Authors: Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Jia Cai, Feipeng Cai, Xiaolin Huang, Jie Yang
Deep Neural Networks (DNNs) are vulnerable to invisible perturbations on the images generated by adversarial attacks, which raises researches on the adversarial robustness of DNNs. A series of methods represented by the adversarial training and its variants have proven as one of the most effective techniques in enhancing the DNN robustness. Generally, adversarial training focuses on enriching the training data by involving perturbed data. Such data augmentation effect of the involved perturbed data in adversarial training does not contribute to the robustness of DNN itself and usually suffers from clean accuracy drop. Towards the robustness of DNN itself, we in this paper propose a novel defense that aims at augmenting the model in order to learn features that are adaptive to diverse inputs, including adversarial examples. More specifically, to augment the model, multiple paths are embedded into the network, and an orthogonality constraint is imposed on these paths to guarantee the diversity among them. A margin-maximization loss is then designed to further boost such DIversity via Orthogonality (DIO). In this way, the proposed DIO augments the model and enhances the robustness of DNN itself as the learned features can be corrected by these mutually-orthogonal paths. Extensive empirical results on various data sets, structures and attacks verify the stronger adversarial robustness of the proposed DIO utilizing model augmentation. Besides, DIO can also be flexibly combined with different data augmentation techniques (e.g., TRADES and DDPM), further promoting robustness gains.
Authors: Ming Lu, Tong Chen, Dandan Ding, Fengqing Zhu, Zhan Ma
Inspired by the facts that retinal cells actually segregate the visual scene into different attributes (e.g., spatial details, temporal motion) for respective neuronal processing, we propose to first decompose the input video into respective spatial texture frames (STF) at its native spatial resolution that preserve the rich spatial details, and the other temporal motion frames (TMF) at a lower spatial resolution that retain the motion smoothness; then compress them together using any popular video coder; and finally synthesize decoded STFs and TMFs for high-fidelity video reconstruction at the same resolution as its native input. This work simply applies the bicubic resampling in decomposition and HEVC compliant codec in compression, and puts the focus on the synthesis part. For resolution-adaptive synthesis, a motion compensation network (MCN) is devised on TMFs to efficiently align and aggregate temporal motion features that will be jointly processed with corresponding STFs using a non-local texture transfer network (NL-TTN) to better augment spatial details, by which the compression and resolution resampling noises can be effectively alleviated with better rate-distortion efficiency. Such "Decomposition, Compression, Synthesis (DCS)" based scheme is codec agnostic, currently exemplifying averaged $\approx$1 dB PSNR gain or $\approx$25% BD-rate saving, against the HEVC anchor using reference software. In addition, experimental comparisons to the state-of-the-art methods and ablation studies are conducted to further report the efficiency and generalization of DCS algorithm, promising an encouraging direction for future video coding.
Authors: Reina Kaneko, Yuya Sato, Takumi Ueda, Hiroshi Higashi, Yuichi Tanaka
This paper introduces a new benchmarking dataset for marine snow removal of underwater images. Marine snow is one of the main degradation sources of underwater images that are caused by small particles, e.g., organic matter and sand, between the underwater scene and photosensors. We mathematically model two typical types of marine snow from the observations of real underwater images. The modeled artifacts are synthesized with underwater images to construct large-scale pairs of ground truth and degraded images to calculate objective qualities for marine snow removal and to train a deep neural network. We propose two marine snow removal tasks using the dataset and show the first benchmarking results of marine snow removal. The Marine Snow Removal Benchmarking Dataset is publicly available online.
Authors: Shawn L. Beaulieu, Jeff Clune, Nick Cheney
Existing machines are functionally specific tools that were made for easy prediction and control. Tomorrow's machines may be closer to biological systems in their mutability, resilience, and autonomy. But first they must be capable of learning and retaining new information without being exposed to it arbitrarily often. Past efforts to engineer such systems have sought to build or regulate artificial neural networks using disjoint sets of weights that are uniquely sensitive to specific tasks or inputs. This has not yet enabled continual learning over long sequences of previously unseen data without corrupting existing knowledge: a problem known as catastrophic forgetting. In this paper, we introduce a system that can learn sequentially over previously unseen datasets (ImageNet, CIFAR-100) with little forgetting over time. This is done by controlling the activity of weights in a convolutional neural network on the basis of inputs using top-down regulation generated by a second feed-forward neural network. We find that our method learns continually under domain transfer with sparse bursts of activity in weights that are recycled across tasks, rather than by maintaining task-specific modules. Sparse synaptic bursting is found to balance activity and suppression such that new functions can be learned without corrupting extant knowledge, thus mirroring the balance of order and disorder in systems at the edge of chaos. This behavior emerges during a prior pre-training (or 'meta-learning') phase in which regulated synapses are selectively disinhibited, or grown, from an initial state of uniform suppression through prediction error minimization.
Authors: Geri Skenderi, Christian Joppi, Matteo Denitto, Marco Cristani
New fashion product sales forecasting is a challenging problem that involves many business dynamics and cannot be solved by classical forecasting approaches. In this paper, we investigate the effectiveness of systematically probing exogenous knowledge in the form of Google Trends time series and combining it with multi-modal information related to a brand-new fashion item, in order to effectively forecast its sales despite the lack of past data. In particular, we propose a neural network-based approach, where an encoder learns a representation of the exogenous time series, while the decoder forecasts the sales based on the Google Trends encoding and the available visual and metadata information. Our model works in a non-autoregressive manner, avoiding the compounding effect of large first-step errors. As a second contribution, we present VISUELLE, a publicly available dataset for the task of new fashion product sales forecasting, containing multimodal information for 5577 real, new products sold between 2016-2019 from Nunalie, an Italian fast-fashion company. The dataset is equipped with images of products, metadata, related sales, and associated Google Trends. We use VISUELLE to compare our approach against state-of-the-art alternatives and several baselines, showing that our neural network-based approach is the most accurate in terms of both percentage and absolute error. It is worth noting that the addition of exogenous knowledge boosts the forecasting accuracy by 1.5% in terms of Weighted Absolute Percentage Error (WAPE), revealing the importance of exploiting informative external information. The code and dataset are both available at https://github.com/HumaticsLAB/GTM-Transformer.
