation results for their decision in accepting or rejecting the automatic segmentation results, which is particularly important for clinical applications. Our code will be available at https://github.com/QPaws/MEFN.
Authors: Jonas Ngnaw\'e, Sabyasachi Sahoo, Yann Pequignot, Fr\'ed\'eric Precioso, Christian Gagn\'e
Abstract: Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to imperceptible perturbations, creating serious risks when deploying them for high-stakes real-world applications. While detecting such cases may be critical, evaluating a model's vulnerability at a per-instance level using adversarial attacks is computationally too intensive and unsuitable for real-time deployment scenarios. The input space margin is the exact score to detect non-robust samples and is intractable for deep neural networks. This paper introduces the concept of margin consistency -- a property that links the input space margins and the logit margins in robust models -- for efficient detection of vulnerable samples. First, we establish that margin consistency is a necessary and sufficient condition to use a model's logit margin as a score for identifying non-robust samples. Next, through comprehensive empirical analysis of various robustly trained models on CIFAR10 and CIFAR100 datasets, we show that they indicate strong margin consistency with a strong correlation between their input space margins and the logit margins. Then, we show that we can effectively use the logit margin to confidently detect brittle decisions with such models and accurately estimate robust accuracy on an arbitrarily large test set by estimating the input margins only on a small subset. Finally, we address cases where the model is not sufficiently margin-consistent by learning a pseudo-margin from the feature representation. Our findings highlight the potential of leveraging deep representations to efficiently assess adversarial vulnerability in deployment scenarios.
Authors: Zirui Wang, Mengzhou Xia, Luxi He, Howard Chen, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi, Alexis Chevalier, Sanjeev Arora, Danqi Chen
Abstract: Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and homogeneous charts with template-based questions, leading to an over-optimistic measure of progress. We demonstrate that although open-source models can appear to outperform strong proprietary models on these benchmarks, a simple stress test with slightly different charts or questions can deteriorate performance by up to 34.5%. In this work, we propose CharXiv, a comprehensive evaluation suite involving 2,323 natural, challenging, and diverse charts from arXiv papers. CharXiv includes two types of questions: 1) descriptive questions about examining basic chart elements and 2) reasoning questions that require synthesizing information across complex visual elements in the chart. To ensure quality, all charts and questions are handpicked, curated, and verified by human experts. Our results reveal a substantial, previously underestimated gap between the reasoning skills of the strongest proprietary model (i.e., GPT-4o), which achieves 47.1% accuracy, and the strongest open-source model (i.e., InternVL Chat V1.5), which achieves 29.2%. All models lag far behind human performance of 80.5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs. We hope CharXiv facilitates future research on MLLM chart understanding by providing a more realistic and faithful measure of progress. Project page and leaderboard: https://charxiv.github.io/
Authors: Alpha Renner, Lazar Supic, Andreea Danielescu, Giacomo Indiveri, Bruno A. Olshausen, Yulia Sandamirskaya, Friedrich T. Sommer, E. Paxon Frady
Abstract: Analyzing a visual scene by inferring the configuration of a generative model is widely considered the most flexible and generalizable approach to scene understanding. Yet, one major problem is the computational challenge of the inference procedure, involving a combinatorial search across object identities and poses. Here we propose a neuromorphic solution exploiting three key concepts: (1) a computational framework based on Vector Symbolic Architectures (VSA) with complex-valued vectors; (2) the design of Hierarchical Resonator Networks (HRN) to factorize the non-commutative transforms translation and rotation in visual scenes; (3) the design of a multi-compartment spiking phasor neuron model for implementing complex-valued resonator networks on neuromorphic hardware. The VSA framework uses vector binding operations to form a generative image model in which binding acts as the equivariant operation for geometric transformations. A scene can, therefore, be described as a sum of vector products, which can then be efficiently factorized by a resonator network to infer objects and their poses. The HRN features a partitioned architecture in which vector binding is equivariant for horizontal and vertical translation within one partition and for rotation and scaling within the other partition. The spiking neuron model allows mapping the resonator network onto efficient and low-power neuromorphic hardware. Our approach is demonstrated on synthetic scenes composed of simple 2D shapes undergoing rigid geometric transformations and color changes. A companion paper demonstrates the same approach in real-world application scenarios for machine vision and robotics.
Authors: Bruno Galerne, Lara Raad, Jos\'e Lezama, Jean-Michel Morel
Abstract: Neural style transfer (NST) is a deep learning technique that produces an unprecedentedly rich style transfer from a style image to a content image. It is particularly impressive when it comes to transferring style from a painting to an image. NST was originally achieved by solving an optimization problem to match the global statistics of the style image while preserving the local geometric features of the content image. The two main drawbacks of this original approach is that it is computationally expensive and that the resolution of the output images is limited by high GPU memory requirements. Many solutions have been proposed to both accelerate NST and produce images with larger size. However, our investigation shows that these accelerated methods all compromise the quality of the produced images in the context of painting style transfer. Indeed, transferring the style of a painting is a complex task involving features at different scales, from the color palette and compositional style to the fine brushstrokes and texture of the canvas. This paper provides a solution to solve the original global optimization for ultra-high resolution (UHR) images, enabling multiscale NST at unprecedented image sizes. This is achieved by spatially localizing the computation of each forward and backward passes through the VGG network. Extensive qualitative and quantitative comparisons, as well as a \textcolor{coverletter}{perceptual study}, show that our method produces style transfer of unmatched quality for such high-resolution painting styles. By a careful comparison, we show that state-of-the-art fast methods are still prone to artifacts, thus suggesting that fast painting style transfer remains an open problem. Source code is available at https://github.com/bgalerne/scaling_painting_style_transfer.
URLs: https://github.com/bgalerne/scaling_painting_style_transfer.
Authors: Masoud Dayani Najafabadi, Mohammad Reza Ahmadzadeh
Abstract: Compared to regular cameras, Dynamic Vision Sensors or Event Cameras can output compact visual data based on a change in the intensity in each pixel location asynchronously. In this paper, we study the application of current image-based SLAM techniques to these novel sensors. To this end, the information in adaptively selected event windows is processed to form motion-compensated images. These images are then used to reconstruct the scene and estimate the 6-DOF pose of the camera. We also propose an inertial version of the event-only pipeline to assess its capabilities. We compare the results of different configurations of the proposed algorithm against the ground truth for sequences of two publicly available event datasets. We also compare the results of the proposed event-inertial pipeline with the state-of-the-art and show it can produce comparable or more accurate results provided the map estimate is reliable.
Authors: Bj\"orn Michele, Alexandre Boulch, Gilles Puy, Tuan-Hung Vu, Renaud Marlet, Nicolas Courty
Abstract: Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can exhibit large performance discrepancies due for instance to different lidar patterns or changes in acquisition conditions. This paper addresses the corresponding Unsupervised Domain Adaptation (UDA) task for semantic segmentation. To mitigate this problem, we introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data. As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data. This novel strategy differs from classical minimization of statistical divergences or lidar-specific domain adaptation techniques. Our experiments demonstrate that our method achieves a better performance than the current state of the art, both in real-to-real and synthetic-to-real scenarios.
Authors: Mike Laszkiewicz, Jonas Ricker, Johannes Lederer, Asja Fischer
Abstract: Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes to the generative model. We address these shortcomings by, first, viewing single-model attribution through the lens of anomaly detection. Arising from this change of perspective, we propose FLIPAD, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach and its flexibility to various domains.
