Authors: S\'egol\`ene Martin (OPIS, CVN), Yunshi Huang (ETS), Fereshteh Shakeri (ETS), Jean-Christophe Pesquet (OPIS, CVN), Ismail Ben Ayed (ETS)
Abstract: Transductive inference has been widely investigated in few-shot image classification, but completely overlooked in the recent, fast growing literature on adapting vision-langage models like CLIP. This paper addresses the transductive zero-shot and few-shot CLIP classification challenge, in which inference is performed jointly across a mini-batch of unlabeled query samples, rather than treating each instance independently. We initially construct informative vision-text probability features, leading to a classification problem on the unit simplex set. Inspired by Expectation-Maximization (EM), our optimization-based classification objective models the data probability distribution for each class using a Dirichlet law. The minimization problem is then tackled with a novel block Majorization-Minimization algorithm, which simultaneously estimates the distribution parameters and class assignments. Extensive numerical experiments on 11 datasets underscore the benefits and efficacy of our batch inference approach.On zero-shot tasks with test batches of 75 samples, our approach yields near 20% improvement in ImageNet accuracy over CLIP's zero-shot performance. Additionally, we outperform state-of-the-art methods in the few-shot setting. The code is available at: https://github.com/SegoleneMartin/transductive-CLIP.
Authors: Zolt\'an \'A. Milacski, Koichiro Niinuma, Ryosuke Kawamura, Fernando de la Torre, L\'aszl\'o A. Jeni
Abstract: The connection between our 3D surroundings and the descriptive language that characterizes them would be well-suited for localizing and generating human motion in context but for one problem. The complexity introduced by multiple modalities makes capturing this connection challenging with a fixed set of descriptors. Specifically, closed vocabulary scene encoders, which require learning text-scene associations from scratch, have been favored in the literature, often resulting in inaccurate motion grounding. In this paper, we propose a method that integrates an open vocabulary scene encoder into the architecture, establishing a robust connection between text and scene. Our two-step approach starts with pretraining the scene encoder through knowledge distillation from an existing open vocabulary semantic image segmentation model, ensuring a shared text-scene feature space. Subsequently, the scene encoder is fine-tuned for conditional motion generation, incorporating two novel regularization losses that regress the category and size of the goal object. Our methodology achieves up to a 30% reduction in the goal object distance metric compared to the prior state-of-the-art baseline model on the HUMANISE dataset. This improvement is demonstrated through evaluations conducted using three implementations of our framework and a perceptual study. Additionally, our method is designed to seamlessly accommodate future 2D segmentation methods that provide per-pixel text-aligned features for distillation.
Authors: Mengyi Shan, Lu Dong, Yutao Han, Yuan Yao, Tao Liu, Ifeoma Nwogu, Guo-Jun Qi, Mitch Hill
Abstract: This work aims to generate natural and diverse group motions of multiple humans from textual descriptions. While single-person text-to-motion generation is extensively studied, it remains challenging to synthesize motions for more than one or two subjects from in-the-wild prompts, mainly due to the lack of available datasets. In this work, we curate human pose and motion datasets by estimating pose information from large-scale image and video datasets. Our models use a transformer-based diffusion framework that accommodates multiple datasets with any number of subjects or frames. Experiments explore both generation of multi-person static poses and generation of multi-person motion sequences. To our knowledge, our method is the first to generate multi-subject motion sequences with high diversity and fidelity from a large variety of textual prompts.
Authors: Robert Gabriel Popescu, Nantheera Anantrasirichai, Juliet Biggs
Abstract: Satellite images have the potential to detect volcanic deformation prior to eruptions, but while a vast number of images are routinely acquired, only a small percentage contain volcanic deformation events. Manual inspection could miss these anomalies, and an automatic system modelled with supervised learning requires suitably labelled datasets. To tackle these issues, this paper explores the use of unsupervised deep learning on satellite data for the purpose of identifying volcanic deformation as anomalies. Our detector is based on Patch Distribution Modeling (PaDiM), and the detection performance is enhanced with a weighted distance, assigning greater importance to features from deeper layers. Additionally, we propose a preprocessing approach to handle noisy and incomplete data points. The final framework was tested with five volcanoes, which have different deformation characteristics and its performance was compared against the supervised learning method for volcanic deformation detection.
Authors: Wentian Xu, Matthew Moffat, Thalia Seale, Ziyun Liang, Felix Wagner, Daniel Whitehouse, David Menon, Virginia Newcombe, Natalie Voets, Abhirup Banerjee, Konstantinos Kamnitsas
Abstract: Models for segmentation of brain lesions in multi-modal MRI are commonly trained for a specific pathology using a single database with a predefined set of MRI modalities, determined by a protocol for the specific disease. This work explores the following open questions: Is it feasible to train a model using multiple databases that contain varying sets of MRI modalities and annotations for different brain pathologies? Will this joint learning benefit performance on the sets of modalities and pathologies available during training? Will it enable analysis of new databases with different sets of modalities and pathologies? We develop and compare different methods and show that promising results can be achieved with appropriate, simple and practical alterations to the model and training framework. We experiment with 7 databases containing 5 types of brain pathologies and different sets of MRI modalities. Results demonstrate, for the first time, that joint training on multi-modal MRI databases with different brain pathologies and sets of modalities is feasible and offers practical benefits. It enables a single model to segment pathologies encountered during training in diverse sets of modalities, while facilitating segmentation of new types of pathologies such as via follow-up fine-tuning. The insights this study provides into the potential and limitations of this paradigm should prove useful for guiding future advances in the direction. Code and pretrained models: https://github.com/WenTXuL/MultiUnet
Authors: Jiaze Wang, Yi Wang, Ziyu Guo, Renrui Zhang, Donghao Zhou, Guangyong Chen, Anfeng Liu, Pheng-Ann Heng
Abstract: Data augmentation has proven to be a vital tool for enhancing the generalization capabilities of deep learning models, especially in the context of 3D vision where traditional datasets are often limited. Despite previous advancements, existing methods primarily cater to unimodal data scenarios, leaving a gap in the augmentation of multimodal triplet data, which integrates text, images, and point clouds. Simultaneously augmenting all three modalities enhances diversity and improves alignment across modalities, resulting in more comprehensive and robust 3D representations. To address this gap, we propose TripletMix, a novel approach to address the previously unexplored issue of multimodal data augmentation in 3D understanding. TripletMix innovatively applies the principles of mixed-based augmentation to multimodal triplet data, allowing for the preservation and optimization of cross-modal connections. Our proposed TripletMix combines feature-level and input-level augmentations to achieve dual enhancement between raw data and latent features, significantly improving the model's cross-modal understanding and generalization capabilities by ensuring feature consistency and providing diverse and realistic training samples. We demonstrate that TripletMix not only improves the baseline performance of models in various learning scenarios including zero-shot and linear probing classification but also significantly enhances model generalizability. Notably, we improved the zero-shot classification accuracy on ScanObjectNN from 51.3 percent to 61.9 percent, and on Objaverse-LVIS from 46.8 percent to 51.4 percent. Our findings highlight the potential of multimodal data augmentation to significantly advance 3D object recognition and understanding.
Authors: Hongjun Wu, Li Xiao, Xingkuo Zhang, Yining Miao
Abstract: Knowledge distillation is commonly employed to compress neural networks, reducing the inference costs and memory footprint. In the scenario of homogenous architecture, feature-based methods have been widely validated for their effectiveness. However, in scenarios where the teacher and student models are of heterogeneous architectures, the inherent differences in feature representation significantly degrade the performance of these methods. Recent studies have highlighted that low-frequency components constitute the majority of image features. Motivated by this, we propose a Low-Frequency Components-based Contrastive Knowledge Distillation (LFCC) framework that significantly enhances the performance of feature-based distillation between heterogeneous architectures. Specifically, we designe a set of multi-scale low-pass filters to extract the low-frequency components of intermediate features from both the teacher and student models, aligning them in a compact space to overcome architectural disparities. Moreover, leveraging the intrinsic pairing characteristic of the teacher-student framework, we design an innovative sample-level contrastive learning framework that adeptly restructures the constraints of within-sample feature similarity and between-sample feature divergence into a contrastive learning task. This strategy enables the student model to capitalize on intra-sample feature congruence while simultaneously enhancing the discrimination of features among disparate samples. Consequently, our LFCC framework accurately captures the commonalities in feature representation across heterogeneous architectures. Extensive evaluations and empirical analyses across three architectures (CNNs, Transformers, and MLPs) demonstrate that LFCC achieves superior performance on the challenging benchmarks of ImageNet-1K and CIFAR-100. All codes will be publicly available.
Authors: Haonan Han, Rui Yang, Huan Liao, Jiankai Xing, Zunnan Xu, Xiaoming Yu, Junwei Zha, Xiu Li, Wanhua Li
Abstract: Traditional image-to-3D models often struggle with scenes containing multiple objects due to biases and occlusion complexities. To address this challenge, we present REPARO, a novel approach for compositional 3D asset generation from single images. REPARO employs a two-step process: first, it extracts individual objects from the scene and reconstructs their 3D meshes using off-the-shelf image-to-3D models; then, it optimizes the layout of these meshes through differentiable rendering techniques, ensuring coherent scene composition. By integrating optimal transport-based long-range appearance loss term and high-level semantic loss term in the differentiable rendering, REPARO can effectively recover the layout of 3D assets. The proposed method can significantly enhance object independence, detail accuracy, and overall scene coherence. Extensive evaluation of multi-object scenes demonstrates that our REPARO offers a comprehensive approach to address the complexities of multi-object 3D scene generation from single images.
Authors: Jeffrey Wen, Rizwan Ahmad, Philip Schniter
Abstract: In imaging inverse problems, one seeks to recover an image from missing/corrupted measurements. Because such problems are ill-posed, there is great motivation to quantify the uncertainty induced by the measurement-and-recovery process. Motivated by applications where the recovered image is used for a downstream task, such as soft-output classification, we propose a task-centered approach to uncertainty quantification. In particular, we use conformal prediction to construct an interval that is guaranteed to contain the task output from the true image up to a user-specified probability, and we use the width of that interval to quantify the uncertainty contributed by measurement-and-recovery. For posterior-sampling-based image recovery, we construct locally adaptive prediction intervals. Furthermore, we propose to collect measurements over multiple rounds, stopping as soon as the task uncertainty falls below an acceptable level. We demonstrate our methodology on accelerated magnetic resonance imaging (MRI).
Authors: Maxime Zanella, Ismail Ben Ayed
Abstract: Recent progress in the few-shot adaptation of Vision-Language Models (VLMs) has further pushed their generalization capabilities, at the expense of just a few labeled samples within the target downstream task. However, this promising, already quite abundant few-shot literature has focused principally on prompt learning and, to a lesser extent, on adapters, overlooking the recent advances in Parameter-Efficient Fine-Tuning (PEFT). Furthermore, existing few-shot learning methods for VLMs often rely on heavy training procedures and/or carefully chosen, task-specific hyper-parameters, which might impede their applicability. In response, we introduce Low-Rank Adaptation (LoRA) in few-shot learning for VLMs, and show its potential on 11 datasets, in comparison to current state-of-the-art prompt- and adapter-based approaches. Surprisingly, our simple CLIP-LoRA method exhibits substantial improvements, while reducing the training times and keeping the same hyper-parameters in all the target tasks, i.e., across all the datasets and numbers of shots. Certainly, our surprising results do not dismiss the potential of prompt-learning and adapter-based research. However, we believe that our strong baseline could be used to evaluate progress in these emergent subjects in few-shot VLMs.
Authors: Shubhang Bhatnagar, Narendra Ahuja
Abstract: Deep metric learning (DML) involves training a network to learn a semantically meaningful representation space. Many current approaches mine n-tuples of examples and model interactions within each tuplets. We present a novel, compositional DML model, inspired by electrostatic fields in physics that, instead of in tuples, represents the influence of each example (embedding) by a continuous potential field, and superposes the fields to obtain their combined global potential field. We use attractive/repulsive potential fields to represent interactions among embeddings from images of the same/different classes. Contrary to typical learning methods, where mutual influence of samples is proportional to their distance, we enforce reduction in such influence with distance, leading to a decaying field. We show that such decay helps improve performance on real world datasets with large intra-class variations and label noise. Like other proxy-based methods, we also use proxies to succinctly represent sub-populations of examples. We evaluate our method on three standard DML benchmarks- Cars-196, CUB-200-2011, and SOP datasets where it outperforms state-of-the-art baselines.
Authors: Abrar Fahim, Alex Murphy, Alona Fyshe
Abstract: Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space. Recently, a modality gap has been reported in two-encoder contrastive models like CLIP, meaning that the image and text embeddings reside in disjoint areas of the latent space. Previous studies suggest that this gap exists due to 1) the cone effect, 2) mismatched pairs in the dataset, and 3) insufficient training. We show that, even when accounting for all these factors, and even when using the same modality, the contrastive loss actually creates a gap during training. As a result, We propose that the modality gap is inherent to the two-encoder contrastive loss and rename it the contrastive gap. We present evidence that attributes this contrastive gap to low uniformity in CLIP space, resulting in embeddings that occupy only a small portion of the latent space. To close the gap, we adapt the uniformity and alignment properties of unimodal contrastive loss to the multi-modal setting and show that simply adding these terms to the CLIP loss distributes the embeddings more uniformly in the representational space, closing the gap. In our experiments, we show that the modified representational space achieves better performance than default CLIP loss in downstream tasks such as zero-shot image classification and multi-modal arithmetic.
Authors: Linh Van Ma, Tran Thien Dat Nguyen, Ba-Ngu Vo, Hyunsung Jang, Moongu Jeon
Abstract: We propose a 3D multi-object tracking (MOT) solution using only 2D detections from monocular cameras, which automatically initiates/terminates tracks as well as resolves track appearance-reappearance and occlusions. Moreover, this approach does not require detector retraining when cameras are reconfigured but only the camera matrices of reconfigured cameras need to be updated. Our approach is based on a Bayesian multi-object formulation that integrates track initiation/termination, re-identification, occlusion handling, and data association into a single Bayes filtering recursion. However, the exact filter that utilizes all these functionalities is numerically intractable due to the exponentially growing number of terms in the (multi-object) filtering density, while existing approximations trade-off some of these functionalities for speed. To this end, we develop a more efficient approximation suitable for online MOT by incorporating object features and kinematics into the measurement model, which improves data association and subsequently reduces the number of terms. Specifically, we exploit the 2D detections and extracted features from multiple cameras to provide a better approximation of the multi-object filtering density to realize the track initiation/termination and re-identification functionalities. Further, incorporating a tractable geometric occlusion model based on 2D projections of 3D objects on the camera planes realizes the occlusion handling functionality of the filter. Evaluation of the proposed solution on challenging datasets demonstrates significant improvements and robustness when camera configurations change on-the-fly, compared to existing multi-view MOT solutions. The source code is publicly available at https://github.com/linh-gist/mv-glmb-ab.
Authors: Zhenhai Zhu, Radu Soricut
Abstract: Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on improving the image tokenizer itself has been reported in the literature. In this paper, we propose a new image tokenizer based on wavelet transformation. We show that ViT models with the new tokenizer achieve both higher training throughput and better top-1 precision for the ImageNet validation set. We present a theoretical analysis on why the proposed tokenizer improves the training throughput without any change to ViT model architecture. Our analysis suggests that the new tokenizer can effectively handle high-resolution images and is naturally resistant to adversarial attack. Furthermore, the proposed image tokenizer offers a fresh perspective on important new research directions for ViT-based model design, such as image tokens on a non-uniform grid for image understanding.
Authors: Pritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan \"O. Ar{\i}k, Tomas Pfister
Abstract: Despite their remarkable progress, Multimodal Large Language Models (MLLMs) tend to hallucinate factually inaccurate information. In this work, we address object hallucinations in MLLMs, where information is offered about an object that is not present in the model input. We introduce a contrastive tuning method that can be applied to a pretrained off-the-shelf MLLM for mitigating hallucinations while preserving its general vision-language capabilities. For a given factual token, we create a hallucinated token through generative data augmentation by selectively altering the ground-truth information. The proposed contrastive tuning is applied at the token level to improve the relative likelihood of the factual token compared to the hallucinated one. Our thorough evaluation confirms the effectiveness of contrastive tuning in mitigating hallucination. Moreover, the proposed contrastive tuning is simple, fast, and requires minimal training with no additional overhead at inference.
Authors: Renyi Qu, Mark Yatskar
Abstract: Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from large language models (LLMs). This introduces randomness and compromises both transparency and reliability, which are essential for addressing safety issues in AI systems. We introduce \texttt{Hi-CoDe} (Hierarchical Concept Decomposition), a novel framework designed to enhance model interpretability through structured concept analysis. Our approach consists of two main components: (1) We use GPT-4 to decompose an input image into a structured hierarchy of visual concepts, thereby forming a visual concept tree. (2) We then employ an ensemble of simple linear classifiers that operate on concept-specific features derived from CLIP to perform classification. Our approach not only aligns with the performance of state-of-the-art models but also advances transparency by providing clear insights into the decision-making process and highlighting the importance of various concepts. This allows for a detailed analysis of potential failure modes and improves model compactness, therefore setting a new benchmark in interpretability without compromising the accuracy.
Authors: Ido Sobol, Chenfeng Xu, Or Litany
Abstract: Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce to immersive virtual experiences. Recent advancements in diffusion models, particularly the Zero-1-to-3 model, have been widely adopted for generating plausible views, videos, and 3D models. However, these models still struggle with inconsistencies and implausibility in new views generation, especially for challenging changes in viewpoint. In this work, we propose Zero-to-Hero, a novel test-time approach that enhances view synthesis by manipulating attention maps during the denoising process of Zero-1-to-3. By drawing an analogy between the denoising process and stochastic gradient descent (SGD), we implement a filtering mechanism that aggregates attention maps, enhancing generation reliability and authenticity. This process improves geometric consistency without requiring retraining or significant computational resources. Additionally, we modify the self-attention mechanism to integrate information from the source view, reducing shape distortions. These processes are further supported by a specialized sampling schedule. Experimental results demonstrate substantial improvements in fidelity and consistency, validated on a diverse set of out-of-distribution objects.
Authors: Juntao Zhang, Kun Bian, Peng Cheng, Wenbo An, Jianning Liu, Jun Zhou
Abstract: In recent years, State Space Models (SSMs) with efficient hardware-aware designs, known as the Mamba deep learning models, have made significant progress in modeling long sequences such as language understanding. Therefore, building efficient and general-purpose visual backbones based on SSMs is a promising direction. Compared to traditional convolutional neural networks (CNNs) and Vision Transformers (ViTs), the performance of Vision Mamba (ViM) methods is not yet fully competitive. To enable SSMs to process image data, ViMs typically flatten 2D images into 1D sequences, inevitably ignoring some 2D local dependencies, thereby weakening the model's ability to interpret spatial relationships from a global perspective. We use Fast Fourier Transform (FFT) to obtain the spectrum of the feature map and add it to the original feature map, enabling ViM to model a unified visual representation in both frequency and spatial domains. The introduction of frequency domain information enables ViM to have a global receptive field during scanning. We propose a novel model called Vim-F, which employs pure Mamba encoders and scans in both the frequency and spatial domains. Moreover, we question the necessity of position embedding in ViM and remove it accordingly in Vim-F, which helps to fully utilize the efficient long-sequence modeling capability of ViM. Finally, we redesign a patch embedding for Vim-F, leveraging a convolutional stem to capture more local correlations, further improving the performance of Vim-F. Code is available at: \url{https://github.com/yws-wxs/Vim-F}.
Authors: Mohammadjavad Matinkia, Nilanjan Ray
Abstract: Diffeomorphic image registration (DIR) is a critical task in 3D medical image analysis, aimed at finding topology preserving deformations between pairs of images. Focusing on the solution of the flow map differential equation as the diffeomorphic deformation, recent methods use discrete timesteps along with various regularization terms to penalize the negative determinant of Jacobian and impose smoothness of the solution vector field. In this paper, we propose a novel learning-based approach for diffeomorphic 3D-image registration which finds the diffeomorphisms in the time continuum with fewer regularization terms and no additional integration. As one of the fundamental properties of flow maps, we exploit the semigroup property as the only form of regularization, ensuring temporally continuous diffeomorphic flows between pairs of images. Leveraging this property, our method alleviates the need for additional regularization terms and scaling and squaring integration during both training and evaluation. To achieve time-continuous diffeomorphisms, we employ time-embedded UNets, a technique commonly utilized in diffusion models. The proposed method reveals that ensuring diffeomorphism in a continuous time interval leads to better registration results. Experimental results on two public datasets (OASIS and CANDI) demonstrate the superiority of our model over both learning-based and optimization-based methods.
Authors: Xuehao Gao, Yang Yang, Yang Wu, Shaoyi Du, Auo-Jun Qi
Abstract: Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one's intention. While many fruitful efforts have been made to human motion prediction, most approaches focus on pose-driven prediction and inferring human motion in isolation from the contextual environment, thus leaving the body location movement in the scene behind. However, real-world human movements are goal-directed and highly influenced by the spatial layout of their surrounding scenes. In this paper, instead of planning future human motion in a 'dark' room, we propose a Multi-Condition Latent Diffusion network (MCLD) that reformulates the human motion prediction task as a multi-condition joint inference problem based on the given historical 3D body motion and the current 3D scene contexts. Specifically, instead of directly modeling joint distribution over the raw motion sequences, MCLD performs a conditional diffusion process within the latent embedding space, characterizing the cross-modal mapping from the past body movement and current scene context condition embeddings to the future human motion embedding. Extensive experiments on large-scale human motion prediction datasets demonstrate that our MCLD achieves significant improvements over the state-of-the-art methods on both realistic and diverse predictions.
Authors: You Huang, Zongyu Lan, Liujuan Cao, Xianming Lin, Shengchuan Zhang, Guannan Jiang, Rongrong Ji
Abstract: The Segment Anything Model (SAM) marks a notable milestone in segmentation models, highlighted by its robust zero-shot capabilities and ability to handle diverse prompts. SAM follows a pipeline that separates interactive segmentation into image preprocessing through a large encoder and interactive inference via a lightweight decoder, ensuring efficient real-time performance. However, SAM faces stability issues in challenging samples upon this pipeline. These issues arise from two main factors. Firstly, the image preprocessing disables SAM from dynamically using image-level zoom-in strategies to refocus on the target object during interaction. Secondly, the lightweight decoder struggles to sufficiently integrate interactive information with image embeddings. To address these two limitations, we propose FocSAM with a pipeline redesigned on two pivotal aspects. First, we propose Dynamic Window Multi-head Self-Attention (Dwin-MSA) to dynamically refocus SAM's image embeddings on the target object. Dwin-MSA localizes attention computations around the target object, enhancing object-related embeddings with minimal computational overhead. Second, we propose Pixel-wise Dynamic ReLU (P-DyReLU) to enable sufficient integration of interactive information from a few initial clicks that have significant impacts on the overall segmentation results. Experimentally, FocSAM augments SAM's interactive segmentation performance to match the existing state-of-the-art method in segmentation quality, requiring only about 5.6% of this method's inference time on CPUs.
Authors: Weining Ren, Zihan Zhu, Boyang Sun, Jiaqi Chen, Marc Pollefeys, Songyou Peng
Abstract: Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting changes. Existing methods manage controlled environments and low occlusion ratios but fall short in render quality, especially under high occlusion scenarios. In this paper, we introduce NeRF On-the-go, a simple yet effective approach that enables the robust synthesis of novel views in complex, in-the-wild scenes from only casually captured image sequences. Delving into uncertainty, our method not only efficiently eliminates distractors, even when they are predominant in captures, but also achieves a notably faster convergence speed. Through comprehensive experiments on various scenes, our method demonstrates a significant improvement over state-of-the-art techniques. This advancement opens new avenues for NeRF in diverse and dynamic real-world applications.
Authors: Chaitat Utintu, Pinaki Nath Chowdhury, Aneeshan Sain, Subhadeep Koley, Ayan Kumar Bhunia, Yi-Zhe Song
Abstract: This paper introduces a novel approach to sketch colourisation, inspired by the universal childhood activity of colouring and its professional applications in design and story-boarding. Striking a balance between precision and convenience, our method utilises region masks and colour palettes to allow intuitive user control, steering clear of the meticulousness of manual colour assignments or the limitations of textual prompts. By strategically combining ControlNet and staged generation, incorporating Stable Diffusion v1.5, and leveraging BLIP-2 text prompts, our methodology facilitates faithful image generation and user-directed colourisation. Addressing challenges of local and global consistency, we employ inventive solutions such as an inversion scheme, guided sampling, and a self-attention mechanism with a scaling factor. The resulting tool is not only fast and training-free but also compatible with consumer-grade Nvidia RTX 4090 Super GPUs, making it a valuable asset for both creative professionals and enthusiasts in various fields. Project Page: \url{https://chaitron.github.io/SketchDeco/}
Authors: Bingqian Lin, Yunshuang Nie, Ziming Wei, Yi Zhu, Hang Xu, Shikui Ma, Jianzhuang Liu, Xiaodan Liang
Abstract: Vision-Language Navigation (VLN) requires the agent to follow language instructions to reach a target position. A key factor for successful navigation is to align the landmarks implied in the instruction with diverse visual observations. However, previous VLN agents fail to perform accurate modality alignment especially in unexplored scenes, since they learn from limited navigation data and lack sufficient open-world alignment knowledge. In this work, we propose a new VLN paradigm, called COrrectable LaNdmark DiScOvery via Large ModEls (CONSOLE). In CONSOLE, we cast VLN as an open-world sequential landmark discovery problem, by introducing a novel correctable landmark discovery scheme based on two large models ChatGPT and CLIP. Specifically, we use ChatGPT to provide rich open-world landmark cooccurrence commonsense, and conduct CLIP-driven landmark discovery based on these commonsense priors. To mitigate the noise in the priors due to the lack of visual constraints, we introduce a learnable cooccurrence scoring module, which corrects the importance of each cooccurrence according to actual observations for accurate landmark discovery. We further design an observation enhancement strategy for an elegant combination of our framework with different VLN agents, where we utilize the corrected landmark features to obtain enhanced observation features for action decision. Extensive experimental results on multiple popular VLN benchmarks (R2R, REVERIE, R4R, RxR) show the significant superiority of CONSOLE over strong baselines. Especially, our CONSOLE establishes the new state-of-the-art results on R2R and R4R in unseen scenarios. Code is available at https://github.com/expectorlin/CONSOLE.
Authors: Sifan Zhou, Zhihang Yuan, Dawei Yang, Xubin Wen, Xing Hu, Yuguang Shi, Ziyu Zhao, Xiaobo Lu
Abstract: Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead, making them suitable for onboard deployment and quantization. However, existing pillar-based detectors still suffer from information loss along height dimension and large numerical distribution difference during pillar feature encoding (PFE), which severely limits their performance and quantization potential. To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance. Motivated by this observation, we propose a height-aware pillar feature encoder named PillarHist. Specifically, PillarHist statistics the discrete distribution of points at different heights within one pillar. This simple yet effective design greatly preserves the information along the height dimension while significantly reducing the computation overhead of the PFE. Meanwhile, PillarHist also constrains the arithmetic distribution of PFE input to a stable range, making it quantization-friendly. Notably, PillarHist operates exclusively within the PFE stage to enhance performance, enabling seamless integration into existing pillar-based methods without introducing complex operations. Extensive experiments show the effectiveness of PillarHist in terms of both efficiency and performance.