Authors: Moritz Böhle, Mario Fritz, Bernt Schiele
We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks are Dynamic Alignment Units (DAUs), which are optimised to transform their inputs with dynamically computed weight vectors that align with task-relevant patterns. As a result, CoDA Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions. Given the alignment of the DAUs, the resulting contribution maps align with discriminative input patterns. These model-inherent decompositions are of high visual quality and outperform existing attribution methods under quantitative metrics. Further, CoDA Nets constitute performant classifiers, achieving on par results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet. Lastly, CoDA Nets can be combined with conventional neural network models to yield powerful classifiers that more easily scale to complex datasets such as Imagenet whilst exhibiting an increased interpretable depth, i.e., the output can be explained well in terms of contributions from intermediate layers within the network.
Authors: Haoyu He, Jianfei Cai, Jing Liu, Zizheng Pan, Jing Zhang, Dacheng Tao, Bohan Zhuang
Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive computational resource consumption and the lack of intrinsic inductive bias for modeling local visual patterns. To solve both issues, we devise a simple yet effective method named Single-Path Vision Transformer pruning (SPViT), to efficiently and automatically compress the pre-trained ViTs into compact models with proper locality added. Specifically, we first propose a novel weight-sharing scheme between MSA and convolutional operations, delivering a single-path space to encode all candidate operations. In this way, we cast the operation search problem as finding which subset of parameters to use in each MSA layer, which significantly reduces the computational cost and optimization difficulty, and the convolution kernels can be well initialized using pre-trained MSA parameters. Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers. Similarly, we further employ learnable gates to encode the fine-grained MLP expansion ratios of FFN layers. In this way, our SPViT optimizes the learnable gates to automatically explore from a vast and unified search space and flexibly adjust the MSA-FFN pruning proportions for each individual dense model. We conduct extensive experiments on two representative ViTs showing that our SPViT achieves a new SOTA for pruning on ImageNet-1k. For example, our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously. The source code is available at https://github.com/ziplab/SPViT.
Authors: Jin Yuan, Shikai Chen, Yao Zhang, Zhongchao Shi, Xin Geng, Jianping Fan, Yong Rui
Multi-label classification aims to recognize multiple objects or attributes from images. However, it is challenging to learn from proper label graphs to effectively characterize such inter-label correlations or dependencies. Current methods often use the co-occurrence probability of labels based on the training set as the adjacency matrix to model this correlation, which is greatly limited by the dataset and affects the model's generalization ability. In this paper, we propose a Graph Attention Transformer Network (GATN), a general framework for multi-label image classification that can effectively mine complex inter-label relationships. First, we use the cosine similarity based on the label word embedding as the initial correlation matrix, which can represent rich semantic information. Subsequently, we design the graph attention transformer layer to transfer this adjacency matrix to adapt to the current domain. Our extensive experiments have demonstrated that our proposed methods can achieve state-of-the-art performance on three datasets.
Authors: Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
Synthetic high-resolution (HR) \& low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing (degrading) process via a deterministic model. However, some degradations in real scenarios are stochastic and cannot be determined by the content of the image. These deterministic models may fail to model the random factors and content-independent parts of degradations, which will limit the performance of the following SR models. In this paper, we propose a probabilistic degradation model (PDM), which studies the degradation $\mathbf{D}$ as a random variable, and learns its distribution by modeling the mapping from a priori random variable $\mathbf{z}$ to $\mathbf{D}$. Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones. Extensive experiments have demonstrated that our degradation model can help the SR model achieve better performance on different datasets. The source codes are released at \url{git@github.com:greatlog/UnpairedSR.git}.
Authors: Lin Xi, Weihai Chen, Xingming Wu, Zhong Liu, Zhengguo Li
Unsupervised video object segmentation (UVOS) aims at automatically separating the primary foreground object(s) from the background in a video sequence. Existing UVOS methods either lack robustness when there are visually similar surroundings (appearance-based) or suffer from deterioration in the quality of their predictions because of dynamic background and inaccurate flow (flow-based). To overcome the limitations, we propose an implicit motion-compensated network (IMCNet) combining complementary cues ($\textit{i.e.}$, appearance and motion) with aligned motion information from the adjacent frames to the current frame at the feature level without estimating optical flows. The proposed IMCNet consists of an affinity computing module (ACM), an attention propagation module (APM), and a motion compensation module (MCM). The light-weight ACM extracts commonality between neighboring input frames based on appearance features. The APM then transmits global correlation in a top-down manner. Through coarse-to-fine iterative inspiring, the APM will refine object regions from multiple resolutions so as to efficiently avoid losing details. Finally, the MCM aligns motion information from temporally adjacent frames to the current frame which achieves implicit motion compensation at the feature level. We perform extensive experiments on $\textit{DAVIS}_{\textit{16}}$ and $\textit{YouTube-Objects}$. Our network achieves favorable performance while running at a faster speed compared to the state-of-the-art methods.