Authors: Xianqiang Lyu, Junhui Hou
Abstract: This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a multi-stage architecture that mimics the optimization process of solving an inverse imaging problem in a data-driven fashion. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. Additionally, DCUNet includes a content-associated deep compensation module at each optimization stage to suppress noise and illumination map estimation errors. To properly mine and leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module that comprehensively exploits redundant information in LF images. The experimental results on both simulated and real datasets demonstrate the superiority of our DCUNet over state-of-the-art methods, both qualitatively and quantitatively. Moreover, DCUNet preserves the essential geometric structure of enhanced LF images much better. The code will be publicly available at https://github.com/lyuxianqiang/LFLL-DCU.
Authors: Ke Fan, Zechen Bai, Tianjun Xiao, Dominik Zietlow, Max Horn, Zixu Zhao, Carl-Johann Simon-Gabriel, Mike Zheng Shou, Francesco Locatello, Bernt Schiele, Thomas Brox, Zheng Zhang, Yanwei Fu, Tong He
Abstract: In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes objects in videos via an object-centric approach with slot attention and then assigns text to the obtained slots. The latter is achieved by an unsupervised way to read localized semantic information from the pre-trained CLIP model. The resulting video object localization is entirely unsupervised apart from the implicit annotation contained in CLIP, and it is effectively the first unsupervised approach that yields good results on regular video benchmarks.
Authors: Hongruixuan Chen, Cuiling Lan, Jian Song, Clifford Broni-Bediako, Junshi Xia, Naoto Yokoya
Abstract: Optical high-resolution imagery and OSM data are two important data sources of change detection (CD). Previous related studies focus on utilizing the information in OSM data to aid the CD on optical high-resolution images. This paper pioneers the direct detection of land-cover changes utilizing paired OSM data and optical imagery, thereby expanding the scope of CD tasks. To this end, we propose an object-guided Transformer (ObjFormer) by naturally combining the object-based image analysis (OBIA) technique with the advanced vision Transformer architecture. This combination can significantly reduce the computational overhead in the self-attention module without adding extra parameters or layers. ObjFormer has a hierarchical pseudo-siamese encoder consisting of object-guided self-attention modules that extracts multi-level heterogeneous features from OSM data and optical images; a decoder consisting of object-guided cross-attention modules can recover land-cover changes from the extracted heterogeneous features. Beyond basic binary change detection, this paper raises a new semi-supervised semantic change detection task that does not require any manually annotated land-cover labels to train semantic change detectors. Two lightweight semantic decoders are added to ObjFormer to accomplish this task efficiently. A converse cross-entropy loss is designed to fully utilize negative samples, contributing to the great performance improvement in this task. A large-scale benchmark dataset called OpenMapCD containing 1,287 samples covering 40 regions on six continents is constructed to conduct detailed experiments. The results show the effectiveness of our methods in this new kind of CD task. Additionally, case studies in Japanese cities demonstrate the framework's generalizability and practical potential. The OpenMapCD and source code are available in https://github.com/ChenHongruixuan/ObjFormer
Authors: Fanghui Song, Jiebao Sun, Shengzhu Shi, Zhichang Guo, Dazhi Zhang
Abstract: Variational level set method has become a powerful tool in image segmentation due to its ability to handle complex topological changes and maintain continuity and smoothness in the process of evolution. However its evolution process can be unstable, which results in over flatted or over sharpened contours and segmentation failure. To improve the accuracy and stability of evolution, we propose a high-order level set variational segmentation method integrated with molecular beam epitaxy (MBE) equation regularization. This method uses the crystal growth in the MBE process to limit the evolution of the level set function, and thus can avoid the re-initialization in the evolution process and regulate the smoothness of the segmented curve. It also works for noisy images with intensity inhomogeneity, which is a challenge in image segmentation. To solve the variational model, we derive the gradient flow and design scalar auxiliary variable (SAV) scheme coupled with fast Fourier transform (FFT), which can significantly improve the computational efficiency compared with the traditional semi-implicit and semi-explicit scheme. Numerical experiments show that the proposed method can generate smooth segmentation curves, retain fine segmentation targets and obtain robust segmentation results of small objects. Compared to existing level set methods, this model is state-of-the-art in both accuracy and efficiency.
Authors: Lv Tang, Peng-Tao Jiang, Hao-Ke Xiao, Bo Li
Abstract: The realm of computer vision has witnessed a paradigm shift with the advent of foundational models, mirroring the transformative influence of large language models in the domain of natural language processing. This paper delves into the exploration of open-world segmentation, presenting a novel approach called Image Prompt Segmentation (IPSeg) that harnesses the power of vision foundational models. IPSeg lies the principle of a training-free paradigm, which capitalizes on image prompt techniques. Specifically, IPSeg utilizes a single image containing a subjective visual concept as a flexible prompt to query vision foundation models like DINOv2 and Stable Diffusion. Our approach extracts robust features for the prompt image and input image, then matches the input representations to the prompt representations via a novel feature interaction module to generate point prompts highlighting target objects in the input image. The generated point prompts are further utilized to guide the Segment Anything Model to segment the target object in the input image. The proposed method stands out by eliminating the need for exhaustive training sessions, thereby offering a more efficient and scalable solution. Experiments on COCO, PASCAL VOC, and other datasets demonstrate IPSeg's efficacy for flexible open-world segmentation using intuitive image prompts. This work pioneers tapping foundation models for open-world understanding through visual concepts conveyed in images.
Authors: Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolin\'ario Passos
Abstract: Text-to-image diffusion models have recently received increasing interest for their astonishing ability to produce high-fidelity images from solely text inputs. Subsequent research efforts aim to exploit and apply their capabilities to real image editing. However, existing image-to-image methods are often inefficient, imprecise, and of limited versatility. They either require time-consuming finetuning, deviate unnecessarily strongly from the input image, and/or lack support for multiple, simultaneous edits. To address these issues, we introduce LEDITS++, an efficient yet versatile and precise textual image manipulation technique. LEDITS++'s novel inversion approach requires no tuning nor optimization and produces high-fidelity results with a few diffusion steps. Second, our methodology supports multiple simultaneous edits and is architecture-agnostic. Third, we use a novel implicit masking technique that limits changes to relevant image regions. We propose the novel TEdBench++ benchmark as part of our exhaustive evaluation. Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods.
Authors: Xunguang Wang, Zhenlan Ji, Pingchuan Ma, Zongjie Li, Shuai Wang
Abstract: Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we formulate a novel and practical targeted attack scenario that the adversary can only know the vision encoder of the victim LVLM, without the knowledge of its prompts (which are often proprietary for service providers and not publicly available) and its underlying large language model (LLM). This practical setting poses challenges to the cross-prompt and cross-model transferability of targeted adversarial attack, which aims to confuse the LVLM to output a response that is semantically similar to the attacker's chosen target text. To this end, we propose an instruction-tuned targeted attack (dubbed \textsc{InstructTA}) to deliver the targeted adversarial attack on LVLMs with high transferability. Initially, we utilize a public text-to-image generative model to "reverse" the target response into a target image, and employ GPT-4 to infer a reasonable instruction $\boldsymbol{p}^\prime$ from the target response. We then form a local surrogate model (sharing the same vision encoder with the victim LVLM) to extract instruction-aware features of an adversarial image example and the target image, and minimize the distance between these two features to optimize the adversarial example. To further improve the transferability with instruction tuning, we augment the instruction $\boldsymbol{p}^\prime$ with instructions paraphrased from GPT-4. Extensive experiments demonstrate the superiority of our proposed method in targeted attack performance and transferability. The code is available at https://github.com/xunguangwang/InstructTA.