Authors: Hanlong Li, Pei Wang, Yuhan Wu, Jing Ren, Yuhang Gao, Lingyun Zhang, Mingtai Zhang, Wenxin Chen
Abstract: Wood-leaf classification is an essential and fundamental prerequisite in the analysis and estimation of forest attributes from terrestrial laser scanning (TLS) point clouds,including critical measurements such as diameter at breast height(DBH),above-ground biomass(AGB),wood volume.To address this,we introduce the Wood-Leaf Classification Network(WLC-Net),a deep learning model derived from PointNet++,designed to differentiate between wood and leaf points within tree point clouds.WLC-Net enhances classification accuracy,completeness,and speed by incorporating linearity as an inherent feature,refining the input-output framework,and optimizing the centroid sampling technique.WLC-Net was trained and assessed using three distinct tree species datasets,comprising a total of 102 individual tree point clouds:21 Chinese ash trees,21 willow trees,and 60 tropical trees.For comparative evaluation,five alternative methods,including PointNet++,DGCNN,Krishna Moorthy's method,LeWoS, and Sun's method,were also applied to these datasets.The classification accuracy of all six methods was quantified using three metrics:overall accuracy(OA),mean Intersection over Union(mIoU),and F1-score.Across all three datasets,WLC-Net demonstrated superior performance, achieving OA scores of 0.9778, 0.9712, and 0.9508;mIoU scores of 0.9761, 0.9693,and 0.9141;and F1-scores of 0.8628, 0.7938,and 0.9019,respectively.The time costs of WLC-Net were also recorded to evaluate the efficiency.The average processing time was 102.74s per million points for WLC-Net.In terms of visual inspect,accuracy evaluation and efficiency evaluation,the results suggest that WLC-Net presents a promising approach for wood-leaf classification,distinguished by its high accuracy. In addition,WLC-Net also exhibits strong applicability across various tree point clouds and holds promise for further optimization.
Authors: Kun Huang, Fanglue Zhang, Neil Dodgson
Abstract: The presence of spherical distortion on the Equirectangular image is an acknowledged challenge in dense regression computer vision tasks, such as surface normal estimation. Recent advances in convolutional neural networks (CNNs) strive to mitigate spherical distortion but often fall short in capturing holistic structures effectively, primarily due to their fixed receptive field. On the other hand, vision transformers (ViTs) excel in establishing long-range dependencies through a global self-attention mechanism, yet they encounter limitations in preserving local details. We introduce \textit{PanoNormal}, a monocular surface normal estimation architecture designed for 360{\deg} images, which combines the strengths of CNNs and ViTs. Specifically, we employ a multi-level global self-attention scheme with the consideration of the spherical feature distribution, enhancing the comprehensive understanding of the scene. Our experimental results demonstrate that our approach achieves state-of-the-art performance across multiple popular 360{\deg} monocular datasets. The code and models will be released.
Authors: Jiachen Li, Weixi Feng, Tsu-Jui Fu, Xinyi Wang, Sugato Basu, Wenhu Chen, William Yang Wang
Abstract: Diffusion-based text-to-video (T2V) models have achieved significant success but continue to be hampered by the slow sampling speed of their iterative sampling processes. To address the challenge, consistency models have been proposed to facilitate fast inference, albeit at the cost of sample quality. In this work, we aim to break the quality bottleneck of a video consistency model (VCM) to achieve $\textbf{both fast and high-quality video generation}$. We introduce T2V-Turbo, which integrates feedback from a mixture of differentiable reward models into the consistency distillation (CD) process of a pre-trained T2V model. Notably, we directly optimize rewards associated with single-step generations that arise naturally from computing the CD loss, effectively bypassing the memory constraints imposed by backpropagating gradients through an iterative sampling process. Remarkably, the 4-step generations from our T2V-Turbo achieve the highest total score on VBench, even surpassing Gen-2 and Pika. We further conduct human evaluations to corroborate the results, validating that the 4-step generations from our T2V-Turbo are preferred over the 50-step DDIM samples from their teacher models, representing more than a tenfold acceleration while improving video generation quality.
Authors: Jordi Armengol-Estap\'e, Vincent Michalski, Ramnath Kumar, Pierre-Luc St-Charles, Doina Precup, Samira Ebrahimi Kahou
Abstract: Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross-modal learning can improve representations for few-shot classification. More specifically, language is a rich modality that can be used to guide visual learning. In this work, we experiment with a multi-modal architecture for few-shot learning that consists of three components: a classifier, an auxiliary network, and a bridge network. While the classifier performs the main classification task, the auxiliary network learns to predict language representations from the same input, and the bridge network transforms high-level features of the auxiliary network into modulation parameters for layers of the few-shot classifier using conditional batch normalization. The bridge should encourage a form of lightweight semantic alignment between language and vision which could be useful for the classifier. However, after evaluating the proposed approach on two popular few-shot classification benchmarks we find that a) the improvements do not reproduce across benchmarks, and b) when they do, the improvements are due to the additional compute and parameters introduced by the bridge network. We contribute insights and recommendations for future work in multi-modal meta-learning, especially when using language representations.
Authors: Jiyoon Myung, Jihyeon Park
Abstract: This paper examines the limitations of advanced text-to-image models in accurately rendering unconventional concepts which are scarcely represented or absent in their training datasets. We identify how these limitations not only confine the creative potential of these models but also pose risks of reinforcing stereotypes. To address these challenges, we introduce the Inpaint Biases framework, which employs user-defined masks and inpainting techniques to enhance the accuracy of image generation, particularly for novel or inaccurately rendered objects. Through experimental validation, we demonstrate how this framework significantly improves the fidelity of generated images to the user's intent, thereby expanding the models' creative capabilities and mitigating the risk of perpetuating biases. Our study contributes to the advancement of text-to-image models as unbiased, versatile tools for creative expression.
Authors: Xinji Mai, Haoran Wang, Zeng Tao, Junxiong Lin, Shaoqi Yan, Yan Wang, Jing Liu, Jiawen Yu, Xuan Tong, Yating Li, Wenqiang Zhang
Abstract: Dynamic Facial Expression Recognition (DFER) is crucial for affective computing but often overlooks the impact of scene context. We have identified a significant issue in current DFER tasks: human annotators typically integrate emotions from various angles, including environmental cues and body language, whereas existing DFER methods tend to consider the scene as noise that needs to be filtered out, focusing solely on facial information. We refer to this as the Rigid Cognitive Problem. The Rigid Cognitive Problem can lead to discrepancies between the cognition of annotators and models in some samples. To align more closely with the human cognitive paradigm of emotions, we propose an Overall Understanding of the Scene DFER method (OUS). OUS effectively integrates scene and facial features, combining scene-specific emotional knowledge for DFER. Extensive experiments on the two largest datasets in the DFER field, DFEW and FERV39k, demonstrate that OUS significantly outperforms existing methods. By analyzing the Rigid Cognitive Problem, OUS successfully understands the complex relationship between scene context and emotional expression, closely aligning with human emotional understanding in real-world scenarios.
Authors: Futa Waseda, Antonio Tejero-de-Pablos
Abstract: Recent studies have revealed that vision-language (VL) models are vulnerable to adversarial attacks for image-text retrieval (ITR). However, existing defense strategies for VL models primarily focus on zero-shot image classification, which do not consider the simultaneous manipulation of image and text, as well as the inherent many-to-many (N:N) nature of ITR, where a single image can be described in numerous ways, and vice versa. To this end, this paper studies defense strategies against adversarial attacks on VL models for ITR for the first time. Particularly, we focus on how to leverage the N:N relationship in ITR to enhance adversarial robustness. We found that, although adversarial training easily overfits to specific one-to-one (1:1) image-text pairs in the train data, diverse augmentation techniques to create one-to-many (1:N) / many-to-one (N:1) image-text pairs can significantly improve adversarial robustness in VL models. Additionally, we show that the alignment of the augmented image-text pairs is crucial for the effectiveness of the defense strategy, and that inappropriate augmentations can even degrade the model's performance. Based on these findings, we propose a novel defense strategy that leverages the N:N relationship in ITR, which effectively generates diverse yet highly-aligned N:N pairs using basic augmentations and generative model-based augmentations. This work provides a novel perspective on defending against adversarial attacks in VL tasks and opens up new research directions for future work.
Authors: Mingrui Ma, Yu Yang
Abstract: Medical image registration is an essential topic in medical image analysis. In this paper, we propose a method for medical image registration using a pretrained large language model. We find that using the pretrained large language model to encode deep features of the medical images in the registration model can effectively improve image registration accuracy, indicating the great potential of the large language model in medical image registration tasks. We use dual encoders to perform deep feature extraction on image pairs and then input the features into the pretrained large language model. To adapt the large language model to our registration task, the weights of the large language model are frozen in the registration model, and an adapter is utilized to fine-tune the large language model, which aims at (a) mapping the visual tokens to the language space before the large language model computing, (b) project the modeled language tokens output from the large language model to the visual space. Our method combines output features from the fine-tuned large language model with the features output from each encoder layer to gradually generate the deformation fields required for registration in the decoder. To demonstrate the effectiveness of the large prediction model in registration tasks, we conducted experiments on knee and brain MRI and achieved state-of-the-art results.
Authors: Zhaoliang Zhang, Tianchen Song, Yongjae Lee, Li Yang, Cheng Peng, Rama Chellappa, Deliang Fan
Abstract: Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a point-based scene representation, 3DGS potentially generates a large number of Gaussians to fit the scene, leading to high memory usage. Improvements that have been proposed require either an empirical and preset pruning ratio or importance score threshold to prune the point cloud. Such hyperparamter requires multiple rounds of training to optimize and achieve the maximum pruning ratio, while maintaining the rendering quality for each scene. In this work, we propose learning-to-prune 3DGS (LP-3DGS), where a trainable binary mask is applied to the importance score that can find optimal pruning ratio automatically. Instead of using the traditional straight-through estimator (STE) method to approximate the binary mask gradient, we redesign the masking function to leverage the Gumbel-Sigmoid method, making it differentiable and compatible with the existing training process of 3DGS. Extensive experiments have shown that LP-3DGS consistently produces a good balance that is both efficient and high quality.
Authors: Zhangkai Ni, Yue Liu, Keyan Ding, Wenhan Yang, Hanli Wang, Shiqi Wang
Abstract: Deep learning-based methods have significantly influenced the blind image quality assessment (BIQA) field, however, these methods often require training using large amounts of human rating data. In contrast, traditional knowledge-based methods are cost-effective for training but face challenges in effectively extracting features aligned with human visual perception. To bridge these gaps, we propose integrating deep features from pre-trained visual models with a statistical analysis model into a Multi-scale Deep Feature Statistics (MDFS) model for achieving opinion-unaware BIQA (OU-BIQA), thereby eliminating the reliance on human rating data and significantly improving training efficiency. Specifically, we extract patch-wise multi-scale features from pre-trained vision models, which are subsequently fitted into a multivariate Gaussian (MVG) model. The final quality score is determined by quantifying the distance between the MVG model derived from the test image and the benchmark MVG model derived from the high-quality image set. A comprehensive series of experiments conducted on various datasets show that our proposed model exhibits superior consistency with human visual perception compared to state-of-the-art BIQA models. Furthermore, it shows improved generalizability across diverse target-specific BIQA tasks. Our code is available at: https://github.com/eezkni/MDFS
Authors: Zhenhua Zhao, Ji Chen, Zhicheng Lin, Haojiang Ying
Abstract: Whether face processing depends on unique, domain-specific neurocognitive mechanisms or domain-general object recognition mechanisms has long been debated. Directly testing these competing hypotheses in humans has proven challenging due to extensive exposure to both faces and objects. Here, we systematically test these hypotheses by capitalizing on recent progress in convolutional neural networks (CNNs) that can be trained without face exposure (i.e., pre-trained weights). Domain-general mechanism accounts posit that face processing can emerge from a neural network without specialized pre-training on faces. Consequently, we trained CNNs solely on objects and tested their ability to recognize and represent faces as well as objects that look like faces (face pareidolia stimuli).... Due to the character limits, for more details see in attached pdf
Authors: Zhenbei Wu, Qiang Wang, Jie Yang
Abstract: The scarcity of free-hand sketch presents a challenging problem. Despite the emergence of some large-scale sketch datasets, these datasets primarily consist of sketches at the single-object level. There continues to be a lack of large-scale paired datasets for scene sketches. In this paper, we propose a self-supervised method for scene sketch generation that does not rely on any existing scene sketch, enabling the transformation of single-object sketches into scene sketches. To accomplish this, we introduce a method for vector sketch captioning and sketch semantic expansion. Additionally, we design a sketch generation network that incorporates a fusion of multi-modal perceptual constraints, suitable for application in zero-shot image-to-sketch downstream task, demonstrating state-of-the-art performance through experimental validation. Finally, leveraging our proposed sketch-to-sketch generation method, we contribute a large-scale dataset centered around scene sketches, comprising highly semantically consistent "text-sketch-image" triplets. Our research confirms that this dataset can significantly enhance the capabilities of existing models in sketch-based image retrieval and sketch-controlled image synthesis tasks. We will make our dataset and code publicly available.
Authors: Xuan-Bac Nguyen, Hojin Jang, Xin Li, Samee U. Khan, Pawan Sinha, Khoa Luu
Abstract: The human brain is a highly efficient processing unit, and understanding how it works can inspire new algorithms and architectures in machine learning. In this work, we introduce a novel framework named Brain Activation Network (BRACTIVE), a transformer-based approach to studying the human visual brain. The main objective of BRACTIVE is to align the visual features of subjects with corresponding brain representations via fMRI signals. It allows us to identify the brain's Regions of Interest (ROI) of the subjects. Unlike previous brain research methods, which can only identify ROIs for one subject at a time and are limited by the number of subjects, BRACTIVE automatically extends this identification to multiple subjects and ROIs. Our experiments demonstrate that BRACTIVE effectively identifies person-specific regions of interest, such as face and body-selective areas, aligning with neuroscience findings and indicating potential applicability to various object categories. More importantly, we found that leveraging human visual brain activity to guide deep neural networks enhances performance across various benchmarks. It encourages the potential of BRACTIVE in both neuroscience and machine intelligence studies.
Authors: Jingjing Xie, Yuxin Zhang, Mingbao Lin, Zhihang Lin, Liujuan Cao, Rongrong Ji
Abstract: Post-training Sparsity (PTS) is a recently emerged avenue that chases efficient network sparsity with limited data in need. Existing PTS methods, however, undergo significant performance degradation compared with traditional methods that retrain the sparse networks via the whole dataset, especially at high sparsity ratios. In this paper, we attempt to reconcile this disparity by transposing three cardinal factors that profoundly alter the performance of conventional sparsity into the context of PTS. Our endeavors particularly comprise (1) A base-decayed sparsity objective that promotes efficient knowledge transferring from dense network to the sparse counterpart. (2) A reducing-regrowing search algorithm designed to ascertain the optimal sparsity distribution while circumventing overfitting to the small calibration set in PTS. (3) The employment of dynamic sparse training predicated on the preceding aspects, aimed at comprehensively optimizing the sparsity structure while ensuring training stability. Our proposed framework, termed UniPTS, is validated to be much superior to existing PTS methods across extensive benchmarks. As an illustration, it amplifies the performance of POT, a recently proposed recipe, from 3.9% to 68.6% when pruning ResNet-50 at 90% sparsity ratio on ImageNet. We release the code of our paper at https://github.com/xjjxmu/UniPTS.
Authors: Ziqi Ren, Jie Li, Xuetong Xue, Xin Li, Fan Yang, Zhicheng Jiao, Xinbo Gao
Abstract: Deciphering the human visual experience through brain activities captured by fMRI represents a compelling and cutting-edge challenge in the field of neuroscience research. Compared to merely predicting the viewed image itself, decoding brain activity into meaningful captions provides a higher-level interpretation and summarization of visual information, which naturally enhances the application flexibility in real-world situations. In this work, we introduce MindSemantix, a novel multi-modal framework that enables LLMs to comprehend visually-evoked semantic content in brain activity. Our MindSemantix explores a more ideal brain captioning paradigm by weaving LLMs into brain activity analysis, crafting a seamless, end-to-end Brain-Language Model. To effectively capture semantic information from brain responses, we propose Brain-Text Transformer, utilizing a Brain Q-Former as its core architecture. It integrates a pre-trained brain encoder with a frozen LLM to achieve multi-modal alignment of brain-vision-language and establish a robust brain-language correspondence. To enhance the generalizability of neural representations, we pre-train our brain encoder on a large-scale, cross-subject fMRI dataset using self-supervised learning techniques. MindSemantix provides more feasibility to downstream brain decoding tasks such as stimulus reconstruction. Conditioned by MindSemantix captioning, our framework facilitates this process by integrating with advanced generative models like Stable Diffusion and excels in understanding brain visual perception. MindSemantix generates high-quality captions that are deeply rooted in the visual and semantic information derived from brain activity. This approach has demonstrated substantial quantitative improvements over prior art. Our code will be released.
Authors: Yasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang, Feng Gao, Ying Nian Wu, Oscar Leong
Abstract: Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the instantaneous change-of-variables formula, one can directly compute image likelihoods from a learned flow, making them enticing candidates as priors for downstream tasks such as inverse problems. In particular, a natural approach would be to incorporate such image probabilities in a maximum-a-posteriori (MAP) estimation problem. A major obstacle, however, lies in the slow computation of the log-likelihood, as it requires backpropagating through an ODE solver, which can be prohibitively slow for high-dimensional problems. In this work, we propose an iterative algorithm to approximate the MAP estimator efficiently to solve a variety of linear inverse problems. Our algorithm is mathematically justified by the observation that the MAP objective can be approximated by a sum of $N$ ``local MAP'' objectives, where $N$ is the number of function evaluations. By leveraging Tweedie's formula, we show that we can perform gradient steps to sequentially optimize these objectives. We validate our approach for various linear inverse problems, such as super-resolution, deblurring, inpainting, and compressed sensing, and demonstrate that we can outperform other methods based on flow matching.
Authors: Simranjit Singh, Georgios Pavlakos, Dimitrios Stamoulis
Abstract: As interest in "reformulating" the 3D Visual Question Answering (VQA) problem in the context of foundation models grows, it is imperative to assess how these new paradigms influence existing closed-vocabulary datasets. In this case study, we evaluate the zero-shot performance of foundational models (GPT-4 Vision and GPT-4) on well-established 3D VQA benchmarks, namely 3D-VQA and ScanQA. We provide an investigation to contextualize the performance of GPT-based agents relative to traditional modeling approaches. We find that GPT-based agents without any fine-tuning perform on par with the closed vocabulary approaches. Our findings corroborate recent results that "blind" models establish a surprisingly strong baseline in closed-vocabulary settings. We demonstrate that agents benefit significantly from scene-specific vocabulary via in-context textual grounding. By presenting a preliminary comparison with previous baselines, we hope to inform the community's ongoing efforts to refine multi-modal 3D benchmarks.
Authors: Gu\'enol\'e Fiche, Simon Leglaive, Xavier Alameda-Pineda, Francesc Moreno-Noguer
Abstract: Human Mesh Recovery (HMR) from a single RGB image is a highly ambiguous problem, as similar 2D projections can correspond to multiple 3D interpretations. Nevertheless, most HMR methods overlook this ambiguity and make a single prediction without accounting for the associated uncertainty. A few approaches generate a distribution of human meshes, enabling the sampling of multiple predictions; however, none of them is competitive with the latest single-output model when making a single prediction. This work proposes a new approach based on masked generative modeling. By tokenizing the human pose and shape, we formulate the HMR task as generating a sequence of discrete tokens conditioned on an input image. We introduce MEGA, a MaskEd Generative Autoencoder trained to recover human meshes from images and partial human mesh token sequences. Given an image, our flexible generation scheme allows us to predict a single human mesh in deterministic mode or to generate multiple human meshes in stochastic mode. MEGA enables us to propose multiple outputs and to evaluate the uncertainty of the predictions. Experiments on in-the-wild benchmarks show that MEGA achieves state-of-the-art performance in deterministic and stochastic modes, outperforming single-output and multi-output approaches.
Authors: Zelin Peng, Zhengqin Xu, Zhilin Zeng, Yaoming Wang, Lingxi Xie, Qi Tian, Wei Shen
Abstract: Open-vocabulary semantic segmentation seeks to label each pixel in an image with arbitrary text descriptions. Vision-language foundation models, especially CLIP, have recently emerged as powerful tools for acquiring open-vocabulary capabilities. However, fine-tuning CLIP to equip it with pixel-level prediction ability often suffers three issues: 1) high computational cost, 2) misalignment between the two inherent modalities of CLIP, and 3) degraded generalization ability on unseen categories. To address these issues, we propose H-CLIP a symmetrical parameter-efficient fine-tuning (PEFT) strategy conducted in hyperspherical space for both of the two CLIP modalities. Specifically, the PEFT strategy is achieved by a series of efficient block-diagonal learnable transformation matrices and a dual cross-relation communication module among all learnable matrices. Since the PEFT strategy is conducted symmetrically to the two CLIP modalities, the misalignment between them is mitigated. Furthermore, we apply an additional constraint to PEFT on the CLIP text encoder according to the hyperspherical energy principle, i.e., minimizing hyperspherical energy during fine-tuning preserves the intrinsic structure of the original parameter space, to prevent the destruction of the generalization ability offered by the CLIP text encoder. Extensive evaluations across various benchmarks show that H-CLIP achieves new SOTA open-vocabulary semantic segmentation results while only requiring updating approximately 4% of the total parameters of CLIP.
Authors: Zhiyuan You, Jinjin Gu, Zheyuan Li, Xin Cai, Kaiwen Zhu, Tianfan Xue, Chao Dong
Abstract: With the rapid advancement of Vision Language Models (VLMs), VLM-based Image Quality Assessment (IQA) seeks to describe image quality linguistically to align with human expression and capture the multifaceted nature of IQA tasks. However, current methods are still far from practical usage. First, prior works focus narrowly on specific sub-tasks or settings, which do not align with diverse real-world applications. Second, their performance is sub-optimal due to limitations in dataset coverage, scale, and quality. To overcome these challenges, we introduce Depicted image Quality Assessment in the Wild (DepictQA-Wild). Our method includes a multi-functional IQA task paradigm that encompasses both assessment and comparison tasks, brief and detailed responses, full-reference and non-reference scenarios. We introduce a ground-truth-informed dataset construction approach to enhance data quality, and scale up the dataset to 495K under the brief-detail joint framework. Consequently, we construct a comprehensive, large-scale, and high-quality dataset, named DQ-495K. We also retain image resolution during training to better handle resolution-related quality issues, and estimate a confidence score that is helpful to filter out low-quality responses. Experimental results demonstrate that DepictQA-Wild significantly outperforms traditional score-based methods, prior VLM-based IQA models, and proprietary GPT-4V in distortion identification, instant rating, and reasoning tasks. Our advantages are further confirmed by real-world applications including assessing the web-downloaded images and ranking model-processed images. Datasets and codes will be released in https://depictqa.github.io/depictqa-wild/.
Authors: Jiaze Wang, Hao Chen, Hongcan Xu, Jinpeng Li, Bowen Wang, Kun Shao, Furui Liu, Huaxi Chen, Guangyong Chen, Pheng-Ann Heng
Abstract: Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. However, traditional methods often struggle to capture the complex dynamics of meteorological systems, particularly in the presence of high-resolution data. In this paper, we propose the Spatial-Frequency Attention Network (SFANet), a novel deep learning framework designed to address these challenges and enhance the accuracy of spatiotemporal weather prediction. Drawing inspiration from the limitations of existing methodologies, we present an innovative approach that seamlessly integrates advanced token mixing and attention mechanisms. By leveraging both pooling and spatial mixing strategies, SFANet optimizes the processing of high-dimensional spatiotemporal sequences, preserving inter-component relational information and modeling extensive long-range relationships. To further enhance feature integration, we introduce a novel spatial-frequency attention module, enabling the model to capture intricate cross-modal correlations. Our extensive experimental evaluation on two distinct datasets, the Storm EVent ImageRy (SEVIR) and the Institute for Climate and Application Research (ICAR) - El Ni\~{n}o Southern Oscillation (ENSO) dataset, demonstrates the remarkable performance of SFANet. Notably, SFANet achieves substantial advancements over state-of-the-art methods, showcasing its proficiency in forecasting precipitation patterns and predicting El Ni\~{n}o events.
Authors: Nikhil Gosala, K\"ursat Petek, B Ravi Kiran, Senthil Yogamani, Paulo Drews-Jr, Wolfram Burgard, Abhinav Valada
Abstract: Semantic Bird's Eye View (BEV) maps offer a rich representation with strong occlusion reasoning for various decision making tasks in autonomous driving. However, most BEV mapping approaches employ a fully supervised learning paradigm that relies on large amounts of human-annotated BEV ground truth data. In this work, we address this limitation by proposing the first unsupervised representation learning approach to generate semantic BEV maps from a monocular frontal view (FV) image in a label-efficient manner. Our approach pretrains the network to independently reason about scene geometry and scene semantics using two disjoint neural pathways in an unsupervised manner and then finetunes it for the task of semantic BEV mapping using only a small fraction of labels in the BEV. We achieve label-free pretraining by exploiting spatial and temporal consistency of FV images to learn scene geometry while relying on a novel temporal masked autoencoder formulation to encode the scene representation. Extensive evaluations on the KITTI-360 and nuScenes datasets demonstrate that our approach performs on par with the existing state-of-the-art approaches while using only 1% of BEV labels and no additional labeled data.
Authors: Chuanbiao Song, Yan Hong, Jun Lan, Huijia Zhu, Weiqiang Wang, Jianfu Zhang
Abstract: This study reveals a cutting-edge re-balanced contrastive learning strategy aimed at strengthening face anti-spoofing capabilities within facial recognition systems, with a focus on countering the challenges posed by printed photos, and highly realistic silicone or latex masks. Leveraging the HySpeFAS dataset, which benefits from Snapshot Spectral Imaging technology to provide hyperspectral images, our approach harmonizes class-level contrastive learning with data resampling and an innovative real-face oriented reweighting technique. This method effectively mitigates dataset imbalances and reduces identity-related biases. Notably, our strategy achieved an unprecedented 0.0000\% Average Classification Error Rate (ACER) on the HySpeFAS dataset, ranking first at the Chalearn Snapshot Spectral Imaging Face Anti-spoofing Challenge on CVPR 2024.