Authors: Philipp Flotho, Cosmas Heiss, Gabriele Steidl, Daniel J. Strauss
Microexpressions are fast and spatially small facial expressions that are difficult to detect. Therefore motion magnification techniques, which aim at amplifying and hence revealing subtle motion in videos, appear useful for handling such expressions. There are basically two main approaches, namely via Eulerian or Lagrangian techniques. While the first one magnifies motion implicitly by operating directly on image pixels, the Lagrangian approach uses optical flow (OF) techniques to extract and magnify pixel trajectories. In this paper, we propose a novel approach for local Lagrangian motion magnification of facial micro-motions. Our contribution is three-fold: first, we fine tune the recurrent all-pairs field transforms (RAFT) for OFs deep learning approach for faces by adding ground truth obtained from the variational dense inverse search (DIS) for OF algorithm applied to the CASME II video set of facial micro expressions. This enables us to produce OFs of facial videos in an efficient and sufficiently accurate way. Second, since facial micro-motions are both local in space and time, we propose to approximate the OF field by sparse components both in space and time leading to a double sparse decomposition. Third, we use this decomposition to magnify micro-motions in specific areas of the face, where we introduce a new forward warping strategy using a triangular splitting of the image grid and barycentric interpolation of the RGB vectors at the corners of the transformed triangles. We demonstrate the feasibility of our approach by various examples.
Authors: Zijian Ying, Qianmu Li, Zhichao Lian, Jun Hou, Tong Lin, Tao Wang
Saliency maps have proven to be a highly efficacious approach for explicating the decisions of Convolutional Neural Networks. However, extant methodologies predominantly rely on gradients, which constrain their ability to explicate complex models. Furthermore, such approaches are not fully adept at leveraging negative gradient information to improve interpretive veracity. In this study, we present a novel concept, termed positive and negative excitation, which enables the direct extraction of positive and negative excitation for each layer, thus enabling complete layer-by-layer information utilization sans gradients. To organize these excitations into final saliency maps, we introduce a double-chain backpropagation procedure. A comprehensive experimental evaluation, encompassing both binary classification and multi-classification tasks, was conducted to gauge the effectiveness of our proposed method. Encouragingly, the results evince that our approach offers a significant improvement over the state-of-the-art methods in terms of salient pixel removal, minor pixel removal, and inconspicuous adversarial perturbation generation guidance. Additionally, we verify the correlation between positive and negative excitations.
Authors: Thibault Clérice (ENC, CJM, HiSoMA, UJML, ALMAnaCH)
Layout Analysis (the identification of zones and their classification) is the first step along line segmentation in Optical Character Recognition and similar tasks. The ability of identifying main body of text from marginal text or running titles makes the difference between extracting the work full text of a digitized book and noisy outputs. We show that most segmenters focus on pixel classification and that polygonization of this output has not been used as a target for the latest competition on historical document (ICDAR 2017 and onwards), despite being the focus in the early 2010s. We propose to shift, for efficiency, the task from a pixel classification-based polygonization to an object detection using isothetic rectangles. We compare the output of Kraken and YOLOv5 in terms of segmentation and show that the later severely outperforms the first on small datasets (1110 samples and below). We release two datasets for training and evaluation on historical documents as well as a new package, YALTAi, which injects YOLOv5 in the segmentation pipeline of Kraken 4.1.
Authors: Jonathan Fhima, Jan Van Eijgen, Moti Freiman, Ingeborg Stalmans, Joachim A. Behar
Introduction: For supervised deep learning (DL) tasks, researchers need a large annotated dataset. In medical data science, one of the major limitations to develop DL models is the lack of annotated examples in large quantity. This is most often due to the time and expertise required to annotate. We introduce Lirot. ai, a novel platform for facilitating and crowd-sourcing image segmentations. Methods: Lirot. ai is composed of three components; an iPadOS client application named Lirot. ai-app, a backend server named Lirot. ai-server and a python API name Lirot. ai-API. Lirot. ai-app was developed in Swift 5.6 and Lirot. ai-server is a firebase backend. Lirot. ai-API allows the management of the database. Lirot. ai-app can be installed on as many iPadOS devices as needed so that annotators may be able to perform their segmentation simultaneously and remotely. We incorporate Apple Pencil compatibility, making the segmentation faster, more accurate, and more intuitive for the expert than any other computer-based alternative. Results: We demonstrate the usage of Lirot. ai for the creation of a retinal fundus dataset with reference vasculature segmentations. Discussion and future work: We will use active learning strategies to continue enlarging our retinal fundus dataset by including a more efficient process to select the images to be annotated and distribute them to annotators.
Authors: Eddy Zhou, Alex Zhuang, Alikasim Budhwani, Owen Leather, Rowan Dempster, Quanquan Li, Mohammad Al-Sharman, Derek Rayside, William Melek
When applied to autonomous vehicle (AV) settings, action recognition can enhance an environment model's situational awareness. This is especially prevalent in scenarios where traditional geometric descriptions and heuristics in AVs are insufficient. However, action recognition has traditionally been studied for humans, and its limited adaptability to noisy, un-clipped, un-pampered, raw RGB data has limited its application in other fields. To push for the advancement and adoption of action recognition into AVs, this work proposes a novel two-stage action recognition system, termed RALACs. RALACs formulates the problem of action recognition for road scenes, and bridges the gap between it and the established field of human action recognition. This work shows how attention layers can be useful for encoding the relations across agents, and stresses how such a scheme can be class-agnostic. Furthermore, to address the dynamic nature of agents on the road, RALACs constructs a novel approach to adapting Region of Interest (ROI) Alignment to agent tracks for downstream action classification. Finally, our scheme also considers the problem of active agent detection, and utilizes a novel application of fusing optical flow maps to discern relevant agents in a road scene. We show that our proposed scheme can outperform the baseline on the ICCV2021 Road Challenge dataset and by deploying it on a real vehicle platform, we provide preliminary insight to the usefulness of action recognition in decision making.