Authors: Israt Zarin Era, Imtiaz Ahmed, Zhichao Liu, Srinjoy Das
Abstract: Foundation models are currently driving a paradigm shift in computer vision tasks for various fields including biology, astronomy, and robotics among others, leveraging user-generated prompts to enhance their performance. In the Laser Additive Manufacturing (LAM) domain, accurate image-based defect segmentation is imperative to ensure product quality and facilitate real-time process control. However, such tasks are often characterized by multiple challenges including the absence of labels and the requirement for low latency inference among others. Porosity is a very common defect in LAM due to lack of fusion, entrapped gas, and keyholes, directly affecting mechanical properties like tensile strength, stiffness, and hardness, thereby compromising the quality of the final product. To address these issues, we construct a framework for image segmentation using a state-of-the-art Vision Transformer (ViT) based Foundation model (Segment Anything Model) with a novel multi-point prompt generation scheme using unsupervised clustering. Utilizing our framework we perform porosity segmentation in a case study of laser-based powder bed fusion (L-PBF) and obtain high accuracy without using any labeled data to guide the prompt tuning process. By capitalizing on lightweight foundation model inference combined with unsupervised prompt generation, we envision constructing a real-time anomaly detection pipeline that could revolutionize current laser additive manufacturing processes, thereby facilitating the shift towards Industry 4.0 and promoting defect-free production along with operational efficiency.
Authors: Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki
Abstract: State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website (https://odin-seg.github.io).
Authors: Xingyu Miao, Yang Bai, Haoran Duan, Yawen Huang, Fan Wan, Yang Long, Yefeng Zheng
Abstract: The goal of our work is to generate high-quality novel views from monocular videos of complex and dynamic scenes. Prior methods, such as DynamicNeRF, have shown impressive performance by leveraging time-varying dynamic radiation fields. However, these methods have limitations when it comes to accurately modeling the motion of complex objects, which can lead to inaccurate and blurry renderings of details. To address this limitation, we propose a novel approach that builds upon a recent generalization NeRF, which aggregates nearby views onto new viewpoints. However, such methods are typically only effective for static scenes. To overcome this challenge, we introduce a module that operates in both the time and frequency domains to aggregate the features of object motion. This allows us to learn the relationship between frames and generate higher-quality images. Our experiments demonstrate significant improvements over state-of-the-art methods on dynamic scene datasets. Specifically, our approach outperforms existing methods in terms of both the accuracy and visual quality of the synthesized views. Our code is available on https://github.com/xingy038/CTNeRF.
Authors: Long Ma, Jiajia Zhang, Hongping Deng, Ningyu Zhang, Qinglang Guo, Haiyang Yu, Yong Liao, Pengyuan Zhou
Abstract: The escalating quality of video generated by advanced video generation methods results in new security challenges, while there have been few relevant research efforts: 1) There is no open-source dataset for generated video detection, 2) No generated video detection method has been proposed so far. To this end, we propose an open-source dataset and a detection method for generated video for the first time. First, we propose a scalable dataset consisting of 964 prompts, covering various forgery targets, scenes, behaviors, and actions, as well as various generation models with different architectures and generation methods, including the most popular commercial models like OpenAI's Sora and Google's Veo. Second, we found via probing experiments that spatial artifact-based detectors lack generalizability. Hence, we propose a simple yet effective \textbf{de}tection model based on \textbf{f}rame \textbf{co}nsistency (\textbf{DeCoF}), which focuses on temporal artifacts by eliminating the impact of spatial artifacts during feature learning. Extensive experiments demonstrate the efficacy of DeCoF in detecting videos generated by unseen video generation models and confirm its powerful generalizability across several commercially proprietary models. Our code and dataset will be released at \url{https://github.com/wuwuwuyue/DeCoF}.
Authors: Yuxi Wei, Zi Wang, Yifan Lu, Chenxin Xu, Changxing Liu, Hao Zhao, Siheng Chen, Yanfeng Wang
Abstract: Scene simulation in autonomous driving has gained significant attention because of its huge potential for generating customized data. However, existing editable scene simulation approaches face limitations in terms of user interaction efficiency, multi-camera photo-realistic rendering and external digital assets integration. To address these challenges, this paper introduces ChatSim, the first system that enables editable photo-realistic 3D driving scene simulations via natural language commands with external digital assets. To enable editing with high command flexibility,~ChatSim leverages a large language model (LLM) agent collaboration framework. To generate photo-realistic outcomes, ChatSim employs a novel multi-camera neural radiance field method. Furthermore, to unleash the potential of extensive high-quality digital assets, ChatSim employs a novel multi-camera lighting estimation method to achieve scene-consistent assets' rendering. Our experiments on Waymo Open Dataset demonstrate that ChatSim can handle complex language commands and generate corresponding photo-realistic scene videos.
Authors: Dongyang Liu, Renrui Zhang, Longtian Qiu, Siyuan Huang, Weifeng Lin, Shitian Zhao, Shijie Geng, Ziyi Lin, Peng Jin, Kaipeng Zhang, Wenqi Shao, Chao Xu, Conghui He, Junjun He, Hao Shao, Pan Lu, Hongsheng Li, Yu Qiao, Peng Gao
Abstract: We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying multi-stage training into a one-stage all-in-one paradigm. To fully unleash the potential of MLLMs, we assemble a comprehensive multi-domain and multimodal dataset covering publicly available resources in language, vision, and vision-language tasks. We further enrich this collection with our curated OCR intensive and Set-of-Mark datasets, extending the diversity and generality. By training over different base LLMs including TinyLlama1.1B, InternLM2-7B, LLaMA2-13B, and Mixtral8x7B, we obtain a spectrum of MLLMs that vary in parameter size and multilingual capabilities. Comprehensive benchmarking reveals a strong correlation between the multi-modal performance with the data and parameter scales. Code and models are released at https://github.com/Alpha-VLLM/LLaMA2-Accessory
Authors: Henrique Jesus, Hugo Proen\c{c}a
Abstract: Large vision models based in deep learning architectures have been consistently advancing the state-of-the-art in biometric recognition. However, three weaknesses are commonly reported for such kind of approaches: 1) their extreme demands in terms of learning data; 2) the difficulties in generalising between different domains; and 3) the lack of interpretability/explainability, with biometrics being of particular interest, as it is important to provide evidence able to be used for forensics/legal purposes (e.g., in courts). To the best of our knowledge, this paper describes the first recognition framework/strategy that aims at addressing the three weaknesses simultaneously. At first, it relies exclusively in synthetic samples for learning purposes. Instead of requiring a large amount and variety of samples for each subject, the idea is to exclusively enroll a 3D point cloud per identity. Then, using generative strategies, we synthesize a very large (potentially infinite) number of samples, containing all the desired covariates (poses, clothing, distances, perspectives, lighting, occlusions,...). Upon the synthesizing method used, it is possible to adapt precisely to different kind of domains, which accounts for generalization purposes. Such data are then used to learn a model that performs local registration between image pairs, establishing positive correspondences between body parts that are the key, not only to recognition (according to cardinality and distribution), but also to provide an interpretable description of the response (e.g.: "both samples are from the same person, as they have similar facial shape, hair color and legs thickness").