Authors: Yiming Cui, Cheng Han, Dongfang Liu
Abstract: Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current models usually aggregate features from the neighboring frames to enhance the object representations for the task heads to generate more accurate predictions. Though getting better performance, these methods rely on the information from the future frames and suffer from high computational complexity. Meanwhile, the aggregation process is not reconfigurable during the inference time. These issues make most of the existing models infeasible for online applications. To solve these problems, we introduce a stepwise spatial global-local aggregation network. Our proposed models mainly contain three parts: 1). Multi-stage stepwise network gradually refines the predictions and object representations from the previous stage; 2). Spatial global-local aggregation fuses the local information from the neighboring frames and global semantics from the current frame to eliminate the feature degradation; 3). Dynamic aggregation strategy stops the aggregation process early based on the refinement results to remove redundancy and improve efficiency. Extensive experiments on the ImageNet VID benchmark validate the effectiveness and efficiency of our proposed models.
Authors: Ruipeng Zhang, Ziqing Fan, Jiangchao Yao, Ya Zhang, Yanfeng Wang
Abstract: This paper presents a Domain-Inspired Sharpness-Aware Minimization (DISAM) algorithm for optimization under domain shifts. It is motivated by the inconsistent convergence degree of SAM across different domains, which induces optimization bias towards certain domains and thus impairs the overall convergence. To address this issue, we consider the domain-level convergence consistency in the sharpness estimation to prevent the overwhelming (deficient) perturbations for less (well) optimized domains. Specifically, DISAM introduces the constraint of minimizing variance in the domain loss, which allows the elastic gradient calibration in perturbation generation: when one domain is optimized above the averaging level \textit{w.r.t.} loss, the gradient perturbation towards that domain will be weakened automatically, and vice versa. Under this mechanism, we theoretically show that DISAM can achieve faster overall convergence and improved generalization in principle when inconsistent convergence emerges. Extensive experiments on various domain generalization benchmarks show the superiority of DISAM over a range of state-of-the-art methods. Furthermore, we show the superior efficiency of DISAM in parameter-efficient fine-tuning combined with the pretraining models. The source code is released at https://github.com/MediaBrain-SJTU/DISAM.
Authors: Zijie Jiang, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Kenji Miki
Abstract: Enabling the synthesis of arbitrarily novel viewpoint images within a patient's stomach from pre-captured monocular gastroscopic images is a promising topic in stomach diagnosis. Typical methods to achieve this objective integrate traditional 3D reconstruction techniques, including structure-from-motion (SfM) and Poisson surface reconstruction. These methods produce explicit 3D representations, such as point clouds and meshes, thereby enabling the rendering of the images from novel viewpoints. However, the existence of low-texture and non-Lambertian regions within the stomach often results in noisy and incomplete reconstructions of point clouds and meshes, hindering the attainment of high-quality image rendering. In this paper, we apply the emerging technique of neural radiance fields (NeRF) to monocular gastroscopic data for synthesizing photo-realistic images for novel viewpoints. To address the performance degradation due to view sparsity in local regions of monocular gastroscopy, we incorporate geometry priors from a pre-reconstructed point cloud into the training of NeRF, which introduces a novel geometry-based loss to both pre-captured observed views and generated unobserved views. Compared to other recent NeRF methods, our approach showcases high-fidelity image renderings from novel viewpoints within the stomach both qualitatively and quantitatively.
Authors: Qizhou Chen, Qing Shao
Abstract: Convolutional Neural Networks (CNNs) have been widely employed for image Super-Resolution (SR) in recent years. Various techniques enhance SR performance by altering CNN structures or incorporating improved self-attention mechanisms. Interestingly, these advancements share a common trait. Instead of explicitly learning high-frequency details, they learn an implicit feature processing mode that utilizes weighted sums of a feature map's own elements for reconstruction, akin to convolution and non-local. In contrast, early dictionary-based approaches learn feature decompositions explicitly to match and rebuild Low-Resolution (LR) features. Building on this analysis, we introduce Trainable Feature Matching (TFM) to amalgamate this explicit feature learning into CNNs, augmenting their representation capabilities. Within TFM, trainable feature sets are integrated to explicitly learn features from training images through feature matching. Furthermore, we integrate non-local and channel attention into our proposed Trainable Feature Matching Attention Network (TFMAN) to further enhance SR performance. To alleviate the computational demands of non-local operations, we propose a streamlined variant called Same-size-divided Region-level Non-Local (SRNL). SRNL conducts non-local computations in parallel on blocks uniformly divided from the input feature map. The efficacy of TFM and SRNL is validated through ablation studies and module explorations. We employ a recurrent convolutional network as the backbone of our TFMAN to optimize parameter utilization. Comprehensive experiments on benchmark datasets demonstrate that TFMAN achieves superior results in most comparisons while using fewer parameters. The code is available at https://github.com/qizhou000/tfman.
Authors: Yiting Dong, Xiang He, Guobin Shen, Dongcheng Zhao, Yang Li, Yi Zeng
Abstract: Event data captured by Dynamic Vision Sensors (DVS) offers a unique approach to visual processing that differs from traditional video capture, showcasing its efficiency in dynamic and real-time scenarios. Despite advantages such as high temporal resolution and low energy consumption, the application of event data faces challenges due to limited dataset size and diversity. To address this, we developed EventZoom -- a data augmentation strategy specifically designed for event data. EventZoom employs a progressive temporal strategy that intelligently blends time and space to enhance the diversity and complexity of the data while maintaining its authenticity. This method aims to improve the quality of data for model training and enhance the adaptability and robustness of algorithms in handling complex dynamic scenes. We have experimentally validated EventZoom across various supervised learning frameworks, including supervised, semi-supervised, and unsupervised learning. Our results demonstrate that EventZoom consistently outperforms other data augmentation methods, confirming its effectiveness and applicability as a powerful event-based data augmentation tool in diverse learning settings.
Authors: Yuguang Yang, Runtang Guo, Sheng Wu, Yimi Wang, Linlin Yang, Bo Fan, Jilong Zhong, Juan Zhang, Baochang Zhang
Abstract: Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is a formidable challenge. Current Class Activation Map (CAM) methods highlight regions revealing the model's decision-making basis but lack clear saliency maps and detailed interpretability. To bridge this gap, we propose DecomCAM, a novel decomposition-and-integration method that distills shared patterns from channel activation maps. Utilizing singular value decomposition, DecomCAM decomposes class-discriminative activation maps into orthogonal sub-saliency maps (OSSMs), which are then integrated together based on their contribution to the target concept. Extensive experiments on six benchmarks reveal that DecomCAM not only excels in locating accuracy but also achieves an optimizing balance between interpretability and computational efficiency. Further analysis unveils that OSSMs correlate with discernible object components, facilitating a granular understanding of the model's reasoning. This positions DecomCAM as a potential tool for fine-grained interpretation of advanced deep learning models. The code is avaible at https://github.com/CapricornGuang/DecomCAM.
Authors: Junjie Wang, Guangjing Yang, Wentao Chen, Huahui Yi, Xiaohu Wu, Qicheng Lao
Abstract: In response to the challenges posed by the extensive parameter updates required for full fine-tuning of large-scale pre-trained models, parameter-efficient fine-tuning (PEFT) methods, exemplified by Low-Rank Adaptation (LoRA), have emerged. LoRA simplifies the fine-tuning process but may still struggle with a certain level of redundancy in low-rank matrices and limited effectiveness from merely increasing their rank. To address these issues, a natural idea is to enhance the independence and diversity of the learning process for the low-rank matrices. Therefore, we propose Masked LoRA Experts (MLAE), an innovative approach that applies the concept of masking to PEFT. Our method incorporates a cellular decomposition strategy that transforms a low-rank matrix into independent rank-1 submatrices, or ``experts'', thus enhancing independence. Additionally, we introduce a binary mask matrix that selectively activates these experts during training to promote more diverse and anisotropic learning, based on expert-level dropout strategies. Our investigations reveal that this selective activation not only enhances performance but also fosters a more diverse acquisition of knowledge with a marked decrease in parameter similarity among MLAE, significantly boosting the quality of the model while barely increasing the parameter count. Remarkably, MLAE achieves new SOTA performance with an average accuracy score of 78.8% on the VTAB-1k benchmark and 90.9% on the FGVC benchmark, demonstrating superior performance. Our code is available at https://github.com/jie040109/MLAE.
Authors: Abdul Aziz A. B, A. B Abdul Rahim
Abstract: This research presents a comprehensive assessment of pan-sharpening techniques for satellite imagery, focusing on the critical aspects of spectral fidelity and spatial enhancement. Motivated by the need for informed algorithm selection in remote sensing, A novel cascaded and structured evaluation framework has been proposed with a detailed comparative analysis of existing methodologies. The research findings underscore the intricate trade-offs between spectral accuracy of about 88\% with spatial resolution enhancement. The research sheds light on the practical implications of pan-sharpening and emphasizes the significance of both spectral and spatial aspects in remote sensing applications. Various pan-sharpening algorithms were systematically employed to provide a holistic view of their performance, contributing to a deeper understanding of their capabilities and limitations.
Authors: Yushu Li, Yongyi Su, Xulei Yang, Kui Jia, Xun Xu
Abstract: Existing test-time adaptation (TTA) approaches often adapt models with the unlabeled testing data stream. A recent attempt relaxed the assumption by introducing limited human annotation, referred to as Human-In-the-Loop Test-Time Adaptation (HILTTA) in this study. The focus of existing HILTTA lies on selecting the most informative samples to label, a.k.a. active learning. In this work, we are motivated by a pitfall of TTA, i.e. sensitive to hyper-parameters, and propose to approach HILTTA by synergizing active learning and model selection. Specifically, we first select samples for human annotation (active learning) and then use the labeled data to select optimal hyper-parameters (model selection). A sample selection strategy is tailored for choosing samples by considering the balance between active learning and model selection purposes. We demonstrate on 4 TTA datasets that the proposed HILTTA approach is compatible with off-the-shelf TTA methods which outperform the state-of-the-art HILTTA methods and stream-based active learning methods. Importantly, our proposed method can always prevent choosing the worst hyper-parameters on all off-the-shelf TTA methods. The source code will be released upon publication.
Authors: Miguel A. Ferrer, Abhijit Das, Moises Diaz, Aythami Morales, Cristina Carmona-Duarte, Umapada Pal
Abstract: Script identification plays a vital role in applications that involve handwriting and document analysis within a multi-script and multi-lingual environment. Moreover, it exhibits a profound connection with human cognition. This paper provides a new database for benchmarking script identification algorithms, which contains both printed and handwritten documents collected from a wide variety of scripts, such as Arabic, Bengali (Bangla), Gujarati, Gurmukhi, Devanagari, Japanese, Kannada, Malayalam, Oriya, Roman, Tamil, Telugu, and Thai. The dataset consists of 1,135 documents scanned from local newspaper and handwritten letters as well as notes from different native writers. Further, these documents are segmented into lines and words, comprising a total of 13,979 and 86,655 lines and words, respectively, in the dataset. Easy-to-go benchmarks are proposed with handcrafted and deep learning methods. The benchmark includes results at the document, line, and word levels with printed and handwritten documents. Results of script identification independent of the document/line/word level and independent of the printed/handwritten letters are also given. The new multi-lingual database is expected to create new script identifiers, present various challenges, including identifying handwritten and printed samples and serve as a foundation for future research in script identification based on the reported results of the three benchmarks.
Authors: Junjie Fei, Mahmoud Ahmed, Jian Ding, Eslam Mohamed Bakr, Mohamed Elhoseiny
Abstract: While 3D MLLMs have achieved significant progress, they are restricted to object and scene understanding and struggle to understand 3D spatial structures at the part level. In this paper, we introduce Kestrel, representing a novel approach that empowers 3D MLLMs with part-aware understanding, enabling better interpretation and segmentation grounding of 3D objects at the part level. Despite its significance, the current landscape lacks tasks and datasets that endow and assess this capability. Therefore, we propose two novel tasks: (1) Part-Aware Point Grounding, the model is tasked with directly predicting a part-level segmentation mask based on user instructions, and (2) Part-Aware Point Grounded Captioning, the model provides a detailed caption that includes part-level descriptions and their corresponding masks. To support learning and evaluating for these tasks, we introduce 3DCoMPaT Grounded Instructions Dataset (3DCoMPaT-GRIN). 3DCoMPaT-GRIN Vanilla, comprising 789k part-aware point cloud-instruction-segmentation mask triplets, is used to evaluate MLLMs' ability of part-aware segmentation grounding. 3DCoMPaT-GRIN Grounded Caption, containing 107k part-aware point cloud-instruction-grounded caption triplets, assesses both MLLMs' part-aware language comprehension and segmentation grounding capabilities. Our introduced tasks, dataset, and Kestrel represent a preliminary effort to bridge the gap between human cognition and 3D MLLMs, i.e., the ability to perceive and engage with the environment at both global and part levels. Extensive experiments on the 3DCoMPaT-GRIN show that Kestrel can generate user-specified segmentation masks, a capability not present in any existing 3D MLLM. Kestrel thus established a benchmark for evaluating the part-aware language comprehension and segmentation grounding of 3D objects. Project page at https://feielysia.github.io/Kestrel.github.io/
Authors: Ho Chun Wu, Esther Hoi Shan Lau, Paul Yuen, Kevin Hung, John Kwok Tai Chui, Andrew Kwok Fai Lui
Abstract: Pedestrian trajectory modelling in an urban complex is challenging because pedestrians can have many possible destinations, such as shops, escalators, and attractions. Moreover, weather and time-of-day may affect pedestrian behavior. In this paper, a new weather-time-trajectory fusion network (WTTFNet) is proposed to improve the performance of baseline deep neural network architecture. By incorporating weather and time-of-day information as an embedding structure, a novel WTTFNet based on gate multimodal unit is used to fuse the multimodal information and deep representation of trajectories. A joint loss function based on focal loss is used to co-optimize both the deep trajectory features and final classifier, which helps to improve the accuracy in predicting the intended destination of pedestrians and hence the trajectories under possible scenarios of class imbalances. Experimental results using the Osaka Asia and Pacific Trade Center (ATC) dataset shows improved performance of the proposed approach over state-of-the-art algorithms by 23.67% increase in classification accuracy, 9.16% and 7.07% reduction of average and final displacement error. The proposed approach may serve as an attractive approach for improving existing baseline trajectory prediction models when they are applied to scenarios with influences of weather-time conditions. It can be employed in numerous applications such as pedestrian facility engineering, public space development and technology-driven retail.
Authors: Jinzhong Wang, Xuetao Tian, Shun Dai, Tao Zhuo, Haorui Zeng, Hongjuan Liu, Jiaqi Liu, Xiuwei Zhang, Yanning Zhang
Abstract: Multispectral object detection, utilizing both visible (RGB) and thermal infrared (T) modals, has garnered significant attention for its robust performance across diverse weather and lighting conditions. However, effectively exploiting the complementarity between RGB-T modals while maintaining efficiency remains a critical challenge. In this paper, a very simple Group Shuffled Multi-receptive Attention (GSMA) module is proposed to extract and combine multi-scale RGB and thermal features. Then, the extracted multi-modal features are directly integrated with a multi-level path aggregation neck, which significantly improves the fusion effect and efficiency. Meanwhile, multi-modal object detection often adopts union annotations for both modals. This kind of supervision is not sufficient and unfair, since objects observed in one modal may not be seen in the other modal. To solve this issue, Multi-modal Supervision (MS) is proposed to sufficiently supervise RGB-T object detection. Comprehensive experiments on two challenging benchmarks, KAIST and DroneVehicle, demonstrate the proposed model achieves the state-of-the-art accuracy while maintaining competitive efficiency.
Authors: Rui Yang, Shuang Wang, Yingping Han, Yuanheng Li, Dong Zhao, Dou Quan, Yanhe Guo, Licheng Jiao
Abstract: Remote Sensing Image-Text Retrieval (RSITR) is pivotal for knowledge services and data mining in the remote sensing (RS) domain. Considering the multi-scale representations in image content and text vocabulary can enable the models to learn richer representations and enhance retrieval. Current multi-scale RSITR approaches typically align multi-scale fused image features with text features, but overlook aligning image-text pairs at distinct scales separately. This oversight restricts their ability to learn joint representations suitable for effective retrieval. We introduce a novel Multi-Scale Alignment (MSA) method to overcome this limitation. Our method comprises three key innovations: (1) Multi-scale Cross-Modal Alignment Transformer (MSCMAT), which computes cross-attention between single-scale image features and localized text features, integrating global textual context to derive a matching score matrix within a mini-batch, (2) a multi-scale cross-modal semantic alignment loss that enforces semantic alignment across scales, and (3) a cross-scale multi-modal semantic consistency loss that uses the matching matrix from the largest scale to guide alignment at smaller scales. We evaluated our method across multiple datasets, demonstrating its efficacy with various visual backbones and establishing its superiority over existing state-of-the-art methods. The GitHub URL for our project is: https://github.com/yr666666/MSA
Authors: Jiaqi Xu, Xinyi Zou, Kunzhe Huang, Yunkuo Chen, Bo Liu, MengLi Cheng, Xing Shi, Jun Huang
Abstract: This paper presents EasyAnimate, an advanced method for video generation that leverages the power of transformer architecture for high-performance outcomes. We have expanded the DiT framework originally designed for 2D image synthesis to accommodate the complexities of 3D video generation by incorporating a motion module block. It is used to capture temporal dynamics, thereby ensuring the production of consistent frames and seamless motion transitions. The motion module can be adapted to various DiT baseline methods to generate video with different styles. It can also generate videos with different frame rates and resolutions during both training and inference phases, suitable for both images and videos. Moreover, we introduce slice VAE, a novel approach to condense the temporal axis, facilitating the generation of long duration videos. Currently, EasyAnimate exhibits the proficiency to generate videos with 144 frames. We provide a holistic ecosystem for video production based on DiT, encompassing aspects such as data pre-processing, VAE training, DiT models training (both the baseline model and LoRA model), and end-to-end video inference. Code is available at: https://github.com/aigc-apps/EasyAnimate. We are continuously working to enhance the performance of our method.
Authors: Xuelin Qian, Ruiqi Wu, Gong Cheng, Junwei Han
Abstract: Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different times and locations, adapting to new identities while preserving knowledge of previous ones. Existing approaches, either rehearsal-free or rehearsal-based, still suffer from the problem of catastrophic forgetting since they try to cram diverse knowledge into one fixed model. To overcome this limitation, we introduce a novel framework AdalReID, that adopts knowledge adapters and a parameter-free auto-selection mechanism for lifelong learning. Concretely, we incrementally build distinct adapters to learn domain-specific knowledge at each step, which can effectively learn and preserve knowledge across different datasets. Meanwhile, the proposed auto-selection strategy adaptively calculates the knowledge similarity between the input set and the adapters. On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model. Extensive experiments are conducted to demonstrate the superiority of our AdalReID, which significantly outperforms SOTAs by about 10$\sim$20\% mAP on both seen and unseen domains.
Authors: Jihao Liu, Jinliang Zheng, Boxiao Liu, Yu Liu, Hongsheng Li
Abstract: Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on noisy web-scale datasets is computationally demanding. On the other hand, mask-then-predict pre-training approaches, like Masked Image Modeling (MIM), offer efficient self-supervised learning for single-modal representations. This paper introduces Unmasked Token Alignment (UTA), a method that leverages existing CLIP models to further enhance its vision-language representations. UTA trains a Vision Transformer (ViT) by aligning unmasked visual tokens to the corresponding image tokens from a frozen CLIP vision encoder, which automatically aligns the ViT model with the CLIP text encoder. The pre-trained ViT can be directly applied for zero-shot evaluation even without training on image-text pairs. Compared to MIM approaches, UTA does not suffer from training-finetuning inconsistency and is much more training-efficient by avoiding using the extra [MASK] tokens. Extensive experimental results demonstrate that UTA can enhance CLIP models and outperform existing MIM methods on various uni- and multi-modal benchmarks. Code and models are available at https://github.com/jihaonew/UTA.
Authors: Shuai Yuan, Guancong Lin, Lixian Zhang, Runmin Dong, Jinxiao Zhang, Shuang Chen, Juepeng Zheng, Jie Wang, Haohuan Fu
Abstract: Fine urban change segmentation using multi-temporal remote sensing images is essential for understanding human-environment interactions. Despite advances in remote sensing data for urban monitoring, coarse-grained classification systems and the lack of continuous temporal observations hinder the application of deep learning to urban change analysis. To address this, we introduce FUSU, a multi-source, multi-temporal change segmentation dataset for fine-grained urban semantic understanding. FUSU features the most detailed land use classification system to date, with 17 classes and 30 billion pixels of annotations. It includes bi-temporal high-resolution satellite images with 20-50 cm ground sample distance and monthly optical and radar satellite time series, covering 847 km2 across five urban areas in China. The fine-grained pixel-wise annotations and high spatial-temporal resolution data provide a robust foundation for deep learning models to understand urbanization and land use changes. To fully leverage FUSU, we propose a unified time-series architecture for both change detection and segmentation and benchmark FUSU on various methods for several tasks. Dataset and code will be available at: https://github.com/yuanshuai0914/FUSU.
Authors: Dipam Goswami, Albin Soutif--Cormerais, Yuyang Liu, Sandesh Kamath, Bart{\l}omiej Twardowski, Joost van de Weijer
Abstract: Continual learning methods are known to suffer from catastrophic forgetting, a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore, to reduce potential drift in the feature extractor, existing exemplar-free methods are typically evaluated in settings where the first task is significantly larger than subsequent tasks. Their performance drops drastically in more challenging settings starting with a smaller first task. To address this problem of feature drift estimation for exemplar-free methods, we propose to adversarially perturb the current samples such that their embeddings are close to the old class prototypes in the old model embedding space. We then estimate the drift in the embedding space from the old to the new model using the perturbed images and compensate the prototypes accordingly. We exploit the fact that adversarial samples are transferable from the old to the new feature space in a continual learning setting. The generation of these images is simple and computationally cheap. We demonstrate in our experiments that the proposed approach better tracks the movement of prototypes in embedding space and outperforms existing methods on several standard continual learning benchmarks as well as on fine-grained datasets. Code is available at https://github.com/dipamgoswami/ADC.
Authors: Markus J. Buehler
Abstract: We present Cephalo, a series of multimodal vision large language models (V-LLMs) designed for materials science applications, integrating visual and linguistic data for enhanced understanding and interaction within human-AI and multi-agent AI frameworks. A key innovation of Cephalo is its advanced dataset generation method, which employs a sophisticated algorithm to accurately detect and separate images and their corresponding textual descriptions from PDF documents, such as scientific papers. The method includes a careful refinement of image-text pairs through integrated vision and language processing, ensuring high-quality, contextually relevant, and well reasoned training data. Cephalo is trained on integrated image and text data extracted from thousands of scientific papers and science-focused Wikipedia pages demonstrates can interpret complex visual scenes, generate precise language descriptions, and answer queries about images effectively. The combination of a vision encoder with an autoregressive transformer supports complex natural language understanding in an integrated model, which can be coupled with other generative methods to create an image-to-text-to-image or image-to-text-to-3D pipeline. To explore the development of larger models from smaller ones, we merge sets of layers that originate from different pre-trained source models. This hybrid approach allows us to leverage the domain-specific expertise and general conversational capabilities to harness the strengths of multiple models. We examine the models in diverse use cases that incorporate biological materials, fracture and engineering analysis, protein biophysics, and bio-inspired design based on insect behavior. Generative applications include bio-inspired designs, including pollen-inspired architected materials, as well as the synthesis of bio-inspired material microstructures from a photograph of a solar eclipse.
Authors: Hongyuan Dong, Jiawen Li, Bohong Wu, Jiacong Wang, Yuan Zhang, Haoyuan Guo
Abstract: Image captioning has long been regarded as a fundamental task in visual understanding. Recently, however, few large vision-language model (LVLM) research discusses model's image captioning performance because of the outdated short-caption benchmarks and unreliable evaluation metrics. In this work, we propose to benchmark detail image caption task by curating high-quality evaluation datasets annotated by human experts, GPT-4V and Gemini-1.5-Pro. We also design a more reliable caption evaluation metric called CAPTURE (CAPtion evaluation by exTracting and coUpling coRE information). CAPTURE extracts visual elements, e.g., objects, attributes and relations from captions, and then matches these elements through three stages, achieving the highest consistency with expert judgements over other rule-based or model-based caption metrics. The proposed benchmark and metric provide reliable evaluation for LVLM's detailed image captioning ability. Guided by this evaluation, we further explore to unleash LVLM's detail caption capabilities by synthesizing high-quality data through a five-stage data construction pipeline. Our pipeline only uses a given LVLM itself and other open-source tools, without any human or GPT-4V annotation in the loop. Experiments show that the proposed data construction strategy significantly improves model-generated detail caption data quality for LVLMs with leading performance, and the data quality can be further improved in a self-looping paradigm. All code and dataset will be publicly available at https://github.com/foundation-multimodal-models/CAPTURE.
URLs: https://github.com/foundation-multimodal-models/CAPTURE.
Authors: Zengqun Zhao, Yu Cao, Shaogang Gong, Ioannis Patras
Abstract: Current facial expression recognition (FER) models are often designed in a supervised learning manner thus are constrained by the lack of large-scale facial expression images with high-quality annotations. Consequently, these models often fail to generalize well, performing poorly on unseen images in training. Vision-language-based zero-shot models demonstrate a promising potential for addressing such challenges. However, these models lack task-specific knowledge therefore are not optimized for the nuances of recognizing facial expressions. To bridge this gap, this work proposes a novel method, Exp-CLIP, to enhance zero-shot FER by transferring the task knowledge from large language models (LLMs). Specifically, based on the pre-trained vision-language encoders, we incorporate a projection head designed to map the initial joint vision-language space into a space that captures representations of facial actions. To train this projection head for subsequent zero-shot predictions, we propose to align the projected visual representations with task-specific semantic meanings derived from the LLM encoder, and the text instruction-based strategy is employed to customize the LLM knowledge. Given unlabelled facial data and efficient training of the projection head, Exp-CLIP achieves superior zero-shot results to the CLIP models and several other large vision-language models (LVLMs) on seven in-the-wild FER datasets. The code and pre-trained models are available at \url{https://github.com/zengqunzhao/Exp-CLIP}.
Authors: Omar Moured, Shahid Ali Farooqui, Karin Muller, Sharifeh Fadaeijouybari, Thorsten Schwarz, Mohammed Javed, Rainer Stiefelhagen
Abstract: Alternative Texts (Alt-Text) for chart images are essential for making graphics accessible to people with blindness and visual impairments. Traditionally, Alt-Text is manually written by authors but often encounters issues such as oversimplification or complication. Recent trends have seen the use of AI for Alt-Text generation. However, existing models are susceptible to producing inaccurate or misleading information. We address this challenge by retrieving high-quality alt-texts from similar chart images, serving as a reference for the user when creating alt-texts. Our three contributions are as follows: (1) we introduce a new benchmark comprising 5,000 real images with semantically labeled high-quality Alt-Texts, collected from Human Computer Interaction venues. (2) We developed a deep learning-based model to rank and retrieve similar chart images that share the same visual and textual semantics. (3) We designed a user interface (UI) to facilitate the alt-text creation process. Our preliminary interviews and investigations highlight the usability of our UI. For the dataset and further details, please refer to our project page: https://moured.github.io/alt4blind/.