Authors: Pengjin Wei, Guohang Yan, Yikang Li, Kun Fang, Jie Yang, Wei Liu
With the development of neural networks and the increasing popularity of automatic driving, the calibration of the LiDAR and the camera has attracted more and more attention. This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks. Current research interests mainly focus on obtaining accurate calibration results through information fusion. However, they seldom analyze whether the calibrated results are correct or not, which could be of significant importance in real-world applications. For example, in large-scale production, the LiDARs and the cameras of each smart car have to get well-calibrated as the car leaves the production line, while in the rest of the car life period, the poses of the LiDARs and cameras should also get continually supervised to ensure the security. To this end, this paper proposes a self-checking algorithm to judge whether the extrinsic parameters are well-calibrated by introducing a binary classification network based on the fused information from the camera and the LiDAR. Moreover, since there is no such dataset for the task in this work, we further generate a new dataset branch from the KITTI dataset tailored for the task. Our experiments on the proposed dataset branch demonstrate the performance of our method. To the best of our knowledge, this is the first work to address the significance of continually checking the calibrated extrinsic parameters for autonomous driving. The code is open-sourced on the Github website at https://github.com/OpenCalib/LiDAR2camera_self-check.
Authors: Shengchao Chen, Sufen Ren, Guanjun Wang, Mengxing Huang, Chenyang Xue
Chest imaging plays an essential role in diagnosing and predicting patients with COVID-19 with evidence of worsening respiratory status. Many deep learning-based approaches for pneumonia recognition have been developed to enable computer-aided diagnosis. However, the long training and inference time makes them inflexible, and the lack of interpretability reduces their credibility in clinical medical practice. This paper aims to develop a pneumonia recognition framework with interpretability, which can understand the complex relationship between lung features and related diseases in chest X-ray (CXR) images to provide high-speed analytics support for medical practice. To reduce the computational complexity to accelerate the recognition process, a novel multi-level self-attention mechanism within Transformer has been proposed to accelerate convergence and emphasize the task-related feature regions. Moreover, a practical CXR image data augmentation has been adopted to address the scarcity of medical image data problems to boost the model's performance. The effectiveness of the proposed method has been demonstrated on the classic COVID-19 recognition task using the widespread pneumonia CXR image dataset. In addition, abundant ablation experiments validate the effectiveness and necessity of all of the components of the proposed method.
Authors: Wei Jiang, Jiayu Yang, Yongqi Zhai, Peirong Ning, Feng Gao, Ronggang Wang
Recently, learned image compression has achieved remarkable performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in boosting rate-distortion performance. However, most entropy models only capture correlations in one dimension, while the latent representation contain channel-wise, local spatial, and global spatial correlations. To tackle this issue, we propose the Multi-Reference Entropy Model (MEM) and the advanced version, MEM$^+$. These models capture the different types of correlations present in latent representation. Specifically, We first divide the latent representation into slices. When decoding the current slice, we use previously decoded slices as context and employ the attention map of the previously decoded slice to predict global correlations in the current slice. To capture local contexts, we introduce two enhanced checkerboard context capturing techniques that avoids performance degradation. Based on MEM and MEM$^+$, we propose image compression models MLIC and MLIC$^+$. Extensive experimental evaluations demonstrate that our MLIC and MLIC$^+$ models achieve state-of-the-art performance, reducing BD-rate by $8.05\%$ and $11.39\%$ on the Kodak dataset compared to VTM-17.0 when measured in PSNR. Our code is available at https://github.com/JiangWeibeta/MLIC.
Authors: Haoran You, Yunyang Xiong, Xiaoliang Dai, Bichen Wu, Peizhao Zhang, Haoqi Fan, Peter Vajda, Yingyan Lin
Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a quadratic complexity with the number of input tokens. Existing efficient ViTs adopt local attention (e.g., Swin) or linear attention (e.g., Performer), which sacrifice ViTs' capabilities of capturing either global or local context. In this work, we ask an important research question: Can ViTs learn both global and local context while being more efficient during inference? To this end, we propose a framework called Castling-ViT, which trains ViTs using both linear-angular attention and masked softmax-based quadratic attention, but then switches to having only linear angular attention during ViT inference. Our Castling-ViT leverages angular kernels to measure the similarities between queries and keys via spectral angles. And we further simplify it with two techniques: (1) a novel linear-angular attention mechanism: we decompose the angular kernels into linear terms and high-order residuals, and only keep the linear terms; and (2) we adopt two parameterized modules to approximate high-order residuals: a depthwise convolution and an auxiliary masked softmax attention to help learn both global and local information, where the masks for softmax attention are regularized to gradually become zeros and thus incur no overhead during ViT inference. Extensive experiments and ablation studies on three tasks consistently validate the effectiveness of the proposed Castling-ViT, e.g., achieving up to a 1.8% higher accuracy or 40% MACs reduction on ImageNet classification and 1.2 higher mAP on COCO detection under comparable FLOPs, as compared to ViTs with vanilla softmax-based attentions.