Authors: Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu
Abstract: Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks, and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing, hindering their clinical utility across diverse resource-constrained scenarios in practice. In this paper, we propose a novel and lightweight framework Med-MoE (Mixture-of-Experts) that tackles both discriminative and generative multimodal medical tasks. The learning of Med-MoE consists of three steps: multimodal medical alignment, instruction tuning and routing, and domain-specific MoE tuning. After aligning multimodal medical images with LLM tokens, we then enable the model for different multimodal medical tasks with instruction tuning, together with a trainable router tailored for expert selection across input modalities. Finally, the model is tuned by integrating the router with multiple domain-specific experts, which are selectively activated and further empowered by meta expert. Comprehensive experiments on both open- and close-end medical question answering (Med-VQA) and image classification tasks across datasets such as VQA-RAD, SLAKE and Path-VQA demonstrate that our model can achieve performance superior to or on par with state-of-the-art baselines, while only requiring approximately 30\%-50\% of activated model parameters. Extensive analysis and ablations corroborate the effectiveness and practical utility of our method.
Authors: Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen, Xin Li, Cheng Wang
Abstract: The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes. However, the challenge arises due to the sparsity of LiDAR scans, which leads to pseudo-labels with erroneous size and position, resulting in subpar detection performance. To tackle this problem, this paper introduces a Commonsense Prototype-based Detector, termed CPD, for unsupervised 3D object detection. CPD first constructs Commonsense Prototype (CProto) characterized by high-quality bounding box and dense points, based on commonsense intuition. Subsequently, CPD refines the low-quality pseudo-labels by leveraging the size prior from CProto. Furthermore, CPD enhances the detection accuracy of sparsely scanned objects by the geometric knowledge from CProto. CPD outperforms state-of-the-art unsupervised 3D detectors on Waymo Open Dataset (WOD), PandaSet, and KITTI datasets by a large margin. Besides, by training CPD on WOD and testing on KITTI, CPD attains 90.85% and 81.01% 3D Average Precision on easy and moderate car classes, respectively. These achievements position CPD in close proximity to fully supervised detectors, highlighting the significance of our method. The code will be available at https://github.com/hailanyi/CPD.
Authors: Weifeng Wei, Jie Wang, Shuqi Deng, Jie Liu
Abstract: We introduce a high-fidelity neural implicit dense visual Simultaneous Localization and Mapping (SLAM) system, termed DF-SLAM. In our work, we employ dictionary factors for scene representation, encoding the geometry and appearance information of the scene as a combination of basis and coefficient factors. Compared to neural implicit dense visual SLAM methods that directly encode scene information as features, our method exhibits superior scene detail reconstruction capabilities and more efficient memory usage, while our model size is insensitive to the size of the scene map, making our method more suitable for large-scale scenes. Additionally, we employ feature integration rendering to accelerate color rendering speed while ensuring color rendering quality, further enhancing the real-time performance of our neural SLAM method. Extensive experiments on synthetic and real-world datasets demonstrate that our method is competitive with existing state-of-the-art neural implicit SLAM methods in terms of real-time performance, localization accuracy, and scene reconstruction quality. Our source code is available at https://github.com/funcdecl/DF-SLAM.
Authors: Anderson de Andrade, Ivan Baji\'c
Abstract: We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a different task as much as expected, given the estimated amount of information available in it. We interpret this issue using the predictive $\mathcal{V}$-information framework. In learnable scalable coding, previous work increased the utilization of side-information for input reconstruction by also rewarding input reconstruction when learning this shared representation. We evaluate the impact of this idea in the context of input reconstruction more rigorously and extended it to other computer vision tasks. We perform experiments using representations trained for object detection on COCO 2017 and depth estimation on the Cityscapes dataset, and use them to assist in image reconstruction and semantic segmentation tasks. The results show considerable improvements in the rate-distortion performance of the assisted tasks. Moreover, using the proposed representations, the performance of the base tasks are also improved. Results suggest that the proposed method induces simpler representations that are more compatible with downstream processes.
Authors: Rudolf Herdt, Peter Maass
Abstract: We investigate how generated structures of GANs correlate with their activations in hidden layers, with the purpose of better understanding the inner workings of those models and being able to paint structures with unconditionally trained GANs. This gives us more control over the generated images, allowing to generate them from a semantic segmentation map while not requiring such a segmentation in the training data. To this end we introduce the concept of tileable features, allowing us to identify activations that work well for painting.
Authors: Xiaofeng Cong, Yu Zhao, Jie Gui, Junming Hou, Dacheng Tao
Abstract: Underwater image enhancement (UIE) presents a significant challenge within computer vision research. Despite the development of numerous UIE algorithms, a thorough and systematic review is still absent. To foster future advancements, we provide a detailed overview of the UIE task from several perspectives. Firstly, we introduce the physical models, data construction processes, evaluation metrics, and loss functions. Secondly, we categorize and discuss recent algorithms based on their contributions, considering six aspects: network architecture, learning strategy, learning stage, auxiliary tasks, domain perspective, and disentanglement fusion. Thirdly, due to the varying experimental setups in the existing literature, a comprehensive and unbiased comparison is currently unavailable. To address this, we perform both quantitative and qualitative evaluations of state-of-the-art algorithms across multiple benchmark datasets. Lastly, we identify key areas for future research in UIE. A collection of resources for UIE can be found at {https://github.com/YuZhao1999/UIE}.
Authors: Yunfeng Li, Bo Wang, Jiuran Sun, Xueyi Wu, Ye Li
Abstract: Vision camera and sonar are naturally complementary in the underwater environment. Combining the information from two modalities will promote better observation of underwater targets. However, this problem has not received sufficient attention in previous research. Therefore, this paper introduces a new challenging RGB-Sonar (RGB-S) tracking task and investigates how to achieve efficient tracking of an underwater target through the interaction of RGB and sonar modalities. Specifically, we first propose an RGBS50 benchmark dataset containing 50 sequences and more than 87000 high-quality annotated bounding boxes. Experimental results show that the RGBS50 benchmark poses a challenge to currently popular SOT trackers. Second, we propose an RGB-S tracker called SCANet, which includes a spatial cross-attention module (SCAM) consisting of a novel spatial cross-attention layer and two independent global integration modules. The spatial cross-attention is used to overcome the problem of spatial misalignment of between RGB and sonar images. Third, we propose a SOT data-based RGB-S simulation training method (SRST) to overcome the lack of RGB-S training datasets. It converts RGB images into sonar-like saliency images to construct pseudo-data pairs, enabling the model to learn the semantic structure of RGB-S-like data. Comprehensive experiments show that the proposed spatial cross-attention effectively achieves the interaction between RGB and sonar modalities and SCANet achieves state-of-the-art performance on the proposed benchmark. The code is available at https://github.com/LiYunfengLYF/RGBS50.
Authors: Yunze Man, Liang-Yan Gui, Yu-Xiong Wang
Abstract: Being able to carry out complicated vision language reasoning tasks in 3D space represents a significant milestone in developing household robots and human-centered embodied AI. In this work, we demonstrate that a critical and distinct challenge in 3D vision language reasoning is situational awareness, which incorporates two key components: (1) The autonomous agent grounds its self-location based on a language prompt. (2) The agent answers open-ended questions from the perspective of its calculated position. To address this challenge, we introduce SIG3D, an end-to-end Situation-Grounded model for 3D vision language reasoning. We tokenize the 3D scene into sparse voxel representation and propose a language-grounded situation estimator, followed by a situated question answering module. Experiments on the SQA3D and ScanQA datasets show that SIG3D outperforms state-of-the-art models in situation estimation and question answering by a large margin (e.g., an enhancement of over 30% on situation estimation accuracy). Subsequent analysis corroborates our architectural design choices, explores the distinct functions of visual and textual tokens, and highlights the importance of situational awareness in the domain of 3D question answering.