Authors: Omar Moured, Sara Alzalabny, Anas Osman, Thorsten Schwarz, Karin Muller, Rainer Stiefelhagen
Abstract: Visualizations, such as charts, are crucial for interpreting complex data. However, they are often provided as raster images, which are not compatible with assistive technologies for people with blindness and visual impairments, such as embossed papers or tactile displays. At the same time, creating accessible vector graphics requires a skilled sighted person and is time-intensive. In this work, we leverage advancements in the field of chart analysis to generate tactile charts in an end-to-end manner. Our three key contributions are as follows: (1) introducing the ChartFormer model trained to convert raster chart images into tactile-accessible SVGs, (2) training this model on the Chart2Tactile dataset, a synthetic chart dataset we created following accessibility standards, and (3) evaluating the effectiveness of our SVGs through a pilot user study with an refreshable two-dimensional tactile display. Our work is publicly available at https://github.com/nsothman/ChartFormer .
Authors: David Wilkening, Omar Moured, Thorsten Schwarz, Karin Muller, Rainer Stiefelhagen
Abstract: Exam documents are essential educational materials for exam preparation. However, they pose a significant academic barrier for blind and visually impaired students, as they are often created without accessibility considerations. Typically, these documents are incompatible with screen readers, contain excessive white space, and lack alternative text for visual elements. This situation frequently requires intervention by experienced sighted individuals to modify the format and content for accessibility. We propose ACCSAMS, a semi-automatic system designed to enhance the accessibility of exam documents. Our system offers three key contributions: (1) creating an accessible layout and removing unnecessary white space, (2) adding navigational structures, and (3) incorporating alternative text for visual elements that were previously missing. Additionally, we present the first multilingual manually annotated dataset, comprising 1,293 German and 900 English exam documents which could serve as a good training source for deep learning models.
Authors: Xintong Jiang, Yaxiong Wang, Mengjian Li, Yujiao Wu, Bingwen Hu, Xueming Qian
Abstract: Composed Image Retrieval (CIR) involves searching for target images based on an image-text pair query. While current methods treat this as a query-target matching problem, we argue that CIR triplets contain additional associations beyond this primary relation. In our paper, we identify two new relations within triplets, treating each triplet as a graph node. Firstly, we introduce the concept of text-bridged image alignment, where the query text serves as a bridge between the query image and the target image. We propose a hinge-based cross-attention mechanism to incorporate this relation into network learning. Secondly, we explore complementary text reasoning, considering CIR as a form of cross-modal retrieval where two images compose to reason about complementary text. To integrate these perspectives effectively, we design a twin attention-based compositor. By combining these complementary associations with the explicit query pair-target image relation, we establish a comprehensive set of constraints for CIR. Our framework, CaLa (Complementary Association Learning for Augmenting Composed Image Retrieval), leverages these insights. We evaluate CaLa on CIRR and FashionIQ benchmarks with multiple backbones, demonstrating its superiority in composed image retrieval.
Authors: Sabrina Cynthia Triess, Timo Leitritz, Christian Jauch
Abstract: With rising technologies, the protection of privacy-sensitive information is becoming increasingly important. In industry and production facilities, image or video recordings are beneficial for documentation, tracing production errors or coordinating workflows. Individuals in images or videos need to be anonymized. However, the anonymized data should be reusable for further applications. In this work, we apply the Deep Learning-based full-body anonymization framework DeepPrivacy2, which generates artificial identities, to industrial image and video data. We compare its performance with conventional anonymization techniques. Therefore, we consider the quality of identity generation, temporal consistency, and the applicability of pose estimation and action recognition.
Authors: Saurabh Pathak, Samridha Shrestha, Abdelrahman AlMahmoud
Abstract: Object detection forms a key component in Unmanned Aerial Vehicles (UAVs) for completing high-level tasks that depend on the awareness of objects on the ground from an aerial perspective. In that scenario, adversarial patch attacks on an onboard object detector can severely impair the performance of upstream tasks. This paper proposes a novel model-agnostic defense mechanism against the threat of adversarial patch attacks in the context of UAV-based object detection. We formulate adversarial patch defense as an occlusion removal task. The proposed defense method can neutralize adversarial patches located on objects of interest, without exposure to adversarial patches during training. Our lightweight single-stage defense approach allows us to maintain a model-agnostic nature, that once deployed does not require to be updated in response to changes in the object detection pipeline. The evaluations in digital and physical domains show the feasibility of our method for deployment in UAV object detection pipelines, by significantly decreasing the Attack Success Ratio without incurring significant processing costs. As a result, the proposed defense solution can improve the reliability of object detection for UAVs.
Authors: Laura Fieback (Volkswagen AG, TU Berlin), Jakob Spiegelberg (Volkswagen AG), Hanno Gottschalk (TU Berlin)
Abstract: Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon referred to as hallucinations, remain an unsolved problem with regard to the trustworthiness of LVLMs. To address this problem, recent works proposed to incorporate computationally costly Large (Vision) Language Models in order to detect hallucinations on a sentence- or subsentence-level. In this work, we introduce MetaToken, a lightweight binary classifier to detect hallucinations on the token-level at negligible cost. Based on a statistical analysis, we reveal key factors of hallucinations in LVLMs which have been overseen in previous works. MetaToken can be applied to any open-source LVLM without any knowledge about ground truth data providing a reliable detection of hallucinations. We evaluate our method on four state-of-the-art LVLMs demonstrating the effectiveness of our approach.
Authors: Hongen Liu, Yi Liu, Di Sun, Jiahao Wang, Gang Pan
Abstract: Video text spotting aims to simultaneously localize, recognize and track text instances in videos. To address the limited recognition capability of end-to-end methods, tracking the zero-shot results of state-of-the-art image text spotters directly can achieve impressive performance. However, owing to the domain gap between different datasets, these methods usually obtain limited tracking trajectories on extreme dataset. Fine-tuning transformer-based text spotters on specific datasets could yield performance enhancements, albeit at the expense of considerable training resources. In this paper, we propose a Language Collaboration and Glyph Perception Model, termed LOGO to enhance the performance of conventional text spotters through the integration of a synergy module. To achieve this goal, a language synergy classifier (LSC) is designed to explicitly discern text instances from background noise in the recognition stage. Specially, the language synergy classifier can output text content or background code based on the legibility of text regions, thus computing language scores. Subsequently, fusion scores are computed by taking the average of detection scores and language scores, and are utilized to re-score the detection results before tracking. By the re-scoring mechanism, the proposed LSC facilitates the detection of low-resolution text instances while filtering out text-like regions. Besides, the glyph supervision and visual position mixture module are proposed to enhance the recognition accuracy of noisy text regions, and acquire more discriminative tracking features, respectively. Extensive experiments on public benchmarks validate the effectiveness of the proposed method.
Authors: Justin Deschenaux, Igor Krawczuk, Grigorios Chrysos, Volkan Cevher
Abstract: Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs trained on strictly separate subsets of the data distribution with large gaps on the support of the latent factors. We show that such a model can effectively generate images in the unexplored, intermediate regions of the distribution. For instance, when trained on clearly smiling and non-smiling faces, we demonstrate a sampling procedure which can generate slightly smiling faces without reference images (zero-shot interpolation). We replicate these findings for other attributes as well as other datasets. $\href{https://github.com/jdeschena/ddpm-zero-shot-interpolation}{\text{Our code is available on GitHub.}}$
URLs: https://github.com/jdeschena/ddpm-zero-shot-interpolation
Authors: Weitian Zhang, Yichao Yan, Yunhui Liu, Xingdong Sheng, Xiaokang Yang
Abstract: This paper aims to introduce 3D Gaussian for efficient, expressive, and editable digital avatar generation. This task faces two major challenges: (1) The unstructured nature of 3D Gaussian makes it incompatible with current generation pipelines; (2) the expressive animation of 3D Gaussian in a generative setting that involves training with multiple subjects remains unexplored. In this paper, we propose a novel avatar generation method named $E^3$Gen, to effectively address these challenges. First, we propose a novel generative UV features plane representation that encodes unstructured 3D Gaussian onto a structured 2D UV space defined by the SMPL-X parametric model. This novel representation not only preserves the representation ability of the original 3D Gaussian but also introduces a shared structure among subjects to enable generative learning of the diffusion model. To tackle the second challenge, we propose a part-aware deformation module to achieve robust and accurate full-body expressive pose control. Extensive experiments demonstrate that our method achieves superior performance in avatar generation and enables expressive full-body pose control and editing.
Authors: Ziyang Wang, Shoubin Yu, Elias Stengel-Eskin, Jaehong Yoon, Feng Cheng, Gedas Bertasius, Mohit Bansal
Abstract: Video-language understanding tasks have focused on short video clips, often struggling with long-form video understanding tasks. Recently, many long video-language understanding approaches have leveraged the reasoning capabilities of Large Language Models (LLMs) to perform long video QA, transforming videos into densely sampled frame captions, and asking LLMs to respond to text queries over captions. However, the frames used for captioning are often redundant and contain irrelevant information, making dense sampling inefficient, and ignoring the fact that video QA requires varying levels of granularity, with some video segments being highly relevant to the question (needing more fine-grained detail) while others being less relevant. Thus, these LLM-based approaches are prone to missing information and operate on large numbers of irrelevant captions, lowering both performance and efficiency. To address these issues, we introduce VideoTree, a query-adaptive and hierarchical framework for long-video understanding with LLMs. VideoTree dynamically extracts query-related information from a video and builds a tree-based representation for LLM reasoning. First, VideoTree adaptively selects frames for captioning by iteratively clustering frames based on their visual features and scoring clusters using their relevance to the query. Second, it organizes visual clusters into a query-adaptive and hierarchical tree structure; the tree encodes varying levels of granularity, with higher resolution on relevant segments. Finally, VideoTree produces an answer by traversing the tree's keyframes and passing their captions to an LLM answerer. Our method improves both reasoning accuracy and efficiency compared to existing methods: VideoTree achieves a 7.0%, 2.2%, and 2.7% accuracy gain over baselines on the EgoSchema, NExT-QA, and IntentQA benchmarks, respectively, while reducing inference time by 40%.
Authors: Honglin Lin, Siyu Li, Guoshun Nan, Chaoyue Tang, Xueting Wang, Jingxin Xu, Rong Yankai, Zhili Zhou, Yutong Gao, Qimei Cui, Xiaofeng Tao
Abstract: Image retrieval from contextual descriptions (IRCD) aims to identify an image within a set of minimally contrastive candidates based on linguistically complex text. Despite the success of VLMs, they still significantly lag behind human performance in IRCD. The main challenges lie in aligning key contextual cues in two modalities, where these subtle cues are concealed in tiny areas of multiple contrastive images and within the complex linguistics of textual descriptions. This motivates us to propose ContextBLIP, a simple yet effective method that relies on a doubly contextual alignment scheme for challenging IRCD. Specifically, 1) our model comprises a multi-scale adapter, a matching loss, and a text-guided masking loss. The adapter learns to capture fine-grained visual cues. The two losses enable iterative supervision for the adapter, gradually highlighting the focal patches of a single image to the key textual cues. We term such a way as intra-contextual alignment. 2) Then, ContextBLIP further employs an inter-context encoder to learn dependencies among candidates, facilitating alignment between the text to multiple images. We term this step as inter-contextual alignment. Consequently, the nuanced cues concealed in each modality can be effectively aligned. Experiments on two benchmarks show the superiority of our method. We observe that ContextBLIP can yield comparable results with GPT-4V, despite involving about 7,500 times fewer parameters.
Authors: Ruchika Chavhan, Da Li, Timothy Hospedales
Abstract: While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating societal biases. Recently, the text-to-image generation community has begun addressing these concerns by editing or unlearning undesired concepts from pre-trained models. However, these methods often involve data-intensive and inefficient fine-tuning or utilize various forms of token remapping, rendering them susceptible to adversarial jailbreaks. In this paper, we present a simple and effective training-free approach, ConceptPrune, wherein we first identify critical regions within pre-trained models responsible for generating undesirable concepts, thereby facilitating straightforward concept unlearning via weight pruning. Experiments across a range of concepts including artistic styles, nudity, object erasure, and gender debiasing demonstrate that target concepts can be efficiently erased by pruning a tiny fraction, approximately 0.12% of total weights, enabling multi-concept erasure and robustness against various white-box and black-box adversarial attacks.
Authors: Hanchao Liu, Xiaohang Zhan, Shaoli Huang, Tai-Jiang Mu, Ying Shan
Abstract: Character animation in real-world scenarios necessitates a variety of constraints, such as trajectories, key-frames, interactions, etc. Existing methodologies typically treat single or a finite set of these constraint(s) as separate control tasks. They are often specialized, and the tasks they address are rarely extendable or customizable. We categorize these as solutions to the close-set motion control problem. In response to the complexity of practical motion control, we propose and attempt to solve the open-set motion control problem. This problem is characterized by an open and fully customizable set of motion control tasks. To address this, we introduce a new paradigm, programmable motion generation. In this paradigm, any given motion control task is broken down into a combination of atomic constraints. These constraints are then programmed into an error function that quantifies the degree to which a motion sequence adheres to them. We utilize a pre-trained motion generation model and optimize its latent code to minimize the error function of the generated motion. Consequently, the generated motion not only inherits the prior of the generative model but also satisfies the required constraints. Experiments show that we can generate high-quality motions when addressing a wide range of unseen tasks. These tasks encompass motion control by motion dynamics, geometric constraints, physical laws, interactions with scenes, objects or the character own body parts, etc. All of these are achieved in a unified approach, without the need for ad-hoc paired training data collection or specialized network designs. During the programming of novel tasks, we observed the emergence of new skills beyond those of the prior model. With the assistance of large language models, we also achieved automatic programming. We hope that this work will pave the way for the motion control of general AI agents.
Authors: Lei Li, Songyou Peng, Zehao Yu, Shaohui Liu, R\'emi Pautrat, Xiaochuan Yin, Marc Pollefeys
Abstract: Real-world objects and environments are predominantly composed of edge features, including straight lines and curves. Such edges are crucial elements for various applications, such as CAD modeling, surface meshing, lane mapping, etc. However, existing traditional methods only prioritize lines over curves for simplicity in geometric modeling. To this end, we introduce EMAP, a new method for learning 3D edge representations with a focus on both lines and curves. Our method implicitly encodes 3D edge distance and direction in Unsigned Distance Functions (UDF) from multi-view edge maps. On top of this neural representation, we propose an edge extraction algorithm that robustly abstracts parametric 3D edges from the inferred edge points and their directions. Comprehensive evaluations demonstrate that our method achieves better 3D edge reconstruction on multiple challenging datasets. We further show that our learned UDF field enhances neural surface reconstruction by capturing more details.
Authors: Thomas W. Mitchel, Michael Taylor, Vincent Sitzmann
Abstract: Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to a general-purpose latent space wherein encodings are related by isometries whenever their corresponding observations are geometrically related in world space. Specifically, we regularize the latent space such that maps between encodings preserve a learned inner product and commute with a learned functional operator, in the same manner as rigid-body transformations commute with the Laplacian. This approach forms an effective backbone for self-supervised representation learning, and we demonstrate that a simple off-the-shelf equivariant network operating in the pre-trained latent space can achieve results on par with meticulously-engineered, handcrafted networks designed to handle complex, nonlinear symmetries. Furthermore, isometric maps capture information about the respective transformations in world space, and we show that this allows us to regress camera poses directly from the coefficients of the maps between encodings of adjacent views of a scene.
Authors: Hanwei Zhu, Haoning Wu, Yixuan Li, Zicheng Zhang, Baoliang Chen, Lingyu Zhu, Yuming Fang, Guangtao Zhai, Weisi Lin, Shiqi Wang
Abstract: While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to continuous perceptual quality scores remains largely unexplored. To address this gap, we introduce Compare2Score-an all-around LMM-based no-reference IQA (NR-IQA) model, which is capable of producing qualitatively comparative responses and effectively translating these discrete comparative levels into a continuous quality score. Specifically, during training, we present to generate scaled-up comparative instructions by comparing images from the same IQA dataset, allowing for more flexible integration of diverse IQA datasets. Utilizing the established large-scale training corpus, we develop a human-like visual quality comparator. During inference, moving beyond binary choices, we propose a soft comparison method that calculates the likelihood of the test image being preferred over multiple predefined anchor images. The quality score is further optimized by maximum a posteriori estimation with the resulting probability matrix. Extensive experiments on nine IQA datasets validate that the Compare2Score effectively bridges text-defined comparative levels during training with converted single image quality score for inference, surpassing state-of-the-art IQA models across diverse scenarios. Moreover, we verify that the probability-matrix-based inference conversion not only improves the rating accuracy of Compare2Score but also zero-shot general-purpose LMMs, suggesting its intrinsic effectiveness.
Authors: Marco Introvigne, Andrea Ramazzina, Stefanie Walz, Dominik Scheuble, Mario Bijelic
Abstract: Current autonomous driving technologies are being rolled out in geo-fenced areas with well-defined operation conditions such as time of operation, area, weather conditions and road conditions. In this way, challenging conditions as adverse weather, slippery road or densely-populated city centers can be excluded. In order to lift the geo-fenced restriction and allow a more dynamic availability of autonomous driving functions, it is necessary for the vehicle to autonomously perform an environment condition assessment in real time to identify when the system cannot operate safely and either stop operation or require the resting passenger to take control. In particular, adverse-weather challenges are a fundamental limitation as sensor performance degenerates quickly, prohibiting the use of sensors such as cameras to locate and monitor road signs, pedestrians or other vehicles. To address this issue, we train a deep learning model to identify outdoor weather and dangerous road conditions, enabling a quick reaction to new situations and environments. We achieve this by introducing an improved taxonomy and label hierarchy for a state-of-the-art adverse-weather dataset, relabelling it with a novel semi-automated labeling pipeline. Using the novel proposed dataset and hierarchy, we train RECNet, a deep learning model for the classification of environment conditions from a single RGB frame. We outperform baseline models by relative 16% in F1- Score, while maintaining a real-time capable performance of 20 Hz.
Authors: Wenbo Hu, Zi-Yi Dou, Liunian Harold Li, Amita Kamath, Nanyun Peng, Kai-Wei Chang
Abstract: Large Vision-Language Models (LVLMs) typically encode an image into a fixed number of visual tokens (e.g., 576) and process these tokens with a language model. Despite their strong performance, LVLMs face challenges in adapting to varying computational constraints. This raises the question: can we achieve flexibility in the number of visual tokens to suit different tasks and computational resources? We answer this with an emphatic yes. Inspired by Matryoshka Representation Learning, we introduce the Matryoshka Query Transformer (MQT), capable of encoding an image into m visual tokens during inference, where m can be any number up to a predefined maximum. This is achieved by employing a query transformer with M latent query tokens to compress the visual embeddings. During each training step, we randomly select m <= M latent query tokens and train the model using only these first m tokens, discarding the rest. Combining MQT with LLaVA, we train a single model once, and flexibly and drastically reduce the number of inference-time visual tokens while maintaining similar or better performance compared to training independent models for each number of tokens. Our model, MQT-LLAVA, matches LLaVA-1.5 performance across 11 benchmarks using a maximum of 256 tokens instead of LLaVA's fixed 576. Reducing to 16 tokens (8x less TFLOPs) only sacrifices the performance by 2.4 points on MMBench. On certain tasks such as ScienceQA and MMMU, we can even go down to only 2 visual tokens with performance drops of just 3% and 6% each. Our exploration of the trade-off between the accuracy and computational cost brought about by the number of visual tokens facilitates future research to achieve the best of both worlds.
Authors: Isaac Labe, Noam Issachar, Itai Lang, Sagie Benaim
Abstract: We tackle the task of learning dynamic 3D semantic radiance fields given a single monocular video as input. Our learned semantic radiance field captures per-point semantics as well as color and geometric properties for a dynamic 3D scene, enabling the generation of novel views and their corresponding semantics. This enables the segmentation and tracking of a diverse set of 3D semantic entities, specified using a simple and intuitive interface that includes a user click or a text prompt. To this end, we present DGD, a unified 3D representation for both the appearance and semantics of a dynamic 3D scene, building upon the recently proposed dynamic 3D Gaussians representation. Our representation is optimized over time with both color and semantic information. Key to our method is the joint optimization of the appearance and semantic attributes, which jointly affect the geometric properties of the scene. We evaluate our approach in its ability to enable dense semantic 3D object tracking and demonstrate high-quality results that are fast to render, for a diverse set of scenes. Our project webpage is available on https://isaaclabe.github.io/DGD-Website/
Authors: Tianrun Chen, Chunan Yu, Jing Li, Jianqi Zhang, Lanyun Zhu, Deyi Ji, Yong Zhang, Ying Zang, Zejian Li, Lingyun Sun
Abstract: In this paper, we introduce a new task: Zero-Shot 3D Reasoning Segmentation for parts searching and localization for objects, which is a new paradigm to 3D segmentation that transcends limitations for previous category-specific 3D semantic segmentation, 3D instance segmentation, and open-vocabulary 3D segmentation. We design a simple baseline method, Reasoning3D, with the capability to understand and execute complex commands for (fine-grained) segmenting specific parts for 3D meshes with contextual awareness and reasoned answers for interactive segmentation. Specifically, Reasoning3D leverages an off-the-shelf pre-trained 2D segmentation network, powered by Large Language Models (LLMs), to interpret user input queries in a zero-shot manner. Previous research have shown that extensive pre-training endows foundation models with prior world knowledge, enabling them to comprehend complex commands, a capability we can harness to "segment anything" in 3D with limited 3D datasets (source efficient). Experimentation reveals that our approach is generalizable and can effectively localize and highlight parts of 3D objects (in 3D mesh) based on implicit textual queries, including these articulated 3d objects and real-world scanned data. Our method can also generate natural language explanations corresponding to these 3D models and the decomposition. Moreover, our training-free approach allows rapid deployment and serves as a viable universal baseline for future research of part-level 3d (semantic) object understanding in various fields including robotics, object manipulation, part assembly, autonomous driving applications, augment reality and virtual reality (AR/VR), and medical applications. The code, the model weight, the deployment guide, and the evaluation protocol are: http://tianrun-chen.github.io/Reason3D/
Authors: Simon Giebenhain, Tobias Kirschstein, Martin R\"unz, Lourdes Agapito, Matthias Nie{\ss}ner
Abstract: The creation of high-fidelity, digital versions of human heads is an important stepping stone in the process of further integrating virtual components into our everyday lives. Constructing such avatars is a challenging research problem, due to a high demand for photo-realism and real-time rendering performance. In this work, we propose Neural Parametric Gaussian Avatars (NPGA), a data-driven approach to create high-fidelity, controllable avatars from multi-view video recordings. We build our method around 3D Gaussian Splatting for its highly efficient rendering and to inherit the topological flexibility of point clouds. In contrast to previous work, we condition our avatars' dynamics on the rich expression space of neural parametric head models (NPHM), instead of mesh-based 3DMMs. To this end, we distill the backward deformation field of our underlying NPHM into forward deformations which are compatible with rasterization-based rendering. All remaining fine-scale, expression-dependent details are learned from the multi-view videos. To increase the representational capacity of our avatars, we augment the canonical Gaussian point cloud using per-primitive latent features which govern its dynamic behavior. To regularize this increased dynamic expressivity, we propose Laplacian terms on the latent features and predicted dynamics. We evaluate our method on the public NeRSemble dataset, demonstrating that NPGA significantly outperforms the previous state-of-the-art avatars on the self-reenactment task by 2.6 PSNR. Furthermore, we demonstrate accurate animation capabilities from real-world monocular videos.
Authors: Feipeng Ma, Hongwei Xue, Guangting Wang, Yizhou Zhou, Fengyun Rao, Shilin Yan, Yueyi Zhang, Siying Wu, Mike Zheng Shou, Xiaoyan Sun
Abstract: Most multi-modal tasks can be formulated into problems of either generation or embedding. Existing models usually tackle these two types of problems by decoupling language modules into a text decoder for generation, and a text encoder for embedding. To explore the minimalism of multi-modal paradigms, we attempt to achieve only one model per modality in this work. We propose a Multi-Modal Generative Embedding Model (MM-GEM), whereby the generative and embedding objectives are encapsulated in one Large Language Model. We also propose a PoolAggregator to boost efficiency and enable the ability of fine-grained embedding and generation. A surprising finding is that these two objectives do not significantly conflict with each other. For example, MM-GEM instantiated from ViT-Large and TinyLlama shows competitive performance on benchmarks for multimodal embedding models such as cross-modal retrieval and zero-shot classification, while has good ability of image captioning. Additionally, MM-GEM can seamlessly execute region-level image caption generation and retrieval tasks. Besides, the advanced text model in MM-GEM brings over 5% improvement in Recall@1 for long text and image retrieval.
Authors: Hanrong Ye, De-An Huang, Yao Lu, Zhiding Yu, Wei Ping, Andrew Tao, Jan Kautz, Song Han, Dan Xu, Pavlo Molchanov, Hongxu Yin
Abstract: We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information loss. To address the issue, we propose a visual alignment mechanism with a visual embedding highway module. We then introduce a resource-efficient recipe for training X-VILA, that exhibits proficiency in any-to-any modality conversation, surpassing previous approaches by large margins. X-VILA also showcases emergent properties across modalities even in the absence of similar training data. The project will be made open-source.
Authors: Hongwei Bran, Fernando Navarro, Ivan Ezhov, Amirhossein Bayat, Dhritiman Das, Florian Kofler, Suprosanna Shit, Diana Waldmannstetter, Johannes C. Paetzold, Xiaobin Hu, Benedikt Wiestler, Lucas Zimmer, Tamaz Amiranashvili, Chinmay Prabhakar, Christoph Berger, Jonas Weidner, Michelle Alonso-Basant, Arif Rashid, Ujjwal Baid, Wesam Adel, Deniz Ali, Bhakti Baheti, Yingbin Bai, Ishaan Bhatt, Sabri Can Cetindag, Wenting Chen, Li Cheng, Prasad Dutand, Lara Dular, Mustafa A. Elattar, Ming Feng, Shengbo Gao, Henkjan Huisman, Weifeng Hu, Shubham Innani, Wei Jiat, Davood Karimi, Hugo J. Kuijf, Jin Tae Kwak, Hoang Long Le, Xiang Lia, Huiyan Lin, Tongliang Liu, Jun Ma, Kai Ma, Ting Ma, Ilkay Oksuz, Robbie Holland, Arlindo L. Oliveira, Jimut Bahan Pal, Xuan Pei, Maoying Qiao, Anindo Saha, Raghavendra Selvan, Linlin Shen, Joao Lourenco Silva, Ziga Spiclin, Sanjay Talbar, Dadong Wang, Wei Wang, Xiong Wang, Yin Wang, Ruiling Xia, Kele Xu, Yanwu Yan, Mert Yergin, Shuang Yu, Lingxi Zeng, YingLin Zhang, Jiachen Zhao, Yefeng Zheng, Martin Zukovec, Richard Do, Anton Becker, Amber Simpson, Ender Konukoglu, Andras Jakab, Spyridon Bakas, Leo Joskowicz, Bjoern Menze
Abstract: Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consistent and reliable image segmentation. This variability not only reflects the inherent complexity and subjective nature of medical image interpretation but also directly impacts the development and evaluation of automated segmentation algorithms. Accurately modeling and quantifying this variability is essential for enhancing the robustness and clinical applicability of these algorithms. We report the set-up and summarize the benchmark results of the Quantification of Uncertainties in Biomedical Image Quantification Challenge (QUBIQ), which was organized in conjunction with International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020 and 2021. The challenge focuses on the uncertainty quantification of medical image segmentation which considers the omnipresence of inter-rater variability in imaging datasets. The large collection of images with multi-rater annotations features various modalities such as MRI and CT; various organs such as the brain, prostate, kidney, and pancreas; and different image dimensions 2D-vs-3D. A total of 24 teams submitted different solutions to the problem, combining various baseline models, Bayesian neural networks, and ensemble model techniques. The obtained results indicate the importance of the ensemble models, as well as the need for further research to develop efficient 3D methods for uncertainty quantification methods in 3D segmentation tasks.