Authors: Lemeng Wu, Dilin Wang, Meng Li, Yunyang Xiong, Raghuraman Krishnamoorthi, Qiang Liu, Vikas Chandra
Fusing 3D LiDAR features with 2D camera features is a promising technique for enhancing the accuracy of 3D detection, thanks to their complementary physical properties. While most of the existing methods focus on directly fusing camera features with raw LiDAR point clouds or shallow-level 3D features, it is observed that directly combining 2D and 3D features in deeper layers actually leads to a decrease in accuracy due to feature misalignment. The misalignment, which stems from the aggregation of features learned from large receptive fields, becomes increasingly more severe as we delve into deeper layers. In this paper, we propose PathFusion as a solution to enable the alignment of semantically coherent LiDAR-camera deep feature fusion. PathFusion introduces a path consistency loss at multiple stages within the network, encouraging the 2D backbone and its fusion path to transform 2D features in a way that aligns semantically with the transformation of the 3D backbone. This ensures semantic consistency between 2D and 3D features, even in deeper layers, and amplifies the usage of the network's learning capacity. We apply PathFusion to improve a prior-art fusion baseline, Focals Conv, and observe an improvement of over 1.6% in mAP on the nuScenes test split consistently with and without testing-time data augmentations, and moreover, PathFusion also improves KITTI $\text{AP}_{\text{3D}}$ (R11) by about 0.6% on the moderate level.
Authors: Xiaopin Zhong, Guankun Wang, Weixiang Liu, Zongze Wu, Yuanlong Deng
As a fundamental computer vision task, crowd counting plays an important role in public safety. Currently, deep learning based head detection is a promising method for crowd counting. However, the highly concerned object detection networks cannot be well applied to this problem for three reasons: (1) Existing loss functions fail to address sample imbalance in highly dense and complex scenes; (2) Canonical object detectors lack spatial coherence in loss calculation, disregarding the relationship between object location and background region; (3) Most of the head detection datasets are only annotated with the center points, i.e. without bounding boxes. To overcome these issues, we propose a novel Mask Focal Loss (MFL) based on heatmap via the Gaussian kernel. MFL provides a unifying framework for the loss functions based on both heatmap and binary feature map ground truths. Additionally, we introduce GTA_Head, a synthetic dataset with comprehensive annotations, for evaluation and comparison. Extensive experimental results demonstrate the superior performance of our MFL across various detectors and datasets, and it can reduce MAE and RMSE by up to 47.03% and 61.99%, respectively. Therefore, our work presents a strong foundation for advancing crowd counting methods based on density estimation.
Authors: Siddeshwar Raghavan, Jiangpeng He, Fengqing Zhu
Food image classification is essential for monitoring health and tracking dietary in image-based dietary assessment methods. However, conventional systems often rely on static datasets with fixed classes and uniform distribution. In contrast, real-world food consumption patterns, shaped by cultural, economic, and personal influences, involve dynamic and evolving data. Thus, require the classification system to cope with continuously evolving data. Online Class Incremental Learning (OCIL) addresses the challenge of learning continuously from a single-pass data stream while adapting to the new knowledge and reducing catastrophic forgetting. Experience Replay (ER) based OCIL methods store a small portion of previous data and have shown encouraging performance. However, most existing OCIL works assume that the distribution of encountered data is perfectly balanced, which rarely happens in real-world scenarios. In this work, we explore OCIL for real-world food image classification by first introducing a probabilistic framework to simulate realistic food consumption scenarios. Subsequently, we present an attachable Dynamic Model Update (DMU) module designed for existing ER methods, which enables the selection of relevant images for model training, addressing challenges arising from data repetition and imbalanced sample occurrences inherent in realistic food consumption patterns within the OCIL framework. Our performance evaluation demonstrates significant enhancements compared to established ER methods, showing great potential for lifelong learning in real-world food image classification scenarios. The code of our method is publicly accessible at https://gitlab.com/viper-purdue/OCIL-real-world-food-image-classification
Authors: Pierre-Yves Lajoie, Giovanni Beltrame
Collaborative Simultaneous Localization And Mapping (C-SLAM) is a vital component for successful multi-robot operations in environments without an external positioning system, such as indoors, underground or underwater. In this paper, we introduce Swarm-SLAM, an open-source C-SLAM system that is designed to be scalable, flexible, decentralized, and sparse, which are all key properties in swarm robotics. Our system supports inertial, lidar, stereo, and RGB-D sensing, and it includes a novel inter-robot loop closure prioritization technique that reduces communication and accelerates convergence. We evaluated our ROS-2 implementation on five different datasets, and in a real-world experiment with three robots communicating through an ad-hoc network. Our code is publicly available: https://github.com/MISTLab/Swarm-SLAM
Authors: Balamurali Murugesan, Sukesh Adiga V, Bingyuan Liu, Hervé Lombaert, Ismail Ben Ayed, Jose Dolz
Ensuring reliable confidence scores from deep networks is of pivotal importance in critical decision-making systems, notably in the medical domain. While recent literature on calibrating deep segmentation networks has led to significant progress, their uncertainty is usually modeled by leveraging the information of individual pixels, which disregards the local structure of the object of interest. In particular, only the recent Spatially Varying Label Smoothing (SVLS) approach addresses this issue by softening the pixel label assignments with a discrete spatial Gaussian kernel. In this work, we first present a constrained optimization perspective of SVLS and demonstrate that it enforces an implicit constraint on soft class proportions of surrounding pixels. Furthermore, our analysis shows that SVLS lacks a mechanism to balance the contribution of the constraint with the primary objective, potentially hindering the optimization process. Based on these observations, we propose a principled and simple solution based on equality constraints on the logit values, which enables to control explicitly both the enforced constraint and the weight of the penalty, offering more flexibility. Comprehensive experiments on a variety of well-known segmentation benchmarks demonstrate the superior performance of the proposed approach.