Authors: Yang-Tian Sun, Yi-Hua Huang, Lin Ma, Xiaoyang Lyu, Yan-Pei Cao, Xiaojuan Qi
Abstract: Video representation is a long-standing problem that is crucial for various down-stream tasks, such as tracking,depth prediction,segmentation,view synthesis,and editing. However, current methods either struggle to model complex motions due to the absence of 3D structure or rely on implicit 3D representations that are ill-suited for manipulation tasks. To address these challenges, we introduce a novel explicit 3D representation-video Gaussian representation -- that embeds a video into 3D Gaussians. Our proposed representation models video appearance in a 3D canonical space using explicit Gaussians as proxies and associates each Gaussian with 3D motions for video motion. This approach offers a more intrinsic and explicit representation than layered atlas or volumetric pixel matrices. To obtain such a representation, we distill 2D priors, such as optical flow and depth, from foundation models to regularize learning in this ill-posed setting. Extensive applications demonstrate the versatility of our new video representation. It has been proven effective in numerous video processing tasks, including tracking, consistent video depth and feature refinement, motion and appearance editing, and stereoscopic video generation. Project page: https://sunyangtian.github.io/spatter_a_video_web/
Authors: Nikita Starodubcev, Mikhail Khoroshikh, Artem Babenko, Dmitry Baranchuk
Abstract: Diffusion distillation represents a highly promising direction for achieving faithful text-to-image generation in a few sampling steps. However, despite recent successes, existing distilled models still do not provide the full spectrum of diffusion abilities, such as real image inversion, which enables many precise image manipulation methods. This work aims to enrich distilled text-to-image diffusion models with the ability to effectively encode real images into their latent space. To this end, we introduce invertible Consistency Distillation (iCD), a generalized consistency distillation framework that facilitates both high-quality image synthesis and accurate image encoding in only 3-4 inference steps. Though the inversion problem for text-to-image diffusion models gets exacerbated by high classifier-free guidance scales, we notice that dynamic guidance significantly reduces reconstruction errors without noticeable degradation in generation performance. As a result, we demonstrate that iCD equipped with dynamic guidance may serve as a highly effective tool for zero-shot text-guided image editing, competing with more expensive state-of-the-art alternatives.
Authors: Youngmin Kim, Saejin Kim, Hoyeon Moon, Youngjae Yu, Junhyug Noh
Abstract: Scalp diseases and alopecia affect millions of people around the world, underscoring the urgent need for early diagnosis and management of the disease. However, the development of a comprehensive AI-based diagnosis system encompassing these conditions remains an underexplored domain due to the challenges associated with data imbalance and the costly nature of labeling. To address these issues, we propose ScalpVision, an AI-driven system for the holistic diagnosis of scalp diseases and alopecia. In ScalpVision, effective hair segmentation is achieved using pseudo image-label pairs and an innovative prompting method in the absence of traditional hair masking labels. This approach is crucial for extracting key features such as hair thickness and count, which are then used to assess alopecia severity. Additionally, ScalpVision introduces DiffuseIT-M, a generative model adept at dataset augmentation while maintaining hair information, facilitating improved predictions of scalp disease severity. Our experimental results affirm ScalpVision's efficiency in diagnosing a variety of scalp conditions and alopecia, showcasing its potential as a valuable tool in dermatological care.
Authors: Ningyuan Tang, Minghao Fu, Jianxin Wu
Abstract: The rapid scaling of large vision pretrained models makes fine-tuning tasks more and more difficult on edge devices with low computational resources. We explore a new visual adaptation paradigm called edge tuning, which treats large pretrained models as standalone feature extractors that run on powerful cloud servers. The fine-tuning carries out on edge devices with small networks which require low computational resources. Existing methods that are potentially suitable for our edge tuning paradigm are discussed. But, three major drawbacks hinder their application in edge tuning: low adaptation capability, large adapter network, and high information transfer overhead. To address these issues, we propose Minimal Interaction Edge Tuning, or MIET, which reveals that the sum of intermediate features from pretrained models not only has minimal information transfer but also has high adaptation capability. With a lightweight attention-based adaptor network, MIET achieves information transfer efficiency, parameter efficiency, computational and memory efficiency, and at the same time demonstrates competitive results on various visual adaptation benchmarks.
Authors: Sedigheh Eslami, Gerard de Melo
Abstract: Contrastive Language--Image Pre-training (CLIP) has manifested remarkable improvements in zero-shot classification and cross-modal vision-language tasks. Yet, from a geometrical point of view, the CLIP embedding space has been found to have a pronounced modality gap. This gap renders the embedding space overly sparse and disconnected, with different modalities being densely distributed in distinct subregions of the hypersphere. In this work, we aim at answering two main questions: 1. Does sharing the parameter space between the multi-modal encoders reduce the modality gap? 2. Can the gap be mitigated by pushing apart the uni-modal embeddings via intra-modality separation? We design AlignCLIP, in order to answer these questions and show that answers to both questions are positive. Through extensive experiments, we show that AlignCLIP achieves noticeable enhancements in the cross-modal alignment of the embeddings, and thereby, reduces the modality gap, while maintaining the performance across several downstream evaluations, such as zero-shot image classification, zero-shot multi-modal retrieval and zero-shot semantic text similarity.
Authors: Alpha Renner, Lazar Supic, Andreea Danielescu, Giacomo Indiveri, E. Paxon Frady, Friedrich T. Sommer, Yulia Sandamirskaya
Abstract: Visual Odometry (VO) is a method to estimate self-motion of a mobile robot using visual sensors. Unlike odometry based on integrating differential measurements that can accumulate errors, such as inertial sensors or wheel encoders, visual odometry is not compromised by drift. However, image-based VO is computationally demanding, limiting its application in use cases with low-latency, -memory, and -energy requirements. Neuromorphic hardware offers low-power solutions to many vision and AI problems, but designing such solutions is complicated and often has to be assembled from scratch. Here we propose to use Vector Symbolic Architecture (VSA) as an abstraction layer to design algorithms compatible with neuromorphic hardware. Building from a VSA model for scene analysis, described in our companion paper, we present a modular neuromorphic algorithm that achieves state-of-the-art performance on two-dimensional VO tasks. Specifically, the proposed algorithm stores and updates a working memory of the presented visual environment. Based on this working memory, a resonator network estimates the changing location and orientation of the camera. We experimentally validate the neuromorphic VSA-based approach to VO with two benchmarks: one based on an event camera dataset and the other in a dynamic scene with a robotic task.
Authors: Ziyi He, Albert C. S. Chung
Abstract: Template generation is a critical step in groupwise image registration, which involves aligning a group of subjects into a common space. While existing methods can generate high-quality template images, they often incur substantial time costs or are limited by fixed group scales. In this paper, we present InstantGroup, an efficient groupwise template generation framework based on variational autoencoder (VAE) models that leverage latent representations' arithmetic properties, enabling scalability to groups of any size. InstantGroup features a Dual VAEs backbone with shared-weight twin networks to handle pairs of inputs and incorporates a Displacement Inversion Module (DIM) to maintain template unbiasedness and a Subject-Template Alignment Module (STAM) to improve template quality and registration accuracy. Experiments on 3D brain MRI scans from the OASIS and ADNI datasets reveal that InstantGroup dramatically reduces runtime, generating templates within seconds for various group sizes while maintaining superior performance compared to state-of-the-art baselines on quantitative metrics, including unbiasedness and registration accuracy.