Authors: Yavuz Selim Inan
Abstract: WHO has declared that more than 2.2 billion people worldwide are suffering from visual disorders, such as media haze, glaucoma, and drusen. At least 1 billion of these cases could have been either prevented or successfully treated, yet they remain unaddressed due to poverty, a lack of specialists, inaccurate ocular fundus diagnoses by ophthalmologists, or the presence of a rare disease. To address this, the research has developed the Hybrid Trio-Network Model Algorithm for accurately diagnosing 12 distinct common and rare eye diseases. This algorithm utilized the RFMiD dataset of 3,200 fundus images and the Binary Relevance Method to detect diseases separately, ensuring expandability and avoiding incorrect correlations. Each detector, incorporating finely tuned hyperparameters to optimize performance, consisted of three feature components: A classical transfer learning CNN model, a two-stage CNN model, and a Siamese Network. The diagnosis was made using features extracted through this Trio-Model with Ensembled Machine Learning algorithms. The proposed model achieved an average accuracy of 97% and an AUC score of 0.96. Compared to past benchmark studies, an increase of over 10% in the F1-score was observed for most diseases. Furthermore, using the Siamese Network, the model successfully made predictions in diseases like optic disc pallor, which past studies failed to predict due to low confidence. This diagnostic tool presents a stable, adaptive, cost-effective, efficient, accessible, and fast solution for globalizing early detection of both common and rare diseases.
Authors: Gongyue Zhang, Honghai Liu
Abstract: We have identified a potential method for unifying first-order optimizers through the use of variable Second-Moment Exponential Scaling(SMES). We begin with back propagation, addressing classic phenomena such as gradient vanishing and explosion, as well as issues related to dataset sparsity, and introduce the theory of balance in optimization. Through this theory, we suggest that SGD and adaptive optimizers can be unified under a broader inference, employing variable moving exponential scaling to achieve a balanced approach within a generalized formula for first-order optimizers. We conducted tests on some classic datasets and networks to confirm the impact of different balance coefficients on the overall training process.
Authors: Zefan Yang, Jiajin Zhang, Ge Wang, Mannudeep K. Kalra, Pingkun Yan
Abstract: Accurate prediction of Cardiovascular disease (CVD) risk in medical imaging is central to effective patient health management. Previous studies have demonstrated that imaging features in computed tomography (CT) can help predict CVD risk. However, CT entails notable radiation exposure, which may result in adverse health effects for patients. In contrast, chest X-ray emits significantly lower levels of radiation, offering a safer option. This rationale motivates our investigation into the feasibility of using chest X-ray for predicting CVD risk. Convolutional Neural Networks (CNNs) and Transformers are two established network architectures for computer-aided diagnosis. However, they struggle to model very high resolution chest X-ray due to the lack of large context modeling power or quadratic time complexity. Inspired by state space sequence models (SSMs), a new class of network architectures with competitive sequence modeling power as Transfomers and linear time complexity, we propose Bidirectional Image Mamba (BI-Mamba) to complement the unidirectional SSMs with opposite directional information. BI-Mamba utilizes parallel forward and backwark blocks to encode longe-range dependencies of multi-view chest X-rays. We conduct extensive experiments on images from 10,395 subjects in National Lung Screening Trail (NLST). Results show that BI-Mamba outperforms ResNet-50 and ViT-S with comparable parameter size, and saves significant amount of GPU memory during training. Besides, BI-Mamba achieves promising performance compared with previous state of the art in CT, unraveling the potential of chest X-ray for CVD risk prediction.
Authors: Aditya Gunturu, Yi Wen, Jarin Thundathil, Nandi Zhang, Rubaiat Habib Kazi, Ryo Suzuki
Abstract: We introduce Augmented Physics, a machine learning-powered tool designed for creating interactive physics simulations from static textbook diagrams. Leveraging computer vision techniques, such as Segment Anything and OpenCV, our web-based system enables users to semi-automatically extract diagrams from physics textbooks and then generate interactive simulations based on the extracted content. These interactive diagrams are seamlessly integrated into scanned textbook pages, facilitating interactive and personalized learning experiences across various physics concepts, including gravity, optics, circuits, and kinematics. Drawing on an elicitation study with seven physics instructors, we explore four key augmentation techniques: 1) augmented experiments, 2) animated diagrams, 3) bi-directional manipulatives, and 4) parameter visualization. We evaluate our system through technical evaluation, a usability study (N=12), and expert interviews (N=12). The study findings suggest that our system can facilitate more engaging and personalized learning experiences in physics education.
Authors: Che Liu, Changde Du, Xiaoyu Chen, Huiguang He
Abstract: Drawing inspiration from the hierarchical processing of the human auditory system, which transforms sound from low-level acoustic features to high-level semantic understanding, we introduce a novel coarse-to-fine audio reconstruction method. Leveraging non-invasive functional Magnetic Resonance Imaging (fMRI) data, our approach mimics the inverse pathway of auditory processing. Initially, we utilize CLAP to decode fMRI data coarsely into a low-dimensional semantic space, followed by a fine-grained decoding into the high-dimensional AudioMAE latent space guided by semantic features. These fine-grained neural features serve as conditions for audio reconstruction through a Latent Diffusion Model (LDM). Validation on three public fMRI datasets-Brain2Sound, Brain2Music, and Brain2Speech-underscores the superiority of our coarse-to-fine decoding method over stand-alone fine-grained approaches, showcasing state-of-the-art performance in metrics like FD, FAD, and KL. Moreover, by employing semantic prompts during decoding, we enhance the quality of reconstructed audio when semantic features are suboptimal. The demonstrated versatility of our model across diverse stimuli highlights its potential as a universal brain-to-audio framework. This research contributes to the comprehension of the human auditory system, pushing boundaries in neural decoding and audio reconstruction methodologies.
Authors: Yichen Wen, Zhiquan Tan, Kaipeng Zheng, Chuanlong Xie, Weiran Huang
Abstract: Continual learning requires learning incremental tasks with dynamic data distributions. So far, it has been observed that employing a combination of contrastive loss and distillation loss for training in continual learning yields strong performance. To the best of our knowledge, however, this contrastive continual learning framework lacks convincing theoretical explanations. In this work, we fill this gap by establishing theoretical performance guarantees, which reveal how the performance of the model is bounded by training losses of previous tasks in the contrastive continual learning framework. Our theoretical explanations further support the idea that pre-training can benefit continual learning. Inspired by our theoretical analysis of these guarantees, we propose a novel contrastive continual learning algorithm called CILA, which uses adaptive distillation coefficients for different tasks. These distillation coefficients are easily computed by the ratio between average distillation losses and average contrastive losses from previous tasks. Our method shows great improvement on standard benchmarks and achieves new state-of-the-art performance.
Authors: Zihui Wu, Yu Sun, Yifan Chen, Bingliang Zhang, Yisong Yue, Katherine L. Bouman
Abstract: Diffusion models (DMs) have recently shown outstanding capability in modeling complex image distributions, making them expressive image priors for solving Bayesian inverse problems. However, most existing DM-based methods rely on approximations in the generative process to be generic to different inverse problems, leading to inaccurate sample distributions that deviate from the target posterior defined within the Bayesian framework. To harness the generative power of DMs while avoiding such approximations, we propose a Markov chain Monte Carlo algorithm that performs posterior sampling for general inverse problems by reducing it to sampling the posterior of a Gaussian denoising problem. Crucially, we leverage a general DM formulation as a unified interface that allows for rigorously solving the denoising problem with a range of state-of-the-art DMs. We demonstrate the effectiveness of the proposed method on six inverse problems (three linear and three nonlinear), including a real-world black hole imaging problem. Experimental results indicate that our proposed method offers more accurate reconstructions and posterior estimation compared to existing DM-based imaging inverse methods.
Authors: Hongduan Tian, Feng Liu, Tongliang Liu, Bo Du, Yiu-ming Cheung, Bo Han
Abstract: In cross-domain few-shot classification, \emph{nearest centroid classifier} (NCC) aims to learn representations to construct a metric space where few-shot classification can be performed by measuring the similarities between samples and the prototype of each class. An intuition behind NCC is that each sample is pulled closer to the class centroid it belongs to while pushed away from those of other classes. However, in this paper, we find that there exist high similarities between NCC-learned representations of two samples from different classes. In order to address this problem, we propose a bi-level optimization framework, \emph{maximizing optimized kernel dependence} (MOKD) to learn a set of class-specific representations that match the cluster structures indicated by labeled data of the given task. Specifically, MOKD first optimizes the kernel adopted in \emph{Hilbert-Schmidt independence criterion} (HSIC) to obtain the optimized kernel HSIC (opt-HSIC) that can capture the dependence more precisely. Then, an optimization problem regarding the opt-HSIC is addressed to simultaneously maximize the dependence between representations and labels and minimize the dependence among all samples. Extensive experiments on Meta-Dataset demonstrate that MOKD can not only achieve better generalization performance on unseen domains in most cases but also learn better data representation clusters. The project repository of MOKD is available at: \href{https://github.com/tmlr-group/MOKD}{https://github.com/tmlr-group/MOKD}.
URLs: https://github.com/tmlr-group/MOKD, https://github.com/tmlr-group/MOKD
Authors: Shohei Enomoto
Abstract: Deep neural networks (DNNs) struggle to generalize to out-of-distribution domains that are different from those in training despite their impressive performance. In practical applications, it is important for DNNs to have both high standard accuracy and robustness against out-of-distribution domains. One technique that achieves both of these improvements is disentangled learning with mixture distribution via auxiliary batch normalization layers (ABNs). This technique treats clean and transformed samples as different domains, allowing a DNN to learn better features from mixed domains. However, if we distinguish the domains of the samples based on entropy, we find that some transformed samples are drawn from the same domain as clean samples, and these samples are not completely different domains. To generate samples drawn from a completely different domain than clean samples, we hypothesize that transforming clean high-entropy samples to further increase the entropy generates out-of-distribution samples that are much further away from the in-distribution domain. On the basis of the hypothesis, we propose high entropy propagation~(EntProp), which feeds high-entropy samples to the network that uses ABNs. We introduce two techniques, data augmentation and free adversarial training, that increase entropy and bring the sample further away from the in-distribution domain. These techniques do not require additional training costs. Our experimental results show that EntProp achieves higher standard accuracy and robustness with a lower training cost than the baseline methods. In particular, EntProp is highly effective at training on small datasets.
Authors: Niclas V\"odisch, K\"ursat Petek, Markus K\"appeler, Abhinav Valada, Wolfram Burgard
Abstract: A key challenge for the widespread application of learning-based models for robotic perception is to significantly reduce the required amount of annotated training data while achieving accurate predictions. This is essential not only to decrease operating costs but also to speed up deployment time. In this work, we address this challenge for PAnoptic SegmenTation with fEw Labels (PASTEL) by exploiting the groundwork paved by visual foundation models. We leverage descriptive image features from such a model to train two lightweight network heads for semantic segmentation and object boundary detection, using very few annotated training samples. We then merge their predictions via a novel fusion module that yields panoptic maps based on normalized cut. To further enhance the performance, we utilize self-training on unlabeled images selected by a feature-driven similarity scheme. We underline the relevance of our approach by employing PASTEL to important robot perception use cases from autonomous driving and agricultural robotics. In extensive experiments, we demonstrate that PASTEL significantly outperforms previous methods for label-efficient segmentation even when using fewer annotations. The code of our work is publicly available at http://pastel.cs.uni-freiburg.de.
Authors: Mareike Thies, Fabian Wagner, Noah Maul, Siyuan Mei, Mingxuan Gu, Laura Pfaff, Nastassia Vysotskaya, Haijun Yu, Andreas Maier
Abstract: Computed tomography (CT) relies on precise patient immobilization during image acquisition. Nevertheless, motion artifacts in the reconstructed images can persist. Motion compensation methods aim to correct such artifacts post-acquisition, often incorporating temporal smoothness constraints on the estimated motion patterns. This study analyzes the influence of a spline-based motion model within an existing rigid motion compensation algorithm for cone-beam CT on the recoverable motion frequencies. Results demonstrate that the choice of motion model crucially influences recoverable frequencies. The optimization-based motion compensation algorithm is able to accurately fit the spline nodes for frequencies almost up to the node-dependent theoretical limit according to the Nyquist-Shannon theorem. Notably, a higher node count does not compromise reconstruction performance for slow motion patterns, but can extend the range of recoverable high frequencies for the investigated algorithm. Eventually, the optimal motion model is dependent on the imaged anatomy, clinical use case, and scanning protocol and should be tailored carefully to the expected motion frequency spectrum to ensure accurate motion compensation.
Authors: Jose J. Quintana, Miguel A. Ferrer, Moises Diaz, Jose J. Feo, Adam Wolniakowski, Konstantsin Miatliuk
Abstract: Collaborative robots or cobots interact with humans in a common work environment. In cobots, one under investigated but important issue is related to their movement and how it is perceived by humans. This paper tries to analyze whether humans prefer a robot moving in a human or in a robotic fashion. To this end, the present work lays out what differentiates the movement performed by an industrial robotic arm from that performed by a human one. The main difference lies in the fact that the robotic movement has a trapezoidal speed profile, while for the human arm, the speed profile is bell-shaped and during complex movements, it can be considered as a sum of superimposed bell-shaped movements. Based on the lognormality principle, a procedure was developed for a robotic arm to perform human-like movements. Both speed profiles were implemented in two industrial robots, namely, an ABB IRB 120 and a Universal Robot UR3. Three tests were used to study the subjects' preference when seeing both movements and another analyzed the same when interacting with the robot by touching its ends with their fingers.
Authors: Shusong Xu, Peiye Liu
Abstract: Artificial Intelligence Generated Content(AIGC), known for its superior visual results, represents a promising mitigation method for high-cost advertising applications. Numerous approaches have been developed to manipulate generated content under different conditions. However, a crucial limitation lies in the accurate description of products in advertising applications. Applying previous methods directly may lead to considerable distortion and deformation of advertised products, primarily due to oversimplified content control conditions. Hence, in this work, we propose a patch-enhanced mask encoder approach to ensure accurate product descriptions while preserving diverse backgrounds. Our approach consists of three components Patch Flexible Visibility, Mask Encoder Prompt Adapter and an image Foundation Model. Patch Flexible Visibility is used for generating a more reasonable background image. Mask Encoder Prompt Adapter enables region-controlled fusion. We also conduct an analysis of the structure and operational mechanisms of the Generation Module. Experimental results show our method can achieve the highest visual results and FID scores compared with other methods.
Authors: Zhe Hu, Tuo Liang, Jing Li, Yiren Lu, Yunlai Zhou, Yiran Qiao, Jing Ma, Yu Yin
Abstract: Recent advancements in large multimodal language models have demonstrated remarkable proficiency across a wide range of tasks. Yet, these models still struggle with understanding the nuances of human humor through juxtaposition, particularly when it involves nonlinear narratives that underpin many jokes and humor cues. This paper investigates this challenge by focusing on comics with contradictory narratives, where each comic consists of two panels that create a humorous contradiction. We introduce the YesBut benchmark, which comprises tasks of varying difficulty aimed at assessing AI's capabilities in recognizing and interpreting these comics, ranging from literal content comprehension to deep narrative reasoning. Through extensive experimentation and analysis of recent commercial or open-sourced large (vision) language models, we assess their capability to comprehend the complex interplay of the narrative humor inherent in these comics. Our results show that even state-of-the-art models still lag behind human performance on this task. Our findings offer insights into the current limitations and potential improvements for AI in understanding human creative expressions.
Authors: Anna Breger, Ander Biguri, Malena Sabat\'e Landman, Ian Selby, Nicole Amberg, Elisabeth Brunner, Janek Gr\"ohl, Sepideh Hatamikia, Clemens Karner, Lipeng Ning, S\"oren Dittmer, Michael Roberts, AIX-COVNET Collaboration, Carola-Bibiane Sch\"onlieb
Abstract: Image quality assessment (IQA) is not just indispensable in clinical practice to ensure high standards, but also in the development stage of novel algorithms that operate on medical images with reference data. This paper provides a structured and comprehensive collection of examples where the two most common full reference (FR) image quality measures prove to be unsuitable for the assessment of novel algorithms using different kinds of medical images, including real-world MRI, CT, OCT, X-Ray, digital pathology and photoacoustic imaging data. In particular, the FR-IQA measures PSNR and SSIM are known and tested for working successfully in many natural imaging tasks, but discrepancies in medical scenarios have been noted in the literature. Inconsistencies arising in medical images are not surprising, as they have very different properties than natural images which have not been targeted nor tested in the development of the mentioned measures, and therefore might imply wrong judgement of novel methods for medical images. Therefore, improvement is urgently needed in particular in this era of AI to increase explainability, reproducibility and generalizability in machine learning for medical imaging and beyond. On top of the pitfalls we will provide ideas for future research as well as suggesting guidelines for the usage of FR-IQA measures applied to medical images.
Authors: Shuyu Cheng, Yibo Miao, Yinpeng Dong, Xiao Yang, Xiao-Shan Gao, Jun Zhu
Abstract: This paper studies the challenging black-box adversarial attack that aims to generate adversarial examples against a black-box model by only using output feedback of the model to input queries. Some previous methods improve the query efficiency by incorporating the gradient of a surrogate white-box model into query-based attacks due to the adversarial transferability. However, the localized gradient is not informative enough, making these methods still query-intensive. In this paper, we propose a Prior-guided Bayesian Optimization (P-BO) algorithm that leverages the surrogate model as a global function prior in black-box adversarial attacks. As the surrogate model contains rich prior information of the black-box one, P-BO models the attack objective with a Gaussian process whose mean function is initialized as the surrogate model's loss. Our theoretical analysis on the regret bound indicates that the performance of P-BO may be affected by a bad prior. Therefore, we further propose an adaptive integration strategy to automatically adjust a coefficient on the function prior by minimizing the regret bound. Extensive experiments on image classifiers and large vision-language models demonstrate the superiority of the proposed algorithm in reducing queries and improving attack success rates compared with the state-of-the-art black-box attacks. Code is available at https://github.com/yibo-miao/PBO-Attack.
Authors: Marzieh Gheisari, Auguste Genovesio
Abstract: Supervised deep learning approaches can artificially increase the resolution of microscopy images by learning a mapping between two image resolutions or modalities. However, such methods often require a large set of hard-to-get low-res/high-res image pairs and produce synthetic images with a moderate increase in resolution. Conversely, recent methods based on GAN latent search offered a drastic increase in resolution without the need of paired images. However, they offer limited reconstruction of the high-resolution image interpretable features. Here, we propose a robust super-resolution method based on regularized latent search~(RLS) that offers an actionable balance between fidelity to the ground-truth and realism of the recovered image given a distribution prior. The latter allows to split the analysis of a low-resolution image into a computational super-resolution task performed by deep learning followed by a quantification task performed by a handcrafted algorithm and based on interpretable biological features. This two-step process holds potential for various applications such as diagnostics on mobile devices, where the main aim is not to recover the high-resolution details of a specific sample but rather to obtain high-resolution images that preserve explainable and quantifiable differences between conditions.
Authors: Michail Mamalakis, H\'elo\"ise de Vareilles, Shun-Chin Jim Wu, Ingrid Agartz, Lynn Egeland M{\o}rch-Johnsen, Jane Garrison, Jon Simons, Pietro Lio, John Suckling, Graham Murray
Abstract: In the last decade, computer vision has witnessed the establishment of various training and learning approaches. Techniques like adversarial learning, contrastive learning, diffusion denoising learning, and ordinary reconstruction learning have become standard, representing state-of-the-art methods extensively employed for fully training or pre-training networks across various vision tasks. The exploration of fine-tuning approaches has emerged as a current focal point, addressing the need for efficient model tuning with reduced GPU memory usage and time costs while enhancing overall performance, as exemplified by methodologies like low-rank adaptation (LoRA). Key questions arise: which pre-training technique yields optimal results - adversarial, contrastive, reconstruction, or diffusion denoising? How does the performance of these approaches vary as the complexity of fine-tuning is adjusted? This study aims to elucidate the advantages of pre-training techniques and fine-tuning strategies to enhance the learning process of neural networks in independent identical distribution (IID) cohorts. We underscore the significance of fine-tuning by examining various cases, including full tuning, decoder tuning, top-level tuning, and fine-tuning of linear parameters using LoRA. Systematic summaries of model performance and efficiency are presented, leveraging metrics such as accuracy, time cost, and memory efficiency. To empirically demonstrate our findings, we focus on a multi-task segmentation-classification challenge involving the paracingulate sulcus (PCS) using different 3D Convolutional Neural Network (CNN) architectures by using the TOP-OSLO cohort comprising 596 subjects.
Authors: Anna Breger, Clemens Karner, Ian Selby, Janek Gr\"ohl, S\"oren Dittmer, Edward Lilley, Judith Babar, Jake Beckford, Timothy J Sadler, Shahab Shahipasand, Arthikkaa Thavakumar, Michael Roberts, Carola-Bibiane Sch\"onlieb
Abstract: Image quality assessment (IQA) is standard practice in the development stage of novel machine learning algorithms that operate on images. The most commonly used IQA measures have been developed and tested for natural images, but not in the medical setting. Reported inconsistencies arising in medical images are not surprising, as they have different properties than natural images. In this study, we test the applicability of common IQA measures for medical image data by comparing their assessment to manually rated chest X-ray (5 experts) and photoacoustic image data (1 expert). Moreover, we include supplementary studies on grayscale natural images and accelerated brain MRI data. The results of all experiments show a similar outcome in line with previous findings for medical imaging: PSNR and SSIM in the default setting are in the lower range of the result list and HaarPSI outperforms the other tested measures in the overall performance. Also among the top performers in our medical experiments are the full reference measures DISTS, FSIM, LPIPS and MS-SSIM. Generally, the results on natural images yield considerably higher correlations, suggesting that the additional employment of tailored IQA measures for medical imaging algorithms is needed.
Authors: Mohammadreza Sadeghi, Zihan Wang, Narges Armanfard
Abstract: Unsupervised Continual Learning (UCL) is a burgeoning field in machine learning, focusing on enabling neural networks to sequentially learn tasks without explicit label information. Catastrophic Forgetting (CF), where models forget previously learned tasks upon learning new ones, poses a significant challenge in continual learning, especially in UCL, where labeled information of data is not accessible. CF mitigation strategies, such as knowledge distillation and replay buffers, often face memory inefficiency and privacy issues. Although current research in UCL has endeavored to refine data representations and address CF in streaming data contexts, there is a noticeable lack of algorithms specifically designed for unsupervised clustering. To fill this gap, in this paper, we introduce the concept of Unsupervised Continual Clustering (UCC). We propose Forward-Backward Knowledge Distillation for unsupervised Continual Clustering (FBCC) to counteract CF within the context of UCC. FBCC employs a single continual learner (the ``teacher'') with a cluster projector, along with multiple student models, to address the CF issue. The proposed method consists of two phases: Forward Knowledge Distillation, where the teacher learns new clusters while retaining knowledge from previous tasks with guidance from specialized student models, and Backward Knowledge Distillation, where a student model mimics the teacher's behavior to retain task-specific knowledge, aiding the teacher in subsequent tasks. FBCC marks a pioneering approach to UCC, demonstrating enhanced performance and memory efficiency in clustering across various tasks, outperforming the application of clustering algorithms to the latent space of state-of-the-art UCL algorithms.
Authors: Yingqing He, Zhaoyang Liu, Jingye Chen, Zeyue Tian, Hongyu Liu, Xiaowei Chi, Runtao Liu, Ruibin Yuan, Yazhou Xing, Wenhai Wang, Jifeng Dai, Yong Zhang, Wei Xue, Qifeng Liu, Yike Guo, Qifeng Chen
Abstract: With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on understanding. This survey elaborates on multimodal generation across different domains, including image, video, 3D, and audio, where we highlight the notable advancements with milestone works in these fields. Specifically, we exhaustively investigate the key technical components behind methods and multimodal datasets utilized in these studies. Moreover, we dig into tool-augmented multimodal agents that can use existing generative models for human-computer interaction. Lastly, we also comprehensively discuss the advancement in AI safety and investigate emerging applications as well as future prospects. Our work provides a systematic and insightful overview of multimodal generation, which is expected to advance the development of Artificial Intelligence for Generative Content (AIGC) and world models. A curated list of all related papers can be found at https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation
URLs: https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation
Authors: Kwonjoon Lee, Huiwen Chang, Lu Jiang, Han Zhang, Zhuowen Tu, Ce Liu
Abstract: Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases. In this paper, we investigate if such performance can be extended to image generation. To this end, we integrate the ViT architecture into generative adversarial networks (GANs). For ViT discriminators, we observe that existing regularization methods for GANs interact poorly with self-attention, causing serious instability during training. To resolve this issue, we introduce several novel regularization techniques for training GANs with ViTs. For ViT generators, we examine architectural choices for latent and pixel mapping layers to facilitate convergence. Empirically, our approach, named ViTGAN, achieves comparable performance to the leading CNN-based GAN models on three datasets: CIFAR-10, CelebA, and LSUN bedroom.
Authors: Siyu Xing, Chen Gong, Hewei Guo, Xiao-Yu Zhang, Xinwen Hou, Yu Liu
Abstract: Existing GAN inversion methods work brilliantly in reconstructing high-quality (HQ) images while struggling with more common low-quality (LQ) inputs in practical application. To address this issue, we propose Unsupervised Domain Adaptation (UDA) in the inversion process, namely UDA-inversion, for effective inversion and editing of both HQ and LQ images. Regarding unpaired HQ images as the source domain and LQ images as the unlabeled target domain, we introduce a theoretical guarantee: loss value in the target domain is upper-bounded by loss in the source domain and a novel discrepancy function measuring the difference between two domains. Following that, we can only minimize this upper bound to obtain accurate latent codes for HQ and LQ images. Thus, constructive representations of HQ images can be spontaneously learned and transformed into LQ images without supervision. UDA-Inversion achieves a better PSNR of 22.14 on FFHQ dataset and performs comparably to supervised methods.