Authors: Jincheng Zhang, Kevin Brink, Andrew R Willis
Infrared thermography has been widely used in several domains to capture and measure temperature distributions across surfaces and objects. This methodology can be further expanded to 3D applications if the spatial distribution of the temperature distribution is available. Structure from Motion (SfM) is a photometric range imaging technique that makes it possible to obtain 3D renderings from a cloud of 2D images. To explore the possibility of 3D reconstruction via SfM from infrared images, this article proposes a photometric correction model for infrared sensors based on temperature constancy. Photometric correction is accomplished by estimating the scene irradiance as the values from the solution to a differential equation for microbolometer pixel excitation with unknown coefficients and initial conditions. The model was integrated into an SfM framework and experimental evaluations demonstrate the contribution of the photometric correction for improving the estimates of both the camera motion and the scene structure. Further, experiments show that the reconstruction quality from the corrected infrared imagery achieves performance on par with state-of-the-art reconstruction using RGB sensors.
Authors: Yao Teng, Haisong Liu, Sheng Guo, Limin Wang
Previous object detectors make predictions based on dense grid points or numerous preset anchors. Most of these detectors are trained with one-to-many label assignment strategies. On the contrary, recent query-based object detectors depend on a sparse set of learnable queries and a series of decoder layers. The one-to-one label assignment is independently applied on each layer for the deep supervision during training. Despite the great success of query-based object detection, however, this one-to-one label assignment strategy demands the detectors to have strong fine-grained discrimination and modeling capacity. To solve the above problems, in this paper, we propose a new query-based object detector with cross-stage interaction, coined as StageInteractor. During the forward propagation, we come up with an efficient way to improve this modeling ability by reusing dynamic operators with lightweight adapters. As for the label assignment, a cross-stage label assigner is applied subsequent to the one-to-one label assignment. With this assigner, the training target class labels are gathered across stages and then reallocated to proper predictions at each decoder layer. On MS COCO benchmark, our model improves the baseline by 2.2 AP, and achieves 44.8 AP with ResNet-50 as backbone, 100 queries and 12 training epochs. With longer training time and 300 queries, StageInteractor achieves 51.1 AP and 52.2 AP with ResNeXt-101-DCN and Swin-S, respectively.
Authors: Zidong Cao, Hao Ai, Athanasios V. Vasilakos, Lin Wang
To predict high-resolution (HR) omnidirectional depth map, existing methods typically leverage HR omnidirectional image (ODI) as the input via fully-supervised learning. However, in practice, taking HR ODI as input is undesired due to resource-constrained devices. In addition, depth maps are often with lower resolution than color images. Therefore, in this paper, we explore for the first time to estimate the HR omnidirectional depth directly from a low-resolution (LR) ODI, when no HR depth GT map is available. Our key idea is to transfer the scene structural knowledge from the HR image modality and the corresponding LR depth maps to achieve the goal of HR depth estimation without any extra inference cost. Specifically, we introduce ODI super-resolution (SR) as an auxiliary task and train both tasks collaboratively in a weakly supervised manner to boost the performance of HR depth estimation. The ODI SR task extracts the scene structural knowledge via uncertainty estimation. Buttressed by this, a scene structural knowledge transfer (SSKT) module is proposed with two key components. First, we employ a cylindrical implicit interpolation function (CIIF) to learn cylindrical neural interpolation weights for feature up-sampling and share the parameters of CIIFs between the two tasks. Then, we propose a feature distillation (FD) loss that provides extra structural regularization to help the HR depth estimation task learn more scene structural knowledge. Extensive experiments demonstrate that our weakly-supervised method outperforms baseline methods, and even achieves comparable performance with the fully-supervised methods.
Authors: Ansh Mittal
The various aspects like modeling and interpreting 3D environments and surroundings have enticed humans to progress their research in 3D Computer Vision, Computer Graphics, and Machine Learning. An attempt made by Mildenhall et al in their paper about NeRFs (Neural Radiance Fields) led to a boom in Computer Graphics, Robotics, Computer Vision, and the possible scope of High-Resolution Low Storage Augmented Reality and Virtual Reality-based 3D models have gained traction from res with more than 1000 preprints related to NeRFs published. This paper serves as a bridge for people starting to study these fields by building on the basics of Mathematics, Geometry, Computer Vision, and Computer Graphics to the difficulties encountered in Implicit Representations at the intersection of all these disciplines. This survey provides the history of rendering, Implicit Learning, and NeRFs, the progression of research on NeRFs, and the potential applications and implications of NeRFs in today's world. In doing so, this survey categorizes all the NeRF-related research in terms of the datasets used, objective functions, applications solved, and evaluation criteria for these applications.
Authors: Huayi Zhou, Fei Jiang, Jiaxin Si, Yue Ding, Hongtao Lu
Detection of human body and its parts has been intensively studied. However, most of CNNs-based detectors are trained independently, making it difficult to associate detected parts with body. In this paper, we focus on the joint detection of human body and its parts. Specifically, we propose a novel extended object representation integrating center-offsets of body parts, and construct an end-to-end generic Body-Part Joint Detector (BPJDet). In this way, body-part associations are neatly embedded in a unified representation containing both semantic and geometric contents. Therefore, we can optimize multi-loss to tackle multi-tasks synergistically. Moreover, this representation is suitable for anchor-based and anchor-free detectors. BPJDet does not suffer from error-prone post matching, and keeps a better trade-off between speed and accuracy. Furthermore, BPJDet can be generalized to detect body-part or body-parts of either human or quadruped animals. To verify the superiority of BPJDet, we conduct experiments on datasets of body-part (CityPersons, CrowdHuman and BodyHands) and body-parts (COCOHumanParts and Animals5C). While keeping high detection accuracy, BPJDet achieves state-of-the-art association performance on all datasets. Besides, we show benefits of advanced body-part association capability by improving performance of two representative downstream applications: accurate crowd head detection and hand contact estimation. Project is available in https://hnuzhy.github.io/projects/BPJDet.