Authors: Xiulin Wang, Jing Liu, Fengyu Cong
Abstract: Tensor decomposition is a fundamental technique widely applied in signal processing, machine learning, and various other fields. However, traditional tensor decomposition methods encounter limitations when jointly analyzing multi-block tensors, as they often struggle to effectively explore shared information among tensors. In this study, we first introduce a novel coupled nonnegative CANDECOMP/PARAFAC decomposition algorithm optimized by the alternating proximal gradient method (CoNCPD-APG). This algorithm is specially designed to address the challenges of jointly decomposing different tensors that are partially or fully linked, while simultaneously extracting common components, individual components and, core tensors. Recognizing the computational challenges inherent in optimizing nonnegative constraints over high-dimensional tensor data, we further propose the lraCoNCPD-APG algorithm. By integrating low-rank approximation with the proposed CoNCPD-APG method, the proposed algorithm can significantly decrease the computational burden without compromising decomposition quality, particularly for multi-block large-scale tensors. Simulation experiments conducted on synthetic data, real-world face image data, and two kinds of electroencephalography (EEG) data demonstrate the practicality and superiority of the proposed algorithms for coupled nonnegative tensor decomposition problems. Our results underscore the efficacy of our methods in uncovering meaningful patterns and structures from complex multi-block tensor data, thereby offering valuable insights for future applications.
Authors: Jinbin Huang, Wenbin He, Liang Gou, Liu Ren, Chris Bryan
Abstract: Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most concepts lack interpretability, (2) existing methods require model knowledge, often unavailable at run time. Additionally, (3) there lacks a no-code method for post-understanding model improvement. Addressing these, we present InterVLS. The system facilitates model understanding by discovering text-aligned concepts, measuring their influence with model-agnostic linear surrogates. Employing visual analytics, InterVLS offers concept-based explanations and performance insights. It enables users to adjust concept influences to update a model, facilitating no-code model improvement. We evaluate InterVLS in a user study, illustrating its functionality with two scenarios. Results indicates that InterVLS is effective to help users identify influential concepts to a model, gain insights and adjust concept influence to improve the model. We conclude with a discussion based on our study results.
Authors: Minghong Duan, Linhao Qu, Zhiwei Yang, Manning Wang, Chenxi Zhang, Zhijian Song
Abstract: High-quality whole-slide scanners are expensive, complex, and time-consuming, thus limiting the acquisition and utilization of high-resolution pathology whole-slide images in daily clinical work. Deep learning-based single-image super-resolution techniques are an effective way to solve this problem by synthesizing high-resolution images from low-resolution ones. However, the existing super-resolution models applied in pathology images can only work in fixed integer magnifications, significantly decreasing their applicability. Though methods based on implicit neural representation have shown promising results in arbitrary-scale super-resolution of natural images, applying them directly to pathology images is inadequate because they have unique fine-grained image textures different from natural images. Thus, we propose an Implicit Self-Texture Enhancement-based dual-branch framework (ISTE) for arbitrary-scale super-resolution of pathology images to address this challenge. ISTE contains a pixel learning branch and a texture learning branch, which first learn pixel features and texture features, respectively. Then, we design a two-stage texture enhancement strategy to fuse the features from the two branches to obtain the super-resolution results, where the first stage is feature-based texture enhancement, and the second stage is spatial-domain-based texture enhancement. Extensive experiments on three public datasets show that ISTE outperforms existing fixed-scale and arbitrary-scale algorithms at multiple magnifications and helps to improve downstream task performance. To the best of our knowledge, this is the first work to achieve arbitrary-scale super-resolution in pathology images. Codes will be available.
Authors: Adane Nega Tarekegn, Mohib Ullah, Faouzi Alaya Cheikh
Abstract: Multi-label learning is a rapidly growing research area that aims to predict multiple labels from a single input data point. In the era of big data, tasks involving multi-label classification (MLC) or ranking present significant and intricate challenges, capturing considerable attention in diverse domains. Inherent difficulties in MLC include dealing with high-dimensional data, addressing label correlations, and handling partial labels, for which conventional methods prove ineffective. Recent years have witnessed a notable increase in adopting deep learning (DL) techniques to address these challenges more effectively in MLC. Notably, there is a burgeoning effort to harness the robust learning capabilities of DL for improved modelling of label dependencies and other challenges in MLC. However, it is noteworthy that comprehensive studies specifically dedicated to DL for multi-label learning are limited. Thus, this survey aims to thoroughly review recent progress in DL for multi-label learning, along with a summary of open research problems in MLC. The review consolidates existing research efforts in DL for MLC,including deep neural networks, transformers, autoencoders, and convolutional and recurrent architectures. Finally, the study presents a comparative analysis of the existing methods to provide insightful observations and stimulate future research directions in this domain.
Authors: Yunxin Li, Xinyu Chen, Baotian Hu, Haoyuan Shi, Min Zhang
Abstract: Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the visual knowledge-dimension alignment, i.e., connecting visuals to their relevant knowledge. Visual knowledge plays a significant role in analyzing, inferring, and interpreting information from visuals, helping improve the accuracy of answers to knowledge-based visual questions. In this paper, we mainly explore improving LMMs with visual-language knowledge alignment, especially aimed at challenging knowledge-based visual question answering (VQA). To this end, we present a Cognitive Visual-Language Mapper (CVLM), which contains a pretrained Visual Knowledge Aligner (VKA) and a Fine-grained Knowledge Adapter (FKA) used in the multimodal instruction tuning stage. Specifically, we design the VKA based on the interaction between a small language model and a visual encoder, training it on collected image-knowledge pairs to achieve visual knowledge acquisition and projection. FKA is employed to distill the fine-grained visual knowledge of an image and inject it into Large Language Models (LLMs). We conduct extensive experiments on knowledge-based VQA benchmarks and experimental results show that CVLM significantly improves the performance of LMMs on knowledge-based VQA (average gain by 5.0%). Ablation studies also verify the effectiveness of VKA and FKA, respectively. The codes are available at https://github.com/HITsz-TMG/Cognitive-Visual-Language-Mapper
URLs: https://github.com/HITsz-TMG/Cognitive-Visual-Language-Mapper
Authors: Alessandro Licciardi (Politecnico di Torino, Istituto Nazionale di Fisica Nucleare Sezione di Torino), Davide Carbone (Politecnico di Torino, Istituto Nazionale di Fisica Nucleare Sezione di Torino)
Abstract: Marine mammal communication is a complex field, hindered by the diversity of vocalizations and environmental factors. The Watkins Marine Mammal Sound Database (WMMD) constitutes a comprehensive labeled dataset employed in machine learning applications. Nevertheless, the methodologies for data preparation, preprocessing, and classification documented in the literature exhibit considerable variability and are typically not applied to the dataset in its entirety. This study initially undertakes a concise review of the state-of-the-art benchmarks pertaining to the dataset, with a particular focus on clarifying data preparation and preprocessing techniques. Subsequently, we explore the utilization of the Wavelet Scattering Transform (WST) and Mel spectrogram as preprocessing mechanisms for feature extraction. In this paper, we introduce \textbf{WhaleNet} (Wavelet Highly Adaptive Learning Ensemble Network), a sophisticated deep ensemble architecture for the classification of marine mammal vocalizations, leveraging both WST and Mel spectrogram for enhanced feature discrimination. By integrating the insights derived from WST and Mel representations, we achieved an improvement in classification accuracy by $8-10\%$ over existing architectures, corresponding to a classification accuracy of $97.61\%$.