Authors: Ren\'e Haas, Inbar Huberman-Spiegelglas, Rotem Mulayoff, Stella Gra{\ss}hof, Sami S. Brandt, Tomer Michaeli
Abstract: Denoising Diffusion Models (DDMs) have emerged as a strong competitor to Generative Adversarial Networks (GANs). However, despite their widespread use in image synthesis and editing applications, their latent space is still not as well understood. Recently, a semantic latent space for DDMs, coined `$h$-space', was shown to facilitate semantic image editing in a way reminiscent of GANs. The $h$-space is comprised of the bottleneck activations in the DDM's denoiser across all timesteps of the diffusion process. In this paper, we explore the properties of h-space and propose several novel methods for finding meaningful semantic directions within it. We start by studying unsupervised methods for revealing interpretable semantic directions in pretrained DDMs. Specifically, we show that global latent directions emerge as the principal components in the latent space. Additionally, we provide a novel method for discovering image-specific semantic directions by spectral analysis of the Jacobian of the denoiser w.r.t. the latent code. Next, we extend the analysis by finding directions in a supervised fashion in unconditional DDMs. We demonstrate how such directions can be found by relying on either a labeled data set of real images or by annotating generated samples with a domain-specific attribute classifier. We further show how to semantically disentangle the found direction by simple linear projection. Our approaches are applicable without requiring any architectural modifications, text-based guidance, CLIP-based optimization, or model fine-tuning.
Authors: Brian Chen, Nina Shvetsova, Andrew Rouditchenko, Daniel Kondermann, Samuel Thomas, Shih-Fu Chang, Rogerio Feris, James Glass, Hilde Kuehne
Abstract: Spatio-temporal grounding describes the task of localizing events in space and time, e.g., in video data, based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bounding box supervision. This work addresses this task from a multimodal supervision perspective, proposing a framework for spatio-temporal action grounding trained on loose video and subtitle supervision only, without human annotation. To this end, we combine local representation learning, which focuses on leveraging fine-grained spatial information, with a global representation encoding that captures higher-level representations and incorporates both in a joint approach. To evaluate this challenging task in a real-life setting, a new benchmark dataset is proposed providing dense spatio-temporal grounding annotations in long, untrimmed, multi-action instructional videos for over 5K events. We evaluate the proposed approach and other methods on the proposed and standard downstream tasks showing that our method improves over current baselines in various settings, including spatial, temporal, and untrimmed multi-action spatio-temporal grounding.
Authors: Songwei Ge, Taesung Park, Jun-Yan Zhu, Jia-Bin Huang
Abstract: Plain text has become a prevalent interface for text-to-image synthesis. However, its limited customization options hinder users from accurately describing desired outputs. For example, plain text makes it hard to specify continuous quantities, such as the precise RGB color value or importance of each word. Furthermore, creating detailed text prompts for complex scenes is tedious for humans to write and challenging for text encoders to interpret. To address these challenges, we propose using a rich-text editor supporting formats such as font style, size, color, and footnote. We extract each word's attributes from rich text to enable local style control, explicit token reweighting, precise color rendering, and detailed region synthesis. We achieve these capabilities through a region-based diffusion process. We first obtain each word's region based on attention maps of a diffusion process using plain text. For each region, we enforce its text attributes by creating region-specific detailed prompts and applying region-specific guidance, and maintain its fidelity against plain-text generation through region-based injections. We present various examples of image generation from rich text and demonstrate that our method outperforms strong baselines with quantitative evaluations.
Authors: Jialong Zuo, Jiahao Hong, Feng Zhang, Changqian Yu, Hanyu Zhou, Changxin Gao, Nong Sang, Jingdong Wang
Abstract: Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory performance. The reason is that they neglect critical person-related characteristics, i.e., fine-grained attributes and identities. To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP. Specifically, we elaborately design three pretext tasks: 1) Text-guided Image Colorization, aims to establish the correspondence between the person-related image regions and the fine-grained color-part textual phrases. 2) Image-guided Attributes Prediction, aims to mine fine-grained attribute information of the person body in the image; and 3) Identity-based Vision-Language Contrast, aims to correlate the cross-modal representations at the identity level rather than the instance level. Moreover, to implement our pre-train framework, we construct a large-scale person dataset with image-text pairs named SYNTH-PEDES by automatically generating textual annotations. We pre-train PLIP on SYNTH-PEDES and evaluate our models by spanning downstream person-centric tasks. PLIP not only significantly improves existing methods on all these tasks, but also shows great ability in the zero-shot and domain generalization settings. The code, dataset and weights will be released at~\url{https://github.com/Zplusdragon/PLIP}
Authors: Bosheng Qin, Juncheng Li, Siliang Tang, Tat-Seng Chua, Yueting Zhuang
Abstract: We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for per-example fine-tuning or inversion. The proposed InstructVid2Vid model modifies a pretrained image generation model, Stable Diffusion, to generate a time-dependent sequence of video frames. By harnessing the collective intelligence of disparate models, we engineer a training dataset rich in video-instruction triplets, which is a more cost-efficient alternative to collecting data in real-world scenarios. To enhance the coherence between successive frames within the generated videos, we propose the Inter-Frames Consistency Loss and incorporate it during the training process. With multimodal classifier-free guidance during the inference stage, the generated videos is able to resonate with both the input video and the accompanying instructions. Experimental results demonstrate that InstructVid2Vid is capable of generating high-quality, temporally coherent videos and performing diverse edits, including attribute editing, background changes, and style transfer. These results underscore the versatility and effectiveness of our proposed method.
Authors: Yuguang Yang, Runtang Guo, Sheng Wu, Yimi Wang, Juan Zhang, Xuan Gong, Baochang Zhang
Abstract: Interpretation of deep learning remains a very challenging problem. Although the Class Activation Map (CAM) is widely used to interpret deep model predictions by highlighting object location, it fails to provide insight into the salient features used by the model to make decisions. Furthermore, existing evaluation protocols often overlook the correlation between interpretability performance and the model's decision quality, which presents a more fundamental issue. This paper proposes a new two-stage interpretability method called the Decomposition Class Activation Map (Decom-CAM), which offers a feature-level interpretation of the model's prediction. Decom-CAM decomposes intermediate activation maps into orthogonal features using singular value decomposition and generates saliency maps by integrating them. The orthogonality of features enables CAM to capture local features and can be used to pinpoint semantic components such as eyes, noses, and faces in the input image, making it more beneficial for deep model interpretation. To ensure a comprehensive comparison, we introduce a new evaluation protocol by dividing the dataset into subsets based on classification accuracy results and evaluating the interpretability performance on each subset separately. Our experiments demonstrate that the proposed Decom-CAM outperforms current state-of-the-art methods significantly by generating more precise saliency maps across all levels of classification accuracy. Combined with our feature-level interpretability approach, this paper could pave the way for a new direction for understanding the decision-making process of deep neural networks.
Authors: Chandramouli Sastry, Sri Harsha Dumpala, Sageev Oore
Abstract: We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example consists of one forward-diffusion step followed by one reverse-diffusion step. Using both ResNet-50 and Vision Transformer architectures, we comprehensively evaluate classifiers trained with DiffAug and demonstrate the surprising effectiveness of single-step reverse diffusion in improving robustness to covariate shifts, certified adversarial accuracy and out of distribution detection. When we combine DiffAug with other augmentations such as AugMix and DeepAugment we demonstrate further improved robustness. Finally, building on this approach, we also improve classifier-guided diffusion wherein we observe improvements in: (i) classifier-generalization, (ii) gradient quality (i.e., improved perceptual alignment) and (iii) image generation performance. We thus introduce a computationally efficient technique for training with improved robustness that does not require any additional data, and effectively complements existing augmentation approaches.
Authors: Wenjun Jiang, Tianlong Fan, Changhao Li, Chuanfu Zhang, Tao Zhang, Zong-fu Luo
Abstract: Connectivity robustness, a crucial aspect for understanding, optimizing, and repairing complex networks, has traditionally been evaluated through time-consuming and often impractical simulations. Fortunately, machine learning provides a new avenue for addressing this challenge. However, several key issues remain unresolved, including the performance in more general edge removal scenarios, capturing robustness through attack curves instead of directly training for robustness, scalability of predictive tasks, and transferability of predictive capabilities. In this paper, we address these challenges by designing a convolutional neural networks (CNN) model with spatial pyramid pooling networks (SPP-net), adapting existing evaluation metrics, redesigning the attack modes, introducing appropriate filtering rules, and incorporating the value of robustness as training data. The results demonstrate the thoroughness of the proposed CNN framework in addressing the challenges of high computational time across various network types, failure component types and failure scenarios. However, the performance of the proposed CNN model varies: for evaluation tasks that are consistent with the trained network type, the proposed CNN model consistently achieves accurate evaluations of both attack curves and robustness values across all removal scenarios. When the predicted network type differs from the trained network, the CNN model still demonstrates favorable performance in the scenario of random node failure, showcasing its scalability and performance transferability. Nevertheless, the performance falls short of expectations in other removal scenarios. This observed scenario-sensitivity in the evaluation of network features has been overlooked in previous studies and necessitates further attention and optimization. Lastly, we discuss important unresolved questions and further investigation.
Authors: Xinyuan Li, Yu Guo, Yubei Tu, Yu Ji, Yanchen Liu, Jinwei Ye, Changxi Zheng
Abstract: Reconstructing and tracking deformable surface with little or no texture has posed long-standing challenges. Fundamentally, the challenges stem from textureless surfaces lacking features for establishing cross-image correspondences. In this work, we present a novel type of markers to proactively enrich the object's surface features, and thereby ease the 3D surface reconstruction and correspondence tracking. Our markers are made of fluorescent dyes, visible only under the ultraviolet (UV) light and invisible under regular lighting condition. Leveraging the markers, we design a multi-camera system that captures surface deformation under the UV light and the visible light in a time multiplexing fashion. Under the UV light, markers on the object emerge to enrich its surface texture, allowing high-quality 3D shape reconstruction and tracking. Under the visible light, markers become invisible, allowing us to capture the object's original untouched appearance. We perform experiments on various challenging scenes, including hand gestures, facial expressions, waving cloth, and hand-object interaction. In all these cases, we demonstrate that our system is able to produce robust, high-quality 3D reconstruction and tracking.
Authors: Rama Krishna Kandukuri, Michael Strecke, Joerg Stueckler
Abstract: Physics-based understanding of object interactions from sensory observations is an essential capability in augmented reality and robotics. It enables to capture the properties of a scene for simulation and control. In this paper, we propose a novel approach for real-to-sim which tracks rigid objects in 3D from RGB-D images and infers physical properties of the objects. We use a differentiable physics simulation as state-transition model in an Extended Kalman Filter which can model contact and friction for arbitrary mesh-based shapes and in this way estimate physically plausible trajectories. We demonstrate that our approach can filter position, orientation, velocities, and concurrently can estimate the coefficient of friction of the objects. We analyze our approach on various sliding scenarios in synthetic image sequences of single objects and colliding objects. We also demonstrate and evaluate our approach on a real-world dataset. We make our novel benchmark datasets publicly available to foster future research in this novel problem setting and comparison with our method.
Authors: Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, Yifan Zhang
Abstract: In this paper, we conduct a comprehensive analysis of two dual-branch (Siamese architecture) self-supervised learning approaches, namely Barlow Twins and spectral contrastive learning, through the lens of matrix mutual information. We prove that the loss functions of these methods implicitly optimize both matrix mutual information and matrix joint entropy. This insight prompts us to further explore the category of single-branch algorithms, specifically MAE and U-MAE, for which mutual information and joint entropy become the entropy. Building on this intuition, we introduce the Matrix Variational Masked Auto-Encoder (M-MAE), a novel method that leverages the matrix-based estimation of entropy as a regularizer and subsumes U-MAE as a special case. The empirical evaluations underscore the effectiveness of M-MAE compared with the state-of-the-art methods, including a 3.9% improvement in linear probing ViT-Base, and a 1% improvement in fine-tuning ViT-Large, both on ImageNet.
Authors: Ziyue Huang, Yupeng He, Qingjie Liu, Yunhong Wang
Abstract: In contrast to the incremental classification task, the incremental detection task is characterized by the presence of data ambiguity, as an image may have differently labeled bounding boxes across multiple continuous learning stages. This phenomenon often impairs the model's ability to effectively learn new classes. However, existing research has paid less attention to the forward compatibility of the model, which limits its suitability for incremental learning. To overcome this obstacle, we propose leveraging a visual-language model such as CLIP to generate text feature embeddings for different class sets, which enhances the feature space globally. We then employ super-classes to replace the unavailable novel classes in the early learning stage to simulate the incremental scenario. Finally, we utilize the CLIP image encoder to accurately identify potential objects. We incorporate the finely recognized detection boxes as pseudo-annotations into the training process, thereby further improving the detection performance. We evaluate our approach on various incremental learning settings using the PASCAL VOC 2007 dataset, and our approach outperforms state-of-the-art methods, particularly for recognizing the new classes.
Authors: Chunyi Sun, Junlin Han, Weijian Deng, Xinlong Wang, Zishan Qin, Stephen Gould
Abstract: In the pursuit of efficient automated content creation, procedural generation, leveraging modifiable parameters and rule-based systems, emerges as a promising approach. Nonetheless, it could be a demanding endeavor, given its intricate nature necessitating a deep understanding of rules, algorithms, and parameters. To reduce workload, we introduce 3D-GPT, a framework utilizing large language models~(LLMs) for instruction-driven 3D modeling. 3D-GPT positions LLMs as proficient problem solvers, dissecting the procedural 3D modeling tasks into accessible segments and appointing the apt agent for each task. 3D-GPT integrates three core agents: the task dispatch agent, the conceptualization agent, and the modeling agent. They collaboratively achieve two objectives. First, it enhances concise initial scene descriptions, evolving them into detailed forms while dynamically adapting the text based on subsequent instructions. Second, it integrates procedural generation, extracting parameter values from enriched text to effortlessly interface with 3D software for asset creation. Our empirical investigations confirm that 3D-GPT not only interprets and executes instructions, delivering reliable results but also collaborates effectively with human designers. Furthermore, it seamlessly integrates with Blender, unlocking expanded manipulation possibilities. Our work highlights the potential of LLMs in 3D modeling, offering a basic framework for future advancements in scene generation and animation.
Authors: McKell Woodland, Austin Castelo, Mais Al Taie, Jessica Albuquerque Marques Silva, Mohamed Eltaher, Frank Mohn, Alexander Shieh, Austin Castelo, Suprateek Kundu, Joshua P. Yung, Ankit B. Patel, Kristy K. Brock
Abstract: Fr\'echet Inception Distance (FID) is a widely used metric for assessing synthetic image quality. It relies on an ImageNet-based feature extractor, making its applicability to medical imaging unclear. A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images. Our study challenges this practice by demonstrating that ImageNet-based extractors are more consistent and aligned with human judgment than their RadImageNet counterparts. We evaluated sixteen StyleGAN2 networks across four medical imaging modalities and four data augmentation techniques with Fr\'echet distances (FDs) computed using eleven ImageNet or RadImageNet-trained feature extractors. Comparison with human judgment via visual Turing tests revealed that ImageNet-based extractors produced rankings consistent with human judgment, with the FD derived from the ImageNet-trained SwAV extractor significantly correlating with expert evaluations. In contrast, RadImageNet-based rankings were volatile and inconsistent with human judgment. Our findings challenge prevailing assumptions, providing novel evidence that medical image-trained feature extractors do not inherently improve FDs and can even compromise their reliability. Our code is available at https://github.com/mckellwoodland/fid-med-eval.
Authors: Zhiwen Yan, Weng Fei Low, Yu Chen, Gim Hee Lee
Abstract: 3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering. Despite its high rendering quality and speed at high resolutions, they both deteriorate drastically when rendered at lower resolutions or from far away camera position. During low resolution or far away rendering, the pixel size of the image can fall below the Nyquist frequency compared to the screen size of each splatted 3D Gaussian and leads to aliasing effect. The rendering is also drastically slowed down by the sequential alpha blending of more splatted Gaussians per pixel. To address these issues, we propose a multi-scale 3D Gaussian splatting algorithm, which maintains Gaussians at different scales to represent the same scene. Higher-resolution images are rendered with more small Gaussians, and lower-resolution images are rendered with fewer larger Gaussians. With similar training time, our algorithm can achieve 13\%-66\% PSNR and 160\%-2400\% rendering speed improvement at 4$\times$-128$\times$ scale rendering on Mip-NeRF360 dataset compared to the single scale 3D Gaussian splitting. Our code and more results are available on our project website https://jokeryan.github.io/projects/ms-gs/
Authors: Xuan-Bac Nguyen, Xin Li, Pawan Sinha, Samee U. Khan, Khoa Luu
Abstract: Human perception plays a vital role in forming beliefs and understanding reality. A deeper understanding of brain functionality will lead to the development of novel deep neural networks. In this work, we introduce a novel framework named Brainformer, a straightforward yet effective Transformer-based framework, to analyze Functional Magnetic Resonance Imaging (fMRI) patterns in the human perception system from a machine-learning perspective. Specifically, we present the Multi-scale fMRI Transformer to explore brain activity patterns through fMRI signals. This architecture includes a simple yet efficient module for high-dimensional fMRI signal encoding and incorporates a novel embedding technique called 3D Voxels Embedding. Secondly, drawing inspiration from the functionality of the brain's Region of Interest, we introduce a novel loss function called Brain fMRI Guidance Loss. This loss function mimics brain activity patterns from these regions in the deep neural network using fMRI data. This work introduces a prospective approach to transfer knowledge from human perception to neural networks. Our experiments demonstrate that leveraging fMRI information allows the machine vision model to achieve results comparable to State-of-the-Art methods in various image recognition tasks.
Authors: Zhuo Huang, Chang Liu, Yinpeng Dong, Hang Su, Shibao Zheng, Tongliang Liu
Abstract: Although vision models such as Contrastive Language-Image Pre-Training (CLIP) show impressive generalization performance, their zero-shot robustness is still limited under Out-of-Distribution (OOD) scenarios without fine-tuning. Instead of undesirably providing human supervision as commonly done, it is possible to take advantage of Multi-modal Large Language Models (MLLMs) that hold powerful visual understanding abilities. However, MLLMs are shown to struggle with vision problems due to the incompatibility of tasks, thus hindering their utilization. In this paper, we propose to effectively leverage MLLMs to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner. To solve the incompatibility issue, we propose a novel Denoising In-Context Learning (DICL) strategy to align vision tasks with MLLMs. Concretely, by estimating a transition matrix that captures the probability of one class being confused with another, an instruction containing a correct exemplar and an erroneous one from the most probable noisy class can be constructed. Such an instruction can help any MLLMs with ICL ability to detect and rectify incorrect predictions of vision models. Through extensive experiments on ImageNet, WILDS, DomainBed, and other OOD datasets, we carefully validate the quantitative and qualitative effectiveness of our method. Our code is available at https://github.com/tmllab/Machine_Vision_Therapy.
Authors: Yongqi Dong, Xingmin Lu, Ruohan Li, Wei Song, Bart van Arem, Haneen Farah
Abstract: The burgeoning navigation services using digital maps provide great convenience to drivers. Nevertheless, the presence of anomalies in lane rendering map images occasionally introduces potential hazards, as such anomalies can be misleading to human drivers and consequently contribute to unsafe driving conditions. In response to this concern and to accurately and effectively detect the anomalies, this paper transforms lane rendering image anomaly detection into a classification problem and proposes a four-phase pipeline consisting of data pre-processing, self-supervised pre-training with the masked image modeling (MiM) method, customized fine-tuning using cross-entropy based loss with label smoothing, and post-processing to tackle it leveraging state-of-the-art deep learning techniques, especially those involving Transformer models. Various experiments verify the effectiveness of the proposed pipeline. Results indicate that the proposed pipeline exhibits superior performance in lane rendering image anomaly detection, and notably, the self-supervised pre-training with MiM can greatly enhance the detection accuracy while significantly reducing the total training time. For instance, employing the Swin Transformer with Uniform Masking as self-supervised pretraining (Swin-Trans-UM) yielded a heightened accuracy at 94.77% and an improved Area Under The Curve (AUC) score of 0.9743 compared with the pure Swin Transformer without pre-training (Swin-Trans) with an accuracy of 94.01% and an AUC of 0.9498. The fine-tuning epochs were dramatically reduced to 41 from the original 280. In conclusion, the proposed pipeline, with its incorporation of self-supervised pre-training using MiM and other advanced deep learning techniques, emerges as a robust solution for enhancing the accuracy and efficiency of lane rendering image anomaly detection in digital navigation systems.
Authors: Thomas W. Mitchel, Carlos Esteves, Ameesh Makadia
Abstract: We introduce a framework for intrinsic latent diffusion models operating directly on the surfaces of 3D shapes, with the goal of synthesizing high-quality textures. Our approach is underpinned by two contributions: field latents, a latent representation encoding textures as discrete vector fields on the mesh vertices, and field latent diffusion models, which learn to denoise a diffusion process in the learned latent space on the surface. We consider a single-textured-mesh paradigm, where our models are trained to generate variations of a given texture on a mesh. We show the synthesized textures are of superior fidelity compared those from existing single-textured-mesh generative models. Our models can also be adapted for user-controlled editing tasks such as inpainting and label-guided generation. The efficacy of our approach is due in part to the equivariance of our proposed framework under isometries, allowing our models to seamlessly reproduce details across locally similar regions and opening the door to a notion of generative texture transfer.
Authors: Erez Yosef, Raja Giryes
Abstract: Image reconstruction from noisy sensor measurements is a challenging problem. Many solutions have been proposed for it, where the main approach is learning good natural images prior along with modeling the true statistics of the noise in the scene. In the presence of very low lighting conditions, such approaches are usually not enough, and additional information is required, e.g., in the form of using multiple captures. We suggest as an alternative to add a description of the scene as prior, which can be easily done by the photographer capturing the scene. Inspired by the remarkable success of diffusion models for image generation, using a text-guided diffusion model we show that adding image caption information significantly improves image denoising and reconstruction on both synthetic and real-world images.
Authors: Dvir Samuel, Barak Meiri, Nir Darshan, Shai Avidan, Gal Chechik, Rami Ben-Ari
Abstract: Diffusion inversion is the problem of taking an image and a text prompt that describes it and finding a noise latent that would generate the image. Most current inversion techniques operate by approximately solving an implicit equation and may converge slowly or yield poor reconstructed images. Here, we formulate the problem as finding the roots of an implicit equation and design a method to solve it efficiently. Our solution is based on Newton-Raphson (NR), a well-known technique in numerical analysis. A naive application of NR may be computationally infeasible and tends to converge to incorrect solutions. We describe an efficient regularized formulation that converges quickly to a solution that provides high-quality reconstructions. We also identify a source of inconsistency stemming from prompt conditioning during the inversion process, which significantly degrades the inversion quality. To address this, we introduce a prompt-aware adjustment of the encoding, effectively correcting this issue. Our solution, Regularized Newton-Raphson Inversion, inverts an image within 0.5 sec for latent consistency models, opening the door for interactive image editing. We further demonstrate improved results in image interpolation and generation of rare objects.
Authors: Kang Chen, Yuanjie Liu
Abstract: This article presents a sliding window model for defocus deblurring, named Swintormer, which achieves the best performance to date with remarkably low memory usage. This method utilizes a diffusion model to generate latent prior features, aiding in the restoration of more detailed images. Additionally, by adapting the sliding window strategy, it incorporates specialized Transformer blocks to enhance inference efficiency. The adoption of this new approach has led to a substantial reduction in Multiply-Accumulate Operations (MACs) per iteration, drastically cutting down memory requirements. In comparison to the currently leading GRL method, our Swintormer model significantly reduces the computational load that must depend on memory capacity, from 140.35 GMACs to 8.02 GMACs, while improving the Peak Signal-to-Noise Ratio (PSNR) for defocus deblurring from 27.04 dB to 27.07 dB. This innovative technique enables the processing of higher resolution images on memory-limited devices, vastly broadening potential application scenarios. The article wraps up with an ablation study, offering a comprehensive examination of how each network module contributes to the final performance.The source code and model will be available at the following website: https://github.com/bnm6900030/swintormer.
Authors: F. Xavier Gaya-Morey, Silvia Ramis, Jose M. Buades-Rubio, Cristina Manresa-Yee
Abstract: Facial expression recognition has gained significance as a means of imparting social robots with the capacity to discern the emotional states of users. The use of social robotics includes a variety of settings, including homes, nursing homes or daycare centers, serving to a wide range of users. Remarkable performance has been achieved by deep learning approaches, however, its direct use for recognizing facial expressions in individuals with intellectual disabilities has not been yet studied in the literature, to the best of our knowledge. To address this objective, we train a set of 12 convolutional neural networks in different approaches, including an ensemble of datasets without individuals with intellectual disabilities and a dataset featuring such individuals. Our examination of the outcomes, both the performance and the important image regions for the models, reveals significant distinctions in facial expressions between individuals with and without intellectual disabilities, as well as among individuals with intellectual disabilities. Remarkably, our findings show the need of facial expression recognition within this population through tailored user-specific training methodologies, which enable the models to effectively address the unique expressions of each user.
Authors: Konstantin A. Maslov, Claudio Persello, Thomas Schellenberger, Alfred Stein
Abstract: Accurate global glacier mapping is critical for understanding climate change impacts. Despite its importance, automated glacier mapping at a global scale remains largely unexplored. Here we address this gap and propose Glacier-VisionTransformer-U-Net (GlaViTU), a convolutional-transformer deep learning model, and five strategies for multitemporal global-scale glacier mapping using open satellite imagery. Assessing the spatial, temporal and cross-sensor generalisation shows that our best strategy achieves intersection over union >0.85 on previously unobserved images in most cases, which drops to >0.75 for debris-rich areas such as High-Mountain Asia and increases to >0.90 for regions dominated by clean ice. A comparative validation against human expert uncertainties in terms of area and distance deviations underscores GlaViTU performance, approaching or matching expert-level delineation. Adding synthetic aperture radar data, namely, backscatter and interferometric coherence, increases the accuracy in all regions where available. The calibrated confidence for glacier extents is reported making the predictions more reliable and interpretable. We also release a benchmark dataset that covers 9% of glaciers worldwide. Our results support efforts towards automated multitemporal and global glacier mapping.