Authors: Bin Fan, Yuchao Dai, Yongduek Seo, Mingyi He
The normalized eight-point algorithm has been widely viewed as the cornerstone in two-view geometry computation, where the seminal Hartley's normalization has greatly improved the performance of the direct linear transformation algorithm. A natural question is, whether there exists and how to find other normalization methods that may further improve the performance as per each input sample. In this paper, we provide a novel perspective and propose two contributions to this fundamental problem: 1) we revisit the normalized eight-point algorithm and make a theoretical contribution by presenting the existence of different and better normalization algorithms; 2) we introduce a deep convolutional neural network with a self-supervised learning strategy for normalization. Given eight pairs of correspondences, our network directly predicts the normalization matrices, thus learning to normalize each input sample. Our learning-based normalization module can be integrated with both traditional (e.g., RANSAC) and deep learning frameworks (affording good interpretability) with minimal effort. Extensive experiments on both synthetic and real images demonstrate the effectiveness of our proposed approach.
Authors: Yonggan Fu, Zhifan Ye, Jiayi Yuan, Shunyao Zhang, Sixu Li, Haoran You, Yingyan Lin
Novel view synthesis is an essential functionality for enabling immersive experiences in various Augmented- and Virtual-Reality (AR/VR) applications, for which generalizable Neural Radiance Fields (NeRFs) have gained increasing popularity thanks to their cross-scene generalization capability. Despite their promise, the real-device deployment of generalizable NeRFs is bottlenecked by their prohibitive complexity due to the required massive memory accesses to acquire scene features, causing their ray marching process to be memory-bounded. To this end, we propose Gen-NeRF, an algorithm-hardware co-design framework dedicated to generalizable NeRF acceleration, which for the first time enables real-time generalizable NeRFs. On the algorithm side, Gen-NeRF integrates a coarse-then-focus sampling strategy, leveraging the fact that different regions of a 3D scene contribute differently to the rendered pixel, to enable sparse yet effective sampling. On the hardware side, Gen-NeRF highlights an accelerator micro-architecture to maximize the data reuse opportunities among different rays by making use of their epipolar geometric relationship. Furthermore, our Gen-NeRF accelerator features a customized dataflow to enhance data locality during point-to-hardware mapping and an optimized scene feature storage strategy to minimize memory bank conflicts. Extensive experiments validate the effectiveness of our proposed Gen-NeRF framework in enabling real-time and generalizable novel view synthesis.
Authors: Yuxuan Duan, Li Niu, Yan Hong, Liqing Zhang
In few-shot image generation, directly training GAN models on just a handful of images faces the risk of overfitting. A popular solution is to transfer the models pretrained on large source domains to small target ones. In this work, we introduce WeditGAN, which realizes model transfer by editing the intermediate latent codes $w$ in StyleGANs with learned constant offsets ($\Delta w$), discovering and constructing target latent spaces via simply relocating the distribution of source latent spaces. The established one-to-one mapping between latent spaces can naturally prevents mode collapse and overfitting. Besides, we also propose variants of WeditGAN to further enhance the relocation process by regularizing the direction or finetuning the intensity of $\Delta w$. Experiments on a collection of widely used source/target datasets manifest the capability of WeditGAN in generating realistic and diverse images, which is simple yet highly effective in the research area of few-shot image generation. Codes are available at https://github.com/Ldhlwh/WeditGAN.
Authors: Fabio Bellavia
This paper presents Slime, a novel non-deep image matching framework which models the scene as rough local overlapping planes. This intermediate representation sits in-between the local affine approximation of the keypoint patches and the global matching based on both spatial and similarity constraints, providing a progressive pruning of the correspondences, as planes are easier to handle with respect to general scenes.
Slime decomposes the images into overlapping regions at different scales and computes loose planar homographies. Planes are mutually extended by compatible matches and the images are split into fixed tiles, with only the best homographies retained for each pair of tiles. Stable matches are identified according to the consensus of the admissible stereo configurations provided by pairwise homographies. Within tiles, the rough planes are then merged according to their overlap in terms of matches and further consistent correspondences are extracted.
The whole process only involves homography constraints. As a result, both the coverage and the stability of correct matches over the scene are amplified, together with the ability to spot matches in challenging scenes, allowing traditional hybrid matching pipelines to make up lost ground against recent end-to-end deep matching methods.
In addition, the paper gives a thorough comparative analysis of recent state-of-the-art in image matching represented by end-to-end deep networks and hybrid pipelines. The evaluation considers both planar and non-planar scenes, taking into account critical and challenging scenarios including abrupt temporal image changes and strong variations in relative image rotations. According to this analysis, although the impressive progress done in this field, there is still a wide room for improvements to be investigated in future research.
Authors: Derya Soydaner, Johan Wagemans
As people's aesthetic preferences for images are far from understood, image aesthetic assessment is a challenging artificial intelligence task. The range of factors underlying this task is almost unlimited, but we know that some aesthetic attributes affect those preferences. In this study, we present a multi-task convolutional neural network that takes into account these attributes. The proposed neural network jointly learns the attributes along with the overall aesthetic scores of images. This multi-task learning framework allows for effective generalization through the utilization of shared representations. Our experiments demonstrate that the proposed method outperforms the state-of-the-art approaches in predicting overall aesthetic scores for images in one benchmark of image aesthetics. We achieve near-human performance in terms of overall aesthetic scores when considering the Spearman's rank correlations. Moreover, our model pioneers the application of multi-tasking in another benchmark, serving as a new baseline for future research. Notably, our approach achieves this performance while using fewer parameters compared to existing multi-task neural networks in the literature, and consequently makes our method more efficient in terms of computational complexity.