Authors: Jiahao Huang, Liutao Yang, Fanwen Wang, Yang Nan, Angelica I. Aviles-Rivero, Carola-Bibiane Sch\"onlieb, Daoqiang Zhang, Guang Yang
Abstract: The recent Mamba model has shown remarkable adaptability for visual representation learning, including in medical imaging tasks. This study introduces MambaMIR, a Mamba-based model for medical image reconstruction, as well as its Generative Adversarial Network-based variant, MambaMIR-GAN. Our proposed MambaMIR inherits several advantages, such as linear complexity, global receptive fields, and dynamic weights, from the original Mamba model. The innovated arbitrary-mask mechanism effectively adapt Mamba to our image reconstruction task, providing randomness for subsequent Monte Carlo-based uncertainty estimation. Experiments conducted on various medical image reconstruction tasks, including fast MRI and SVCT, which cover anatomical regions such as the knee, chest, and abdomen, have demonstrated that MambaMIR and MambaMIR-GAN achieve comparable or superior reconstruction results relative to state-of-the-art methods. Additionally, the estimated uncertainty maps offer further insights into the reliability of the reconstruction quality. The code is publicly available at https://github.com/ayanglab/MambaMIR.
Authors: David Heurtel-Depeiges, Charles C. Margossian, Ruben Ohana, Bruno R\'egaldo-Saint Blancard
Abstract: In recent years, denoising problems have become intertwined with the development of deep generative models. In particular, diffusion models are trained like denoisers, and the distribution they model coincide with denoising priors in the Bayesian picture. However, denoising through diffusion-based posterior sampling requires the noise level and covariance to be known, preventing blind denoising. We overcome this limitation by introducing Gibbs Diffusion (GDiff), a general methodology addressing posterior sampling of both the signal and the noise parameters. Assuming arbitrary parametric Gaussian noise, we develop a Gibbs algorithm that alternates sampling steps from a conditional diffusion model trained to map the signal prior to the family of noise distributions, and a Monte Carlo sampler to infer the noise parameters. Our theoretical analysis highlights potential pitfalls, guides diagnostic usage, and quantifies errors in the Gibbs stationary distribution caused by the diffusion model. We showcase our method for 1) blind denoising of natural images involving colored noises with unknown amplitude and spectral index, and 2) a cosmology problem, namely the analysis of cosmic microwave background data, where Bayesian inference of "noise" parameters means constraining models of the evolution of the Universe.
Authors: Yidong Zhao, Joao Tourais, Iain Pierce, Christian Nitsche, Thomas A. Treibel, Sebastian Weing\"artner, Artur M. Schweidtmann, Qian Tao
Abstract: Deep learning (DL)-based methods have achieved state-of-the-art performance for a wide range of medical image segmentation tasks. Nevertheless, recent studies show that deep neural networks (DNNs) can be miscalibrated and overconfident, leading to "silent failures" that are risky} for clinical applications. Bayesian statistics provide an intuitive approach to DL failure detection, based on posterior probability estimation. However, Bayesian DL, and in particular the posterior estimation, is intractable for large medical image segmentation DNNs. To tackle this challenge, we propose a Bayesian learning framework by Hamiltonian Monte Carlo (HMC), tempered by cold posterior (CP) to accommodate medical data augmentation, named HMC-CP. For HMC computation, we further propose a cyclical annealing strategy, which captures both local and global geometries of the posterior distribution, enabling highly efficient Bayesian DNN training with the same computational budget requirements as training a single DNN. The resulting Bayesian DNN outputs an ensemble segmentation along with the segmentation uncertainty. We evaluate the proposed HMC-CP extensively on cardiac magnetic resonance image (MRI) segmentation, using in-domain steady-state free precession (SSFP) cine images as well as out-of-domain datasets of quantitative $T_1$ and $T_2$ mapping.
Authors: Hongruixuan Chen, Jian Song, Chengxi Han, Junshi Xia, Naoto Yokoya
Abstract: Convolutional neural networks (CNN) and Transformers have made impressive progress in the field of remote sensing change detection (CD). However, both architectures have inherent shortcomings: CNN are constrained by a limited receptive field that may hinder their ability to capture broader spatial contexts, while Transformers are computationally intensive, making them costly to train and deploy on large datasets. Recently, the Mamba architecture, based on state space models, has shown remarkable performance in a series of natural language processing tasks, which can effectively compensate for the shortcomings of the above two architectures. In this paper, we explore for the first time the potential of the Mamba architecture for remote sensing CD tasks. We tailor the corresponding frameworks, called MambaBCD, MambaSCD, and MambaBDA, for binary change detection (BCD), semantic change detection (SCD), and building damage assessment (BDA), respectively. All three frameworks adopt the cutting-edge Visual Mamba architecture as the encoder, which allows full learning of global spatial contextual information from the input images. For the change decoder, which is available in all three architectures, we propose three spatio-temporal relationship modeling mechanisms, which can be naturally combined with the Mamba architecture and fully utilize its attribute to achieve spatio-temporal interaction of multi-temporal features, thereby obtaining accurate change information. On five benchmark datasets, our proposed frameworks outperform current CNN- and Transformer-based approaches without using any complex training strategies or tricks, fully demonstrating the potential of the Mamba architecture in CD tasks. Further experiments show that our architecture is quite robust to degraded data. The source code will be available in https://github.com/ChenHongruixuan/MambaCD
Authors: Romario Gualdr\'on-Hurtado, Roman Jacome, Sergio Urrea, Henry Arguello, Luis Gonzalez
Abstract: Deep-learning (DL)-based image deconvolution (ID) has exhibited remarkable recovery performance, surpassing traditional linear methods. However, unlike traditional ID approaches that rely on analytical properties of the point spread function (PSF) to achieve high recovery performance - such as specific spectrum properties or small conditional numbers in the convolution matrix - DL techniques lack quantifiable metrics for evaluating PSF suitability for DL-assisted recovery. Aiming to enhance deconvolution quality, we propose a metric that employs a non-linear approach to learn the invertibility of an arbitrary PSF using a neural network by mapping it to a unit impulse. A lower discrepancy between the mapped PSF and a unit impulse indicates a higher likelihood of successful inversion by a DL network. Our findings reveal that this metric correlates with high recovery performance in DL and traditional methods, thereby serving as an effective regularizer in deconvolution tasks. This approach reduces the computational complexity over conventional condition number assessments and is a differentiable process. These useful properties allow its application in designing diffractive optical elements through end-to-end (E2E) optimization, achieving invertible PSFs, and outperforming the E2E baseline framework.
Authors: Jiahao Huang, Liutao Yang, Fanwen Wang, Yang Nan, Weiwen Wu, Chengyan Wang, Kuangyu Shi, Angelica I. Aviles-Rivero, Carola-Bibiane Sch\"onlieb, Daoqiang Zhang, Guang Yang
Abstract: Deep learning has been extensively applied in medical image reconstruction, where Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) represent the predominant paradigms, each possessing distinct advantages and inherent limitations: CNNs exhibit linear complexity with local sensitivity, whereas ViTs demonstrate quadratic complexity with global sensitivity. The emerging Mamba has shown superiority in learning visual representation, which combines the advantages of linear scalability and global sensitivity. In this study, we introduce MambaMIR, an Arbitrary-Masked Mamba-based model with wavelet decomposition for joint medical image reconstruction and uncertainty estimation. A novel Arbitrary Scan Masking (ASM) mechanism "masks out" redundant information to introduce randomness for further uncertainty estimation. Compared to the commonly used Monte Carlo (MC) dropout, our proposed MC-ASM provides an uncertainty map without the need for hyperparameter tuning and mitigates the performance drop typically observed when applying dropout to low-level tasks. For further texture preservation and better perceptual quality, we employ the wavelet transformation into MambaMIR and explore its variant based on the Generative Adversarial Network, namely MambaMIR-GAN. Comprehensive experiments have been conducted for multiple representative medical image reconstruction tasks, demonstrating that the proposed MambaMIR and MambaMIR-GAN outperform other baseline and state-of-the-art methods in different reconstruction tasks, where MambaMIR achieves the best reconstruction fidelity and MambaMIR-GAN has the best perceptual quality. In addition, our MC-ASM provides uncertainty maps as an additional tool for clinicians, while mitigating the typical performance drop caused by the commonly used dropout.