Authors: Youjia Wang, Yiwen Wu, Hengan Zhou, Hongyang Lin, Xingyue Peng, Yingwenqi Jiang, Yingsheng Zhu, Guanpeng Long, Yatu Zhang, Jingya Wang, Lan Xu, Jingyi Yu
Abstract: For facial motion capture and analysis, the dominated solutions are generally based on visual cues, which cannot protect privacy and are vulnerable to occlusions. Inertial measurement units (IMUs) serve as potential rescues yet are mainly adopted for full-body motion capture. In this paper, we propose IMUSIC to fill the gap, a novel path for facial expression capture using purely IMU signals, significantly distant from previous visual solutions.The key design in our IMUSIC is a trilogy. We first design micro-IMUs to suit facial capture, companion with an anatomy-driven IMU placement scheme. Then, we contribute a novel IMU-ARKit dataset, which provides rich paired IMU/visual signals for diverse facial expressions and performances. Such unique multi-modality brings huge potential for future directions like IMU-based facial behavior analysis. Moreover, utilizing IMU-ARKit, we introduce a strong baseline approach to accurately predict facial blendshape parameters from purely IMU signals. Specifically, we tailor a Transformer diffusion model with a two-stage training strategy for this novel tracking task. The IMUSIC framework empowers us to perform accurate facial capture in scenarios where visual methods falter and simultaneously safeguard user privacy. We conduct extensive experiments about both the IMU configuration and technical components to validate the effectiveness of our IMUSIC approach. Notably, IMUSIC enables various potential and novel applications, i.e., privacy-protecting facial capture, hybrid capture against occlusions, or detecting minute facial movements that are often invisible through visual cues. We will release our dataset and implementations to enrich more possibilities of facial capture and analysis in our community.
Authors: Christopher Liao, Christian So, Theodoros Tsiligkaridis, Brian Kulis
Abstract: Domain generalization (DG) is an important problem that learns a model which generalizes to unseen test domains leveraging one or more source domains, under the assumption of shared label spaces. However, most DG methods assume access to abundant source data in the target label space, a requirement that proves overly stringent for numerous real-world applications, where acquiring the same label space as the target task is prohibitively expensive. For this setting, we tackle the multimodal version of the unsupervised domain generalization (MUDG) problem, which uses a large task-agnostic unlabeled source dataset during finetuning. Our framework does not explicitly assume any relationship between the source dataset and target task. Instead, it relies only on the premise that the source dataset can be accurately and efficiently searched in a joint vision-language space. We make three contributions in the MUDG setting. Firstly, we show theoretically that cross-modal approximate nearest neighbor search suffers from low recall due to the large distance between text queries and the image centroids used for coarse quantization. Accordingly, we propose paired k-means, a simple clustering algorithm that improves nearest neighbor recall by storing centroids in query space instead of image space. Secondly, we propose an adaptive text augmentation scheme for target labels designed to improve zero-shot accuracy and diversify retrieved image data. Lastly, we present two simple but effective components to further improve downstream target accuracy. We compare against state-of-the-art name-only transfer, source-free DG and zero-shot (ZS) methods on their respective benchmarks and show consistent improvement in accuracy on 20 diverse datasets. Code is available: https://github.com/Chris210634/mudg
Authors: Pedro Vianna, Muawiz Chaudhary, Paria Mehrbod, An Tang, Guy Cloutier, Guy Wolf, Michael Eickenberg, Eugene Belilovsky
Abstract: Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the biomedical field, their performance can be affected by changes in the data (different machines, populations) between training and test datasets. To ensure robustness and generalization to real-world scenarios, test-time adaptation has been recently studied as an approach to adjust models to a new data distribution during inference. Test-time batch normalization is a simple and popular method that achieved compelling performance on domain shift benchmarks. It is implemented by recalculating batch normalization statistics on test batches. Prior work has focused on analysis with test data that has the same label distribution as the training data. However, in many practical applications this technique is vulnerable to label distribution shifts, sometimes producing catastrophic failure. This presents a risk in applying test time adaptation methods in deployment. We propose to tackle this challenge by only selectively adapting channels in a deep network, minimizing drastic adaptation that is sensitive to label shifts. Our selection scheme is based on two principles that we empirically motivate: (1) later layers of networks are more sensitive to label shift (2) individual features can be sensitive to specific classes. We apply the proposed technique to three classification tasks, including CIFAR10-C, Imagenet-C, and diagnosis of fatty liver, where we explore both covariate and label distribution shifts. We find that our method allows to bring the benefits of TTA while significantly reducing the risk of failure common in other methods, while being robust to choice in hyperparameters.
Authors: Jinyuan Li, Han Li, Di Sun, Jiahao Wang, Wenkun Zhang, Zan Wang, Gang Pan
Abstract: Grounded Multimodal Named Entity Recognition (GMNER) is a nascent multimodal task that aims to identify named entities, entity types and their corresponding visual regions. GMNER task exhibits two challenging properties: 1) The weak correlation between image-text pairs in social media results in a significant portion of named entities being ungroundable. 2) There exists a distinction between coarse-grained referring expressions commonly used in similar tasks (e.g., phrase localization, referring expression comprehension) and fine-grained named entities. In this paper, we propose RiVEG, a unified framework that reformulates GMNER into a joint MNER-VE-VG task by leveraging large language models (LLMs) as a connecting bridge. This reformulation brings two benefits: 1) It maintains the optimal MNER performance and eliminates the need for employing object detection methods to pre-extract regional features, thereby naturally addressing two major limitations of existing GMNER methods. 2) The introduction of entity expansion expression and Visual Entailment (VE) module unifies Visual Grounding (VG) and Entity Grounding (EG). It enables RiVEG to effortlessly inherit the Visual Entailment and Visual Grounding capabilities of any current or prospective multimodal pretraining models. Extensive experiments demonstrate that RiVEG outperforms state-of-the-art methods on the existing GMNER dataset and achieves absolute leads of 10.65%, 6.21%, and 8.83% in all three subtasks.
Authors: Dingkang Liang, Xin Zhou, Wei Xu, Xingkui Zhu, Zhikang Zou, Xiaoqing Ye, Xiao Tan, Xiang Bai
Abstract: Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity method with global modeling appealing. In this paper, we propose PointMamba, transferring the success of Mamba, a recent representative state space model (SSM), from NLP to point cloud analysis tasks. Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs. Specifically, our method leverages space-filling curves for effective point tokenization and adopts an extremely simple, non-hierarchical Mamba encoder as the backbone. Comprehensive evaluations demonstrate that PointMamba achieves superior performance across multiple datasets while significantly reducing GPU memory usage and FLOPs. This work underscores the potential of SSMs in 3D vision-related tasks and presents a simple yet effective Mamba-based baseline for future research. The code is available at https://github.com/LMD0311/PointMamba.
Authors: Rishubh Parihar, Abhijnya Bhat, Abhipsa Basu, Saswat Mallick, Jogendra Nath Kundu, R. Venkatesh Babu
Abstract: Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the biases present in the training datasets. This is especially concerning in the context of faces, where the DM prefers one demographic subgroup vs others (eg. female vs male). In this work, we present a method for debiasing DMs without relying on additional data or model retraining. Specifically, we propose Distribution Guidance, which enforces the generated images to follow the prescribed attribute distribution. To realize this, we build on the key insight that the latent features of denoising UNet hold rich demographic semantics, and the same can be leveraged to guide debiased generation. We train Attribute Distribution Predictor (ADP) - a small mlp that maps the latent features to the distribution of attributes. ADP is trained with pseudo labels generated from existing attribute classifiers. The proposed Distribution Guidance with ADP enables us to do fair generation. Our method reduces bias across single/multiple attributes and outperforms the baseline by a significant margin for unconditional and text-conditional diffusion models. Further, we present a downstream task of training a fair attribute classifier by rebalancing the training set with our generated data.
Authors: Feifei Wang
Abstract: This technical report presents a diffusion model based framework for face swapping between two portrait images. The basic framework consists of three components, i.e., IP-Adapter, ControlNet, and Stable Diffusion's inpainting pipeline, for face feature encoding, multi-conditional generation, and face inpainting respectively. Besides, I introduce facial guidance optimization and CodeFormer based blending to further improve the generation quality. Specifically, we engage a recent light-weighted customization method (i.e., DreamBooth-LoRA), to guarantee the identity consistency by 1) using a rare identifier "sks" to represent the source identity, and 2) injecting the image features of source portrait into each cross-attention layer like the text features. Then I resort to the strong inpainting ability of Stable Diffusion, and utilize canny image and face detection annotation of the target portrait as the conditions, to guide ContorlNet's generation and align source portrait with the target portrait. To further correct face alignment, we add the facial guidance loss to optimize the text embedding during the sample generation. The code is available at: https://github.com/somuchtome/Faceswap
Authors: Dingkang Yang, Kun Yang, Mingcheng Li, Shunli Wang, Shuaibing Wang, Lihua Zhang
Abstract: Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Mainstream CAER methods invariably extract ensemble representations from diverse contexts and subject-centred characteristics to perceive the target person's emotional state. Despite advancements, the biggest challenge remains due to context bias interference. The harmful bias forces the models to rely on spurious correlations between background contexts and emotion labels in likelihood estimation, causing severe performance bottlenecks and confounding valuable context priors. In this paper, we propose a counterfactual emotion inference (CLEF) framework to address the above issue. Specifically, we first formulate a generalized causal graph to decouple the causal relationships among the variables in CAER. Following the causal graph, CLEF introduces a non-invasive context branch to capture the adverse direct effect caused by the context bias. During the inference, we eliminate the direct context effect from the total causal effect by comparing factual and counterfactual outcomes, resulting in bias mitigation and robust prediction. As a model-agnostic framework, CLEF can be readily integrated into existing methods, bringing consistent performance gains.
Authors: Kang Chen, Shiyan Chen, Jiyuan Zhang, Baoyue Zhang, Yajing Zheng, Tiejun Huang, Zhaofei Yu
Abstract: Reconstructing a sequence of sharp images from the blurry input is crucial for enhancing our insights into the captured scene and poses a significant challenge due to the limited temporal features embedded in the image. Spike cameras, sampling at rates up to 40,000 Hz, have proven effective in capturing motion features and beneficial for solving this ill-posed problem. Nonetheless, existing methods fall into the supervised learning paradigm, which suffers from notable performance degradation when applied to real-world scenarios that diverge from the synthetic training data domain. Moreover, the quality of reconstructed images is capped by the generated images based on motion analysis interpolation, which inherently differs from the actual scene, affecting the generalization ability of these methods in real high-speed scenarios. To address these challenges, we propose the first self-supervised framework for the task of spike-guided motion deblurring. Our approach begins with the formulation of a spike-guided deblurring model that explores the theoretical relationships among spike streams, blurry images, and their corresponding sharp sequences. We subsequently develop a self-supervised cascaded framework to alleviate the issues of spike noise and spatial-resolution mismatching encountered in the deblurring model. With knowledge distillation and re-blurring loss, we further design a lightweight deblur network to generate high-quality sequences with brightness and texture consistency with the original input. Quantitative and qualitative experiments conducted on our real-world and synthetic datasets with spikes validate the superior generalization of the proposed framework. Our code, data and trained models will be available at \url{https://github.com/chenkang455/S-SDM}.
Authors: Li-Yuan Tsao, Yi-Chen Lo, Chia-Che Chang, Hao-Wei Chen, Roy Tseng, Chien Feng, Chun-Yi Lee
Abstract: Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature. To overcome these issues, this work introduces a conditional learned prior to the inference phase of a flow-based SR model. This prior is a latent code predicted by our proposed latent module conditioned on the low-resolution image, which is then transformed by the flow model into an SR image. Our framework is designed to seamlessly integrate with any contemporary flow-based SR model without modifying its architecture or pre-trained weights. We evaluate the effectiveness of our proposed framework through extensive experiments and ablation analyses. The proposed framework successfully addresses all the inherent issues in flow-based SR models and enhances their performance in various SR scenarios. Our code is available at: https://github.com/liyuantsao/BFSR
Authors: Taeheon Kim, Sangyun Chung, Damin Yeom, Youngjoon Yu, Hak Gu Kim, Yong Man Ro
Abstract: Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in certain cases (e.g., thermal-obscured pedestrians), particularly due to the modality bias learned from statistically biased datasets. In this paper, we investigate how to mitigate modality bias in multispectral pedestrian detection using Large Language Models (LLMs). Accordingly, we design a Multispectral Chain-of-Thought (MSCoT) prompting strategy, which prompts the LLM to perform multispectral pedestrian detection. Moreover, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework that integrates MSCoT prompting into multispectral pedestrian detection. To this end, we design a Language-driven Multi-modal Fusion (LMF) strategy that enables fusing the outputs of MSCoT prompting with the detection results of vision-based multispectral pedestrian detection models. Extensive experiments validate that MSCoTDet effectively mitigates modality biases and improves multispectral pedestrian detection.
Authors: Lingdong Shen, Fangxin Shang, Xiaoshuang Huang, Yehui Yang, Haifeng Huang, Shiming Xiang
Abstract: In the field of medical image segmentation, tackling Out-of-Distribution (OOD) segmentation tasks in a cost-effective manner remains a significant challenge. Universal segmentation models is a solution, which aim to generalize across the diverse modality of medical images, yet their effectiveness often diminishes when applied to OOD data modalities and tasks, requiring intricate fine-tuning of model for optimal performance. Few-shot learning segmentation methods are typically designed for specific modalities of data and cannot be directly transferred for use with another modality. Therefore, we introduce SegICL, a novel approach leveraging In-Context Learning (ICL) for image segmentation. Unlike existing methods, SegICL has the capability to employ text-guided segmentation and conduct in-context learning with a small set of image-mask pairs, eliminating the need for training the model from scratch or fine-tuning for OOD tasks (including OOD modality and dataset). Extensive experimental demonstrates a positive correlation between the number of shots and segmentation performance on OOD tasks. The performance of segmentation when provided thre-shots is approximately 1.5 times better than the performance in a zero-shot setting. This indicates that SegICL effectively address new segmentation tasks based on contextual information. Additionally, SegICL also exhibits comparable performance to mainstream models on OOD and in-distribution tasks. Our code will be released after paper review.
Authors: Xixuan Hao, Wei Chen, Yibo Yan, Siru Zhong, Kun Wang, Qingsong Wen, Yuxuan Liang
Abstract: Urban region profiling aims to learn a low-dimensional representation of a given urban area while preserving its characteristics, such as demographics, infrastructure, and economic activities, for urban planning and development. However, prevalent pretrained models, particularly those reliant on satellite imagery, face dual challenges. Firstly, concentrating solely on macro-level patterns from satellite data may introduce bias, lacking nuanced details at micro levels, such as architectural details at a place.Secondly, the lack of interpretability in pretrained models limits their utility in providing transparent evidence for urban planning. In response to these issues, we devise a novel framework entitled UrbanVLP based on Vision-Language Pretraining. Our UrbanVLP seamlessly integrates multi-granularity information from both macro (satellite) and micro (street-view) levels, overcoming the limitations of prior pretrained models. Moreover, it introduces automatic text generation and calibration, elevating interpretability in downstream applications by producing high-quality text descriptions of urban imagery. Rigorous experiments conducted across six urban indicator prediction tasks underscore its superior performance.
Authors: Zhuoxu Huang, Zhenkun Fan, Tao Xu, Jungong Han
Abstract: Point cloud video representation learning is challenging due to complex structures and unordered spatial arrangement. Traditional methods struggle with frame-to-frame correlations and point-wise correspondence tracking. Recently, partial differential equations (PDE) have provided a new perspective in uniformly solving spatial-temporal data information within certain constraints. While tracking tangible point correspondence remains challenging, we propose to formalize point cloud video representation learning as a PDE-solving problem. Inspired by fluid analysis, where PDEs are used to solve the deformation of spatial shape over time, we employ PDE to solve the variations of spatial points affected by temporal information. By modeling spatial-temporal correlations, we aim to regularize spatial variations with temporal features, thereby enhancing representation learning in point cloud videos. We introduce Motion PointNet composed of a PointNet-like encoder and a PDE-solving module. Initially, we construct a lightweight yet effective encoder to model an initial state of the spatial variations. Subsequently, we develop our PDE-solving module in a parameterized latent space, tailored to address the spatio-temporal correlations inherent in point cloud video. The process of solving PDE is guided and refined by a contrastive learning structure, which is pivotal in reshaping the feature distribution, thereby optimizing the feature representation within point cloud video data. Remarkably, our Motion PointNet achieves an impressive accuracy of 97.52% on the MSRAction-3D dataset, surpassing the current state-of-the-art in all aspects while consuming minimal resources (only 0.72M parameters and 0.82G FLOPs).
Authors: Daniel Bogdoll, Iramm Hamdard, Lukas Namgyu R\"o{\ss}ler, Felix Geisler, Muhammed Bayram, Felix Wang, Jan Imhof, Miguel de Campos, Anushervon Tabarov, Yitian Yang, Hanno Gottschalk, J. Marius Z\"ollner
Abstract: The scale-up of autonomous vehicles depends heavily on their ability to deal with anomalies, such as rare objects on the road. In order to handle such situations, it is necessary to detect anomalies in the first place. Anomaly detection for autonomous driving has made great progress in the past years but suffers from poorly designed benchmarks with a strong focus on camera data. In this work, we propose AnoVox, the largest benchmark for ANOmaly detection in autonomous driving to date. AnoVox incorporates large-scale multimodal sensor data and spatial VOXel ground truth, allowing for the comparison of methods independent of their used sensor. We propose a formal definition of normality and provide a compliant training dataset. AnoVox is the first benchmark to contain both content and temporal anomalies.
Authors: Takahiro Shindo, Taiju Watanabe, Yui Tatsumi, Hiroshi Watanabe
Abstract: As image recognition models become more prevalent, scalable coding methods for machines and humans gain more importance. Applications of image recognition models include traffic monitoring and farm management. In these use cases, the scalable coding method proves effective because the tasks require occasional image checking by humans. Existing image compression methods for humans and machines meet these requirements to some extent. However, these compression methods are effective solely for specific image recognition models. We propose a learning-based scalable image coding method for humans and machines that is compatible with numerous image recognition models. We combine an image compression model for machines with a compression model, providing additional information to facilitate image decoding for humans. The features in these compression models are fused using a feature fusion network to achieve efficient image compression. Our method's additional information compression model is adjusted to reduce the number of parameters by enabling combinations of features of different sizes in the feature fusion network. Our approach confirms that the feature fusion network efficiently combines image compression models while reducing the number of parameters. Furthermore, we demonstrate the effectiveness of the proposed scalable coding method by evaluating the image compression performance in terms of decoded image quality and bitrate.
Authors: Phillip Sloan, Philip Clatworthy, Edwin Simpson, Majid Mirmehdi
Abstract: Increasing demands on medical imaging departments are taking a toll on the radiologist's ability to deliver timely and accurate reports. Recent technological advances in artificial intelligence have demonstrated great potential for automatic radiology report generation (ARRG), sparking an explosion of research. This survey paper conducts a methodological review of contemporary ARRG approaches by way of (i) assessing datasets based on characteristics, such as availability, size, and adoption rate, (ii) examining deep learning training methods, such as contrastive learning and reinforcement learning, (iii) exploring state-of-the-art model architectures, including variations of CNN and transformer models, (iv) outlining techniques integrating clinical knowledge through multimodal inputs and knowledge graphs, and (v) scrutinising current model evaluation techniques, including commonly applied NLP metrics and qualitative clinical reviews. Furthermore, the quantitative results of the reviewed models are analysed, where the top performing models are examined to seek further insights. Finally, potential new directions are highlighted, with the adoption of additional datasets from other radiological modalities and improved evaluation methods predicted as important areas of future development.
Authors: Mengxi Zhang, Wenhao Wu, Yu Lu, Yuxin Song, Kang Rong, Huanjin Yao, Jianbo Zhao, Fanglong Liu, Yifan Sun, Haocheng Feng, Jingdong Wang
Abstract: Current multimodal Large Language Models (MLLMs) suffer from ``hallucination'', occasionally generating responses that are not grounded in the input images. To tackle this challenge, one promising path is to utilize reinforcement learning from human feedback (RLHF), which steers MLLMs towards learning superior responses while avoiding inferior ones. We rethink the common practice of using binary preferences (i.e., superior, inferior), and find that adopting multi-level preferences (e.g., superior, medium, inferior) is better for two benefits: 1) It narrows the gap between adjacent levels, thereby encouraging MLLMs to discern subtle differences. 2) It further integrates cross-level comparisons (beyond adjacent-level comparisons), thus providing a broader range of comparisons with hallucination examples. To verify our viewpoint, we present the Automated Multi-level Preference (AMP) framework for MLLMs. To facilitate this framework, we first develop an automated dataset generation pipeline that provides high-quality multi-level preference datasets without any human annotators. Furthermore, we design the Multi-level Direct Preference Optimization (MDPO) algorithm to robustly conduct complex multi-level preference learning. Additionally, we propose a new hallucination benchmark, MRHal-Bench. Extensive experiments across public hallucination and general benchmarks, as well as our MRHal-Bench, demonstrate the effectiveness of our proposed method. Code is available at https://github.com/takomc/amp.
Authors: Peng Li, Yuan Liu, Xiaoxiao Long, Feihu Zhang, Cheng Lin, Mengfei Li, Xingqun Qi, Shanghang Zhang, Wenhan Luo, Ping Tan, Wenping Wang, Qifeng Liu, Yike Guo
Abstract: In this paper, we introduce Era3D, a novel multiview diffusion method that generates high-resolution multiview images from a single-view image. Despite significant advancements in multiview generation, existing methods still suffer from camera prior mismatch, inefficacy, and low resolution, resulting in poor-quality multiview images. Specifically, these methods assume that the input images should comply with a predefined camera type, e.g. a perspective camera with a fixed focal length, leading to distorted shapes when the assumption fails. Moreover, the full-image or dense multiview attention they employ leads to an exponential explosion of computational complexity as image resolution increases, resulting in prohibitively expensive training costs. To bridge the gap between assumption and reality, Era3D first proposes a diffusion-based camera prediction module to estimate the focal length and elevation of the input image, which allows our method to generate images without shape distortions. Furthermore, a simple but efficient attention layer, named row-wise attention, is used to enforce epipolar priors in the multiview diffusion, facilitating efficient cross-view information fusion. Consequently, compared with state-of-the-art methods, Era3D generates high-quality multiview images with up to a 512*512 resolution while reducing computation complexity by 12x times. Comprehensive experiments demonstrate that Era3D can reconstruct high-quality and detailed 3D meshes from diverse single-view input images, significantly outperforming baseline multiview diffusion methods. Project page: https://penghtyx.github.io/Era3D/.
Authors: Tharun V. Puthanveettil, Fnu Obaid ur Rahman
Abstract: Object tracking is a fundamental task in computer vision with broad practical applications across various domains, including traffic monitoring, robotics, and autonomous vehicle tracking. In this project, we aim to develop a sophisticated aerial vehicle system known as Track Anything Rapter (TAR), designed to detect, segment, and track objects of interest based on user-provided multimodal queries, such as text, images, and clicks. TAR utilizes cutting-edge pre-trained models like DINO, CLIP, and SAM to estimate the relative pose of the queried object. The tracking problem is approached as a Visual Servoing task, enabling the UAV to consistently focus on the object through advanced motion planning and control algorithms. We showcase how the integration of these foundational models with a custom high-level control algorithm results in a highly stable and precise tracking system deployed on a custom-built PX4 Autopilot-enabled Voxl2 M500 drone. To validate the tracking algorithm's performance, we compare it against Vicon-based ground truth. Additionally, we evaluate the reliability of the foundational models in aiding tracking in scenarios involving occlusions. Finally, we test and validate the model's ability to work seamlessly with multiple modalities, such as click, bounding box, and image templates.
Authors: Jiaqi Li, Qianshan Wei, Chuanyi Zhang, Guilin Qi, Miaozeng Du, Yongrui Chen, Sheng Bi
Abstract: Machine unlearning empowers individuals with the `right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains uncertain whether MU can be effectively applied to Multimodal Large Language Models (MLLMs), particularly in scenarios of forgetting the leaked visual data of concepts. To overcome the challenge, we propose an efficient method, Single Image Unlearning (SIU), to unlearn the visual recognition of a concept by fine-tuning a single associated image for few steps. SIU consists of two key aspects: (i) Constructing Multifaceted fine-tuning data. We introduce four targets, based on which we construct fine-tuning data for the concepts to be forgotten; (ii) Jointly training loss. To synchronously forget the visual recognition of concepts and preserve the utility of MLLMs, we fine-tune MLLMs through a novel Dual Masked KL-divergence Loss combined with Cross Entropy loss. Alongside our method, we establish MMUBench, a new benchmark for MU in MLLMs and introduce a collection of metrics for its evaluation. Experimental results on MMUBench show that SIU completely surpasses the performance of existing methods. Furthermore, we surprisingly find that SIU can avoid invasive membership inference attacks and jailbreak attacks. To the best of our knowledge, we are the first to explore MU in MLLMs. We will release the code and benchmark in the near future.
Authors: Andres Hernandez, Zhongqi Miao, Luisa Vargas, Rahul Dodhia, Juan Lavista
Abstract: The alarming decline in global biodiversity, driven by various factors, underscores the urgent need for large-scale wildlife monitoring. In response, scientists have turned to automated deep learning methods for data processing in wildlife monitoring. However, applying these advanced methods in real-world scenarios is challenging due to their complexity and the need for specialized knowledge, primarily because of technical challenges and interdisciplinary barriers. To address these challenges, we introduce Pytorch-Wildlife, an open-source deep learning platform built on PyTorch. It is designed for creating, modifying, and sharing powerful AI models. This platform emphasizes usability and accessibility, making it accessible to individuals with limited or no technical background. It also offers a modular codebase to simplify feature expansion and further development. Pytorch-Wildlife offers an intuitive, user-friendly interface, accessible through local installation or Hugging Face, for animal detection and classification in images and videos. As two real-world applications, Pytorch-Wildlife has been utilized to train animal classification models for species recognition in the Amazon Rainforest and for invasive opossum recognition in the Galapagos Islands. The Opossum model achieves 98% accuracy, and the Amazon model has 92% recognition accuracy for 36 animals in 90% of the data. As Pytorch-Wildlife evolves, we aim to integrate more conservation tasks, addressing various environmental challenges. Pytorch-Wildlife is available at https://github.com/microsoft/CameraTraps.
Authors: Jia Guo, Shuai Lu, Weihang Zhang, Huiqi Li
Abstract: Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images, serving as an alternative to the conventional one-class-one-model setup. Despite various advancements addressing this challenging task, the detection performance under the multi-class setting still lags far behind state-of-the-art class-separated models. Our research aims to bridge this substantial performance gap. In this paper, we introduce a minimalistic reconstruction-based anomaly detection framework, namely Dinomaly, which leverages pure Transformer architectures without relying on complex designs, additional modules, or specialized tricks. Given this powerful framework consisted of only Attentions and MLPs, we found four simple components that are essential to multi-class anomaly detection: (1) Foundation Transformers that extracts universal and discriminative features, (2) Noisy Bottleneck where pre-existing Dropouts do all the noise injection tricks, (3) Linear Attention that naturally cannot focus, and (4) Loose Reconstruction that does not force layer-to-layer and point-by-point reconstruction. Extensive experiments are conducted across three popular anomaly detection benchmarks including MVTec-AD, VisA, and the recently released Real-IAD. Our proposed Dinomaly achieves impressive image AUROC of 99.6%, 98.7%, and 89.3% on the three datasets respectively, which is not only superior to state-of-the-art multi-class UAD methods, but also surpasses the most advanced class-separated UAD records.