Authors: Andreas Koukounas, Georgios Mastrapas, Michael G\"unther, Bo Wang, Scott Martens, Isabelle Mohr, Saba Sturua, Mohammad Kalim Akram, Joan Fontanals Mart\'inez, Saahil Ognawala, Susana Guzman, Maximilian Werk, Nan Wang, Han Xiao
Abstract: Contrastive Language-Image Pretraining (CLIP) is widely used to train models to align images and texts in a common embedding space by mapping them to fixed-sized vectors. These models are key to multimodal information retrieval and related tasks. However, CLIP models generally underperform in text-only tasks compared to specialized text models. This creates inefficiencies for information retrieval systems that keep separate embeddings and models for text-only and multimodal tasks. We propose a novel, multi-task contrastive training method to address this issue, which we use to train the jina-clip-v1 model to achieve the state-of-the-art performance on both text-image and text-text retrieval tasks.
Authors: Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat, Prayag Tiwari, Stefan Byttner
Abstract: Although input-gradients techniques have evolved to mitigate and tackle the challenges associated with gradients, modern gradient-weighted CAM approaches still rely on vanilla gradients, which are inherently susceptible to the saturation phenomena. Despite recent enhancements have incorporated counterfactual gradient strategies as a mitigating measure, these local explanation techniques still exhibit a lack of sensitivity to their baseline parameter. Our work proposes a gradient-weighted CAM augmentation that tackles both the saturation and sensitivity problem by reshaping the gradient computation, incorporating two well-established and provably approaches: Expected Gradients and kernel smoothing. By revisiting the original formulation as the smoothed expectation of the perturbed integrated gradients, one can concurrently construct more faithful, localized and robust explanations which minimize infidelity. Through fine modulation of the perturbation distribution it is possible to regulate the complexity characteristic of the explanation, selectively discriminating stable features. Our technique, Expected Grad-CAM, differently from recent works, exclusively optimizes the gradient computation, purposefully designed as an enhanced substitute of the foundational Grad-CAM algorithm and any method built therefrom. Quantitative and qualitative evaluations have been conducted to assess the effectiveness of our method.
Authors: Jinuk Kim, Marwa El Halabi, Mingi Ji, Hyun Oh Song
Abstract: Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compression methods remove redundant non-linear activation functions and merge the consecutive convolution layers into a single layer. However, these methods suffer from a critical drawback; the kernel size of the merged layers becomes larger, significantly undermining the latency reduction gained from reducing the depth of the network. We show that this problem can be addressed by jointly pruning convolution layers and activation functions. To this end, we propose LayerMerge, a novel depth compression method that selects which activation layers and convolution layers to remove, to achieve a desired inference speed-up while minimizing performance loss. Since the corresponding selection problem involves an exponential search space, we formulate a novel surrogate optimization problem and efficiently solve it via dynamic programming. Empirical results demonstrate that our method consistently outperforms existing depth compression and layer pruning methods on various network architectures, both on image classification and generation tasks. We release the code at https://github.com/snu-mllab/LayerMerge.
Authors: Peter Lorenz, Mario Fernandez, Jens M\"uller, Ullrich K\"othe
Abstract: Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in real-world scenarios. In recent years, many OOD detectors have been developed, and even the benchmarking has been standardized, i.e. OpenOOD. The number of post-hoc detectors is growing fast and showing an option to protect a pre-trained classifier against natural distribution shifts, claiming to be ready for real-world scenarios. However, its efficacy in handling adversarial examples has been neglected in the majority of studies. This paper investigates the adversarial robustness of the 16 post-hoc detectors on several evasion attacks and discuss a roadmap towards adversarial defense in OOD detectors.
Authors: Junjie Chen, Subin Huang
Abstract: The prevalence of sarcasm in social media, conveyed through text-image combinations, presents significant challenges for sentiment analysis and intention mining. Current multi-modal sarcasm detection methods have been proven to struggle with biases from spurious cues, leading to a superficial understanding of the complex interactions between text and image. To address these issues, we propose InterCLIP-MEP, a robust framework for multi-modal sarcasm detection. InterCLIP-MEP introduces a refined variant of CLIP, Interactive CLIP (InterCLIP), as the backbone, enhancing sample representations by embedding cross-modality information in each encoder. Furthermore, a novel training strategy is designed to adapt InterCLIP for a Memory-Enhanced Predictor (MEP). MEP uses dynamic dual-channel memory to store valuable historical knowledge of test samples and then leverages this memory as a non-parametric classifier to derive the final prediction. By using InterCLIP to encode text-image interactions more effectively and incorporating MEP, InterCLIP-MEP offers a more robust recognition of multi-modal sarcasm. Experiments demonstrate that InterCLIP-MEP achieves state-of-the-art performance on the MMSD2.0 benchmark. Code and data are available at https://github.com/CoderChen01/InterCLIP-MEP.
Authors: Alex Lence, Ahmad Fall, Federica Granese, Blaise Hanczar, Joe-Elie Salem, Jean-Daniel Zucker, Edi Prifti
Abstract: In this work, we address the challenge of reconstructing the complete 12-lead ECG signal from incomplete parts of it. We focus on two main scenarii: (i) reconstructing missing signal segments within an ECG lead and (ii) recovering missing leads from a single-lead. We propose a model with a U-Net architecture trained on a novel objective function to address the reconstruction problem. This function incorporates both spatial and temporal aspects of the ECG by combining the distance in amplitude between the reconstructed and real signals with the signal trend. Through comprehensive assessments using both a real-life dataset and a publicly accessible one, we demonstrate that the proposed approach consistently outperforms state-of-the-art methods based on generative adversarial networks and a CopyPaste strategy. Our proposed model demonstrates superior performance in standard distortion metrics and preserves critical ECG characteristics, particularly the P, Q, R, S, and T wave coordinates. Two emerging clinical applications emphasize the relevance of our work. The first is the increasing need to digitize paper-stored ECGs for utilization in AI-based applications (automatic annotation and risk-quantification), often limited to digital ECG complete 10s recordings. The second is the widespread use of wearable devices that record ECGs but typically capture only a small subset of the 12 standard leads. In both cases, a non-negligible amount of information is lost or not recorded, which our approach aims to recover to overcome these limitations.
Authors: Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
Abstract: The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community established benchmarks such as ImageNet-C as a fundamental prerequisite to measure progress towards those challenges. Similar datasets are largely absent in the medical imaging community which lacks a comprehensive benchmark that spans across imaging modalities and applications. To address this gap, we create and open-source MedMNIST-C, a benchmark dataset based on the MedMNIST+ collection covering 12 datasets and 9 imaging modalities. We simulate task and modality-specific image corruptions of varying severity to comprehensively evaluate the robustness of established algorithms against real-world artifacts and distribution shifts. We further provide quantitative evidence that our simple-to-use artificial corruptions allow for highly performant, lightweight data augmentation to enhance model robustness. Unlike traditional, generic augmentation strategies, our approach leverages domain knowledge, exhibiting significantly higher robustness when compared to widely adopted methods. By introducing MedMNIST-C and open-sourcing the corresponding library allowing for targeted data augmentations, we contribute to the development of increasingly robust methods tailored to the challenges of medical imaging. The code is available at https://github.com/francescodisalvo05/medmnistc-api}{github.com/francescodisalvo05/medmnistc-api .