Authors: Bill Psomas, Ioannis Kakogeorgiou, Nikos Efthymiadis, Giorgos Tolias, Ondrej Chum, Yannis Avrithis, Konstantinos Karantzalos
Abstract: This work introduces composed image retrieval to remote sensing. It allows to query a large image archive by image examples alternated by a textual description, enriching the descriptive power over unimodal queries, either visual or textual. Various attributes can be modified by the textual part, such as shape, color, or context. A novel method fusing image-to-image and text-to-image similarity is introduced. We demonstrate that a vision-language model possesses sufficient descriptive power and no further learning step or training data are necessary. We present a new evaluation benchmark focused on color, context, density, existence, quantity, and shape modifications. Our work not only sets the state-of-the-art for this task, but also serves as a foundational step in addressing a gap in the field of remote sensing image retrieval. Code at: https://github.com/billpsomas/rscir
Authors: Mingshuang Luo, Ruibing Hou, Hong Chang, Zimo Liu, Yaowei Wang, Shiguang Shan
Abstract: This paper presents M$^3$GPT, an advanced $\textbf{M}$ultimodal, $\textbf{M}$ultitask framework for $\textbf{M}$otion comprehension and generation. M$^3$GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal control and generation signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling model generation directly in the raw motion space. This strategy circumvents the information loss associated with discrete tokenizer, resulting in more detailed and comprehensive model generation. Third, M$^3$GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M$^3$GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M$^3$GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks.
Authors: Hanyu Chen, Bailey Miller, Ioannis Gkioulekas
Abstract: We introduce a technique for the reconstruction of high-fidelity surfaces from multi-view images. Our technique uses a new point-based representation, the dipole sum, which generalizes the winding number to allow for interpolation of arbitrary per-point attributes in point clouds with noisy or outlier points. Using dipole sums allows us to represent implicit geometry and radiance fields as per-point attributes of a point cloud, which we initialize directly from structure from motion. We additionally derive Barnes-Hut fast summation schemes for accelerated forward and reverse-mode dipole sum queries. These queries facilitate the use of ray tracing to efficiently and differentiably render images with our point-based representations, and thus update their point attributes to optimize scene geometry and appearance. We evaluate this inverse rendering framework against state-of-the-art alternatives, based on ray tracing of neural representations or rasterization of Gaussian point-based representations. Our technique significantly improves reconstruction quality at equal runtimes, while also supporting more general rendering techniques such as shadow rays for direct illumination. In the supplement, we provide interactive visualizations of our results.
Authors: Zipeng Wang, Dan Xu
Abstract: Neural Radiance Fields (NeRFs) have demonstrated remarkable proficiency in synthesizing photorealistic images of large-scale scenes. However, they are often plagued by a loss of fine details and long rendering durations. 3D Gaussian Splatting has recently been introduced as a potent alternative, achieving both high-fidelity visual results and accelerated rendering performance. Nonetheless, scaling 3D Gaussian Splatting is fraught with challenges. Specifically, large-scale scenes grapples with the integration of objects across multiple scales and disparate viewpoints, which often leads to compromised efficacy as the Gaussians need to balance between detail levels. Furthermore, the generation of initialization points via COLMAP from large-scale dataset is both computationally demanding and prone to incomplete reconstructions. To address these challenges, we present Pyramidal 3D Gaussian Splatting (PyGS) with NeRF Initialization. Our approach represent the scene with a hierarchical assembly of Gaussians arranged in a pyramidal fashion. The top level of the pyramid is composed of a few large Gaussians, while each subsequent layer accommodates a denser collection of smaller Gaussians. We effectively initialize these pyramidal Gaussians through sampling a rapidly trained grid-based NeRF at various frequencies. We group these pyramidal Gaussians into clusters and use a compact weighting network to dynamically determine the influence of each pyramid level of each cluster considering camera viewpoint during rendering. Our method achieves a significant performance leap across multiple large-scale datasets and attains a rendering time that is over 400 times faster than current state-of-the-art approaches.
Authors: Franz Motzkus, Georgii Mikriukov, Christian Hellert, Ute Schmid
Abstract: Ensuring the quality of black-box Deep Neural Networks (DNNs) has become ever more significant, especially in safety-critical domains such as automated driving. While global concept encodings generally enable a user to test a model for a specific concept, linking global concept encodings to the local processing of single network inputs reveals their strengths and limitations. Our proposed framework global-to-local Concept Attribution (glCA) uses approaches from local (why a specific prediction originates) and global (how a model works generally) eXplainable Artificial Intelligence (xAI) to test DNNs for a predefined semantical concept locally. The approach allows for conditioning local, post-hoc explanations on predefined semantic concepts encoded as linear directions in the model's latent space. Pixel-exact scoring concerning the global concept usage assists the tester in further understanding the model processing of single data points for the selected concept. Our approach has the advantage of fully covering the model-internal encoding of the semantic concept and allowing the localization of relevant concept-related information. The results show major differences in the local perception and usage of individual global concept encodings and demand for further investigations regarding obtaining thorough semantic concept encodings.
Authors: Isla Duporge, Maksim Kholiavchenko, Roi Harel, Scott Wolf, Dan Rubenstein, Meg Crofoot, Tanya Berger-Wolf, Stephen Lee, Julie Barreau, Jenna Kline, Michelle Ramirez, Chuck Stewart
Abstract: Using drones to track multiple individuals simultaneously in their natural environment is a powerful approach for better understanding group primate behavior. Previous studies have demonstrated that it is possible to automate the classification of primate behavior from video data, but these studies have been carried out in captivity or from ground-based cameras. To understand group behavior and the self-organization of a collective, the whole troop needs to be seen at a scale where behavior can be seen in relation to the natural environment in which ecological decisions are made. This study presents a novel dataset from drone videos for baboon detection, tracking, and behavior recognition. The baboon detection dataset was created by manually annotating all baboons in drone videos with bounding boxes. A tiling method was subsequently applied to create a pyramid of images at various scales from the original 5.3K resolution images, resulting in approximately 30K images used for baboon detection. The tracking dataset is derived from the detection dataset, where all bounding boxes are assigned the same ID throughout the video. This process resulted in half an hour of very dense tracking data. The behavior recognition dataset was generated by converting tracks into mini-scenes, a video subregion centered on each animal; each mini-scene was manually annotated with 12 distinct behavior types, resulting in over 20 hours of data. Benchmark results show mean average precision (mAP) of 92.62\% for the YOLOv8-X detection model, multiple object tracking precision (MOTA) of 63.81\% for the BotSort tracking algorithm, and micro top-1 accuracy of 63.97\% for the X3D behavior recognition model. Using deep learning to classify wildlife behavior from drone footage facilitates non-invasive insight into the collective behavior of an entire group.
Authors: Linhan Wang, Kai Cheng, Shuo Lei, Shengkun Wang, Wei Yin, Chenyang Lei, Xiaoxiao Long, Chang-Tien Lu
Abstract: We present DC-Gaussian, a new method for generating novel views from in-vehicle dash cam videos. While neural rendering techniques have made significant strides in driving scenarios, existing methods are primarily designed for videos collected by autonomous vehicles. However, these videos are limited in both quantity and diversity compared to dash cam videos, which are more widely used across various types of vehicles and capture a broader range of scenarios. Dash cam videos often suffer from severe obstructions such as reflections and occlusions on the windshields, which significantly impede the application of neural rendering techniques. To address this challenge, we develop DC-Gaussian based on the recent real-time neural rendering technique 3D Gaussian Splatting (3DGS). Our approach includes an adaptive image decomposition module to model reflections and occlusions in a unified manner. Additionally, we introduce illumination-aware obstruction modeling to manage reflections and occlusions under varying lighting conditions. Lastly, we employ a geometry-guided Gaussian enhancement strategy to improve rendering details by incorporating additional geometry priors. Experiments on self-captured and public dash cam videos show that our method not only achieves state-of-the-art performance in novel view synthesis, but also accurately reconstructing captured scenes getting rid of obstructions.
Authors: Yiyu Li, Ke Xu, Gerhard Petrus Hancke, Rynson W. H. Lau
Abstract: Images captured under sub-optimal illumination conditions may contain both over- and under-exposures. Current approaches mainly focus on adjusting image brightness, which may exacerbate the color tone distortion in under-exposed areas and fail to restore accurate colors in over-exposed regions. We observe that over- and under-exposed regions display opposite color tone distribution shifts with respect to each other, which may not be easily normalized in joint modeling as they usually do not have ``normal-exposed'' regions/pixels as reference. In this paper, we propose a novel method to enhance images with both over- and under-exposures by learning to estimate and correct such color shifts. Specifically, we first derive the color feature maps of the brightened and darkened versions of the input image via a UNet-based network, followed by a pseudo-normal feature generator to produce pseudo-normal color feature maps. We then propose a novel COlor Shift Estimation (COSE) module to estimate the color shifts between the derived brightened (or darkened) color feature maps and the pseudo-normal color feature maps. The COSE module corrects the estimated color shifts of the over- and under-exposed regions separately. We further propose a novel COlor MOdulation (COMO) module to modulate the separately corrected colors in the over- and under-exposed regions to produce the enhanced image. Comprehensive experiments show that our method outperforms existing approaches. Project webpage: https://github.com/yiyulics/CSEC.
Authors: Shuojue Yang, Qian Li, Daiyun Shen, Bingchen Gong, Qi Dou, Yueming Jin
Abstract: Tissue deformation poses a key challenge for accurate surgical scene reconstruction. Despite yielding high reconstruction quality, existing methods suffer from slow rendering speeds and long training times, limiting their intraoperative applicability. Motivated by recent progress in 3D Gaussian Splatting, an emerging technology in real-time 3D rendering, this work presents a novel fast reconstruction framework, termed Deform3DGS, for deformable tissues during endoscopic surgery. Specifically, we introduce 3D GS into surgical scenes by integrating a point cloud initialization to improve reconstruction. Furthermore, we propose a novel flexible deformation modeling scheme (FDM) to learn tissue deformation dynamics at the level of individual Gaussians. Our FDM can model the surface deformation with efficient representations, allowing for real-time rendering performance. More importantly, FDM significantly accelerates surgical scene reconstruction, demonstrating considerable clinical values, particularly in intraoperative settings where time efficiency is crucial. Experiments on DaVinci robotic surgery videos indicate the efficacy of our approach, showcasing superior reconstruction fidelity PSNR: (37.90) and rendering speed (338.8 FPS) while substantially reducing training time to only 1 minute/scene.
Authors: Haoyu Zhao, Xingyue Zhao, Lingting Zhu, Weixi Zheng, Yongchao Xu
Abstract: Robot-assisted minimally invasive surgery benefits from enhancing dynamic scene reconstruction, as it improves surgical outcomes. While Neural Radiance Fields (NeRF) have been effective in scene reconstruction, their slow inference speeds and lengthy training durations limit their applicability. To overcome these limitations, 3D Gaussian Splatting (3D-GS) based methods have emerged as a recent trend, offering rapid inference capabilities and superior 3D quality. However, these methods still struggle with under-reconstruction in both static and dynamic scenes. In this paper, we propose HFGS, a novel approach for deformable endoscopic reconstruction that addresses these challenges from spatial and temporal frequency perspectives. Our approach incorporates deformation fields to better handle dynamic scenes and introduces Spatial High-Frequency Emphasis Reconstruction (SHF) to minimize discrepancies in spatial frequency spectra between the rendered image and its ground truth. Additionally, we introduce Temporal High-Frequency Emphasis Reconstruction (THF) to enhance dynamic awareness in neural rendering by leveraging flow priors, focusing optimization on motion-intensive parts. Extensive experiments on two widely used benchmarks demonstrate that HFGS achieves superior rendering quality. Our code will be available.
Authors: Juntae Kim, Sungwon Woo, Jongho Nang
Abstract: This paper addresses image copy detection, a task in online sharing platforms for copyright protection. While previous approaches have performed exceptionally well, the large size of their networks and descriptors remains a significant disadvantage, complicating their practical application. In this paper, we propose a novel method that achieves a competitive performance by using a lightweight network and compact descriptors. By utilizing relational self-supervised distillation to transfer knowledge from a large network to a small network, we enable the training of lightweight networks with a small descriptor size. Our approach, which we call Relational selfsupervised Distillation with Compact Descriptors (RDCD), introduces relational self-supervised distillation (RSD) for flexible representation in a smaller feature space and applies contrastive learning with a hard negative (HN) loss to prevent dimensional collapse. We demonstrate the effectiveness of our method using the DISC2021, Copydays, and NDEC benchmark datasets, with which our lightweight network with compact descriptors achieves a competitive performance. For the DISC2021 benchmark, ResNet-50/EfficientNet- B0 are used as a teacher and student respectively, the micro average precision improved by 5.0%/4.9%/5.9% for 64/128/256 descriptor sizes compared to the baseline method.
Authors: Bencheng Liao, Xinggang Wang, Lianghui Zhu, Qian Zhang, Chang Huang
Abstract: Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory. However, their advantage in terms of actual runtime speed is not significant. To address this issue, we introduce Gated Linear Attention (GLA) for vision, leveraging its superior hardware-awareness and efficiency. We propose direction-wise gating to capture 1D global context through bidirectional modeling and a 2D gating locality injection to adaptively inject 2D local details into 1D global context. Our hardware-aware implementation further merges forward and backward scanning into a single kernel, enhancing parallelism and reducing memory cost and latency. The proposed model, ViG, offers a favorable trade-off in accuracy, parameters, and FLOPs on ImageNet and downstream tasks, outperforming popular Transformer and CNN-based models. Notably, ViG-S matches DeiT-B's accuracy while using only 27% of the parameters and 20% of the FLOPs, running 2$\times$ faster on $224\times224$ images. At $1024\times1024$ resolution, ViG-T uses 5.2$\times$ fewer FLOPs, saves 90% GPU memory, runs 4.8$\times$ faster, and achieves 20.7% higher top-1 accuracy than DeiT-T. These results position ViG as an efficient and scalable solution for visual representation learning. Code is available at \url{https://github.com/hustvl/ViG}.
Authors: Mahyar Bolhassani
Abstract: Coronavirus adversely has affected people worldwide. There are common symptoms between the Covid19 virus disease and other respiratory diseases like pneumonia or Influenza. Therefore, diagnosing it fast is crucial not only to save patients but also to prevent it from spreading. One of the most reliant methods of diagnosis is through X-ray images of a lung. With the help of deep learning approaches, we can teach the deep model to learn the condition of an affected lung. Therefore, it can classify the new sample as if it is a Covid19 infected patient or not. In this project, we train a deep model based on ResNet50 pretrained by ImageNet dataset and CheXNet dataset. Based on the imbalanced CoronaHack Chest X-Ray dataset introducing by Kaggle we applied both binary and multi-class classification. Also, we compare the results when using Focal loss and Cross entropy loss.
Authors: Snehal Jauhri, Ishikaa Lunawat, Georgia Chalvatzaki
Abstract: A significant challenge for real-world robotic manipulation is the effective 6DoF grasping of objects in cluttered scenes from any single viewpoint without the need for additional scene exploration. This work reinterprets grasping as rendering and introduces NeuGraspNet, a novel method for 6DoF grasp detection that leverages advances in neural volumetric representations and surface rendering. It encodes the interaction between a robot's end-effector and an object's surface by jointly learning to render the local object surface and learning grasping functions in a shared feature space. The approach uses global (scene-level) features for grasp generation and local (grasp-level) neural surface features for grasp evaluation. This enables effective, fully implicit 6DoF grasp quality prediction, even in partially observed scenes. NeuGraspNet operates on random viewpoints, common in mobile manipulation scenarios, and outperforms existing implicit and semi-implicit grasping methods. The real-world applicability of the method has been demonstrated with a mobile manipulator robot, grasping in open, cluttered spaces. Project website at https://sites.google.com/view/neugraspnet
Authors: Bilel Guetarni, Feryal Windal, Halim Benhabiles, Marianne Petit, Romain Dubois, Emmanuelle Leteurtre, Dominique Collard
Abstract: Determining lymphoma subtypes is a crucial step for better patient treatment targeting to potentially increase their survival chances. In this context, the existing gold standard diagnosis method, which relies on gene expression technology, is highly expensive and time-consuming, making it less accessibility. Although alternative diagnosis methods based on IHC (immunohistochemistry) technologies exist (recommended by the WHO), they still suffer from similar limitations and are less accurate. Whole Slide Image (WSI) analysis using deep learning models has shown promising potential for cancer diagnosis, that could offer cost-effective and faster alternatives to existing methods. In this work, we propose a vision transformer-based framework for distinguishing DLBCL (Diffuse Large B-Cell Lymphoma) cancer subtypes from high-resolution WSIs. To this end, we introduce a multi-modal architecture to train a classifier model from various WSI modalities. We then leverage this model through a knowledge distillation process to efficiently guide the learning of a mono-modal classifier. Our experimental study conducted on a lymphoma dataset of 157 patients shows the promising performance of our mono-modal classification model, outperforming six recent state-of-the-art methods. In addition, the power-law curve, estimated on our experimental data, suggests that with more training data from a reasonable number of additional patients, our model could achieve competitive diagnosis accuracy with IHC technologies. Furthermore, the efficiency of our framework is confirmed through an additional experimental study on an external breast cancer dataset (BCI dataset).
Authors: Zihao Yue, Liang Zhang, Qin Jin
Abstract: Large Multimodal Models (LMMs) often suffer from multimodal hallucinations, wherein they may create content that is not present in the visual inputs. In this paper, we explore a new angle of this issue: overly detailed training data hinders the model's ability to timely terminate generation, leading to continued outputs beyond visual perception limits. By investigating how the model decides to terminate generation with EOS, the special end-of-sentence token, we find that the model assesses the completeness of the entire sequence by comparing the generated text with the image. This observation suggests that the model possesses an inherent potential of making proper EOS decisions based on its visual perception to avoid overly lengthy outputs. To take advantage of such potential, we explore two methods to mitigate multimodal hallucinations: a training objective that enables the model to reduce hallucinations by learning from regular instruction data, and a data filtering strategy to prevent harmful training data from exacerbating model hallucinations. Both methods significantly improve the hallucination performance of LMMs, without requiring any additional data or knowledge.
Authors: Xiang Li, Soo Min Kwon, Ismail R. Alkhouri, Saiprasad Ravishankar, Qing Qu
Abstract: Diffusion models have recently gained traction as a powerful class of deep generative priors, excelling in a wide range of image restoration tasks due to their exceptional ability to model data distributions. To solve image restoration problems, many existing techniques achieve data consistency by incorporating additional likelihood gradient steps into the reverse sampling process of diffusion models. However, the additional gradient steps pose a challenge for real-world practical applications as they incur a large computational overhead, thereby increasing inference time. They also present additional difficulties when using accelerated diffusion model samplers, as the number of data consistency steps is limited by the number of reverse sampling steps. In this work, we propose a novel diffusion-based image restoration solver that addresses these issues by decoupling the reverse process from the data consistency steps. Our method involves alternating between a reconstruction phase to maintain data consistency and a refinement phase that enforces the prior via diffusion purification. Our approach demonstrates versatility, making it highly adaptable for efficient problem-solving in latent space. Additionally, it reduces the necessity for numerous sampling steps through the integration of consistency models. The efficacy of our approach is validated through comprehensive experiments across various image restoration tasks, including image denoising, deblurring, inpainting, and super-resolution.
Authors: Siting Zhu, Renjie Qin, Guangming Wang, Jiuming Liu, Hesheng Wang
Abstract: We propose SemGauss-SLAM, a dense semantic SLAM system utilizing 3D Gaussian representation, that enables accurate 3D semantic mapping, robust camera tracking, and high-quality rendering simultaneously. In this system, we incorporate semantic feature embedding into 3D Gaussian representation, which effectively encodes semantic information within the spatial layout of the environment for precise semantic scene representation. Furthermore, we propose feature-level loss for updating 3D Gaussian representation, enabling higher-level guidance for 3D Gaussian optimization. In addition, to reduce cumulative drift in tracking and improve semantic reconstruction accuracy, we introduce semantic-informed bundle adjustment leveraging multi-frame semantic associations for joint optimization of 3D Gaussian representation and camera poses, leading to low-drift tracking and accurate mapping. Our SemGauss-SLAM method demonstrates superior performance over existing radiance field-based SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in high-precision semantic segmentation and dense semantic mapping.
Authors: Yifei Shen, Xinyang Jiang, Yezhen Wang, Yifan Yang, Dongqi Han, Dongsheng Li
Abstract: Adding additional control to pretrained diffusion models has become an increasingly popular research area, with extensive applications in computer vision, reinforcement learning, and AI for science. Recently, several studies have proposed training-free loss-based guidance by using off-the-shelf networks pretrained on clean images. This approach enables zero-shot conditional generation for universal control formats, which appears to offer a free lunch in diffusion guidance. In this paper, we aim to develop a deeper understanding of training-free guidance, as well as overcome its limitations. We offer a theoretical analysis that supports training-free guidance from the perspective of optimization, distinguishing it from classifier-based (or classifier-free) guidance. To elucidate their drawbacks, we theoretically demonstrate that training-free guidance is more susceptible to adversarial gradients and exhibits slower convergence rates compared to classifier guidance. We then introduce a collection of techniques designed to overcome the limitations, accompanied by theoretical rationale and empirical evidence. Our experiments in image and motion generation confirm the efficacy of these techniques.
Authors: Kavian Khanjani, Seyed Rasoul Hosseini, Hamid Taheri, Shahrzad Shashaani, Mohammad Teshnehlab
Abstract: In 2019, the world faced a new challenge: a COVID-19 disease caused by the novel coronavirus, SARS-CoV-2. The virus rapidly spread across the globe, leading to a high rate of mortality, which prompted health organizations to take measures to control its transmission. Early disease detection is crucial in the treatment process, and computer-based automatic detection systems have been developed to aid in this effort. These systems often rely on artificial intelligence (AI) approaches such as machine learning, neural networks, fuzzy systems, and deep learning to classify diseases. This study aimed to differentiate COVID-19 patients from others using self-categorizing classifiers and employing various AI methods. This study used two datasets: the blood test samples and radiography images. The best results for the blood test samples obtained from San Raphael Hospital, which include two classes of individuals, those with COVID-19 and those with non-COVID diseases, were achieved through the use of the Ensemble method (a combination of a neural network and two machines learning methods). The results showed that this approach for COVID-19 diagnosis is cost-effective and provides results in a shorter amount of time than other methods. The proposed model achieved an accuracy of 94.09% on the dataset used. Secondly, the radiographic images were divided into four classes: normal, viral pneumonia, ground glass opacity, and COVID-19 infection. These were used for segmentation and classification. The lung lobes were extracted from the images and then categorized into specific classes. We achieved an accuracy of 91.1% on the image dataset. Generally, this study highlights the potential of AI in detecting and managing COVID-19 and underscores the importance of continued research and development in this field.
Authors: Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kiant\'e Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun
Abstract: While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g. value networks, clipping), and is notorious for its sensitivity to the precise implementation of these components. In response, we take a step back and ask what a minimalist RL algorithm for the era of generative models would look like. We propose REBEL, an algorithm that cleanly reduces the problem of policy optimization to regressing the relative reward between two completions to a prompt in terms of the policy, enabling strikingly lightweight implementation. In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL, which allows us to match the strongest known theoretical guarantees in terms of convergence and sample complexity in the RL literature. REBEL can also cleanly incorporate offline data and be extended to handle the intransitive preferences we frequently see in practice. Empirically, we find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO, all while being simpler to implement and more computationally efficient than PPO. When fine-tuning Llama-3-8B-Instruct, REBEL achieves strong performance in AlpacaEval 2.0, MT-Bench, and Open LLM Leaderboard.
Authors: Qiji Zhou, Ruochen Zhou, Zike Hu, Panzhong Lu, Siyang Gao, Yue Zhang
Abstract: Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Large Language Models (MLLMs), enhancing their capability to tackle complex multimodal reasoning problems is a crucial frontier. However, incorporating multimodal rationales in CoT has yet to be thoroughly investigated. We propose the Image-of-Thought (IoT) prompting method, which helps MLLMs to extract visual rationales step-by-step. Specifically, IoT prompting can automatically design critical visual information extraction operations based on the input images and questions. Each step of visual information refinement identifies specific visual rationales that support answers to complex visual reasoning questions. Beyond the textual CoT, IoT simultaneously utilizes visual and textual rationales to help MLLMs understand complex multimodal information. IoT prompting has improved zero-shot visual reasoning performance across various visual understanding tasks in different MLLMs. Moreover, the step-by-step visual feature explanations generated by IoT prompting elucidate the visual reasoning process, aiding in analyzing the cognitive processes of large multimodal models
Authors: Shengfang Zhai, Huanran Chen, Yinpeng Dong, Jiajun Li, Qingni Shen, Yansong Gao, Hang Su, Yang Liu
Abstract: Text-to-image diffusion models have achieved tremendous success in the field of controllable image generation, while also coming along with issues of privacy leakage and data copyrights. Membership inference arises in these contexts as a potential auditing method for detecting unauthorized data usage. While some efforts have been made on diffusion models, they are not applicable to text-to-image diffusion models due to the high computation overhead and enhanced generalization capabilities. In this paper, we first identify a conditional overfitting phenomenon in text-to-image diffusion models, indicating that these models tend to overfit the conditional distribution of images given the text rather than the marginal distribution of images. Based on this observation, we derive an analytical indicator, namely Conditional Likelihood Discrepancy (CLiD), to perform membership inference, which reduces the stochasticity in estimating the memorization of individual samples. Experimental results demonstrate that our method significantly outperforms previous methods across various data distributions and scales. Additionally, our method shows superior resistance to overfitting mitigation strategies such as early stopping and data augmentation.
Authors: Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort
Abstract: Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when outliers are present. Recent findings suggest that rotating activation or weight matrices helps remove outliers and benefits quantization. In this work, we identify a collection of applicable rotation parameterizations that lead to identical outputs in full-precision Transformer architectures, and find that some random rotations lead to much better quantization than others, with an up to 13 points difference in downstream zero-shot reasoning performance. As a result, we propose SpinQuant that optimizes (or learns) the rotation matrices with Cayley optimization on a small validation set. With 4-bit quantization of weight, activation, and KV-cache, SpinQuant narrows the accuracy gap on zero-shot reasoning tasks with full precision to merely 2.9 points on the LLaMA-2 7B model, surpassing LLM-QAT by 19.1 points and SmoothQuant by 25.0 points. SpinQuant also outperforms concurrent work QuaRot, which applies random rotations to remove outliers. In particular, for LLaMA-2 7B/LLaMA-3 8B models that are hard to quantize, SpinQuant reduces the gap to full precision by 30.2%/34.1% relative to QuaRot.