Authors: Kira Maag, Asja Fischer
State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable against adversarial attacks, i.e., non-perceptible perturbations added to the input image causing incorrect predictions, which is hazardous in safety-critical applications like automated driving. Adversarial examples and defense strategies are well studied for the image classification task, while there has been limited research in the context of semantic segmentation. First works however show that the segmentation outcome can be severely distorted by adversarial attacks. In this work, we introduce an uncertainty-based approach for the detection of adversarial attacks in semantic segmentation. We observe that uncertainty as for example captured by the entropy of the output distribution behaves differently on clean and perturbed images and leverage this property to distinguish between the two cases. Our method works in a light-weight and post-processing manner, i.e., we do not modify the model or need knowledge of the process used for generating adversarial examples. In a thorough empirical analysis, we demonstrate the ability of our approach to detect perturbed images across multiple types of adversarial attacks.
Authors: Haotian Xue, Alexandre Araujo, Bin Hu, Yongxin Chen
Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical scenarios, they often differ greatly from the actual data distribution of natural images, resulting in a trade-off between strength and stealthiness. In this paper, we propose a novel framework dubbed Diffusion-Based Projected Gradient Descent (Diff-PGD) for generating realistic adversarial samples. By exploiting a gradient guided by a diffusion model, Diff-PGD ensures that adversarial samples remain close to the original data distribution while maintaining their effectiveness. Moreover, our framework can be easily customized for specific tasks such as digital attacks, physical-world attacks, and style-based attacks. Compared with existing methods for generating natural-style adversarial samples, our framework enables the separation of optimizing adversarial loss from other surrogate losses (e.g., content/smoothness/style loss), making it more stable and controllable. Finally, we demonstrate that the samples generated using Diff-PGD have better transferability and anti-purification power than traditional gradient-based methods. Code will be released in https://github.com/xavihart/Diff-PGD
Authors: Evangelos G. Sartinas, Emmanouil Z. Psarakis, Dimitrios I. Kosmopoulos
An interesting problem in many video-based applications is the generation of short synopses by selecting the most informative frames, a procedure which is known as video summarization. For sign language videos the benefits of using the $t$-parameterized counterpart of the curvature of the 2-D signer's wrist trajectory to identify keyframes, have been recently reported in the literature. In this paper we extend these ideas by modeling the 3-D hand motion that is extracted from each frame of the video. To this end we propose a new informative function based on the $t$-parameterized curvature and torsion of the 3-D trajectory. The method to characterize video frames as keyframes depends on whether the motion occurs in 2-D or 3-D space. Specifically, in the case of 3-D motion we look for the maxima of the harmonic mean of the curvature and torsion of the target's trajectory; in the planar motion case we seek for the maxima of the trajectory's curvature. The proposed 3-D feature is experimentally evaluated in applications of sign language videos on (1) objective measures using ground-truth keyframe annotations, (2) human-based evaluation of understanding, and (3) gloss classification and the results obtained are promising.
Authors: Weijian Luo, Tianyang Hu, Shifeng Zhang, Jiacheng Sun, Zhenguo Li, Zhihua Zhang
Due to the ease of training, ability to scale, and high sample quality, diffusion models (DMs) have become the preferred option for generative modeling, with numerous pre-trained models available for a wide variety of datasets. Containing intricate information about data distributions, pre-trained DMs are valuable assets for downstream applications. In this work, we consider learning from pre-trained DMs and transferring their knowledge to other generative models in a data-free fashion. Specifically, we propose a general framework called Diff-Instruct to instruct the training of arbitrary generative models as long as the generated samples are differentiable with respect to the model parameters. Our proposed Diff-Instruct is built on a rigorous mathematical foundation where the instruction process directly corresponds to minimizing a novel divergence we call Integral Kullback-Leibler (IKL) divergence. IKL is tailored for DMs by calculating the integral of the KL divergence along a diffusion process, which we show to be more robust in comparing distributions with misaligned supports. We also reveal non-trivial connections of our method to existing works such as DreamFusion, and generative adversarial training. To demonstrate the effectiveness and universality of Diff-Instruct, we consider two scenarios: distilling pre-trained diffusion models and refining existing GAN models. The experiments on distilling pre-trained diffusion models show that Diff-Instruct results in state-of-the-art single-step diffusion-based models. The experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models across various settings.
Authors: Se Jin Park, Minsu Kim, Jeongsoo Choi, Yong Man Ro
Talking face generation is the challenging task of synthesizing a natural and realistic face that requires accurate synchronization with a given audio. Due to co-articulation, where an isolated phone is influenced by the preceding or following phones, the articulation of a phone varies upon the phonetic context. Therefore, modeling lip motion with the phonetic context can generate more spatio-temporally aligned lip movement. In this respect, we investigate the phonetic context in generating lip motion for talking face generation. We propose Context-Aware Lip-Sync framework (CALS), which explicitly leverages phonetic context to generate lip movement of the target face. CALS is comprised of an Audio-to-Lip module and a Lip-to-Face module. The former is pretrained based on masked learning to map each phone to a contextualized lip motion unit. The contextualized lip motion unit then guides the latter in synthesizing a target identity with context-aware lip motion. From extensive experiments, we verify that simply exploiting the phonetic context in the proposed CALS framework effectively enhances spatio-temporal alignment. We also demonstrate the extent to which the phonetic context assists in lip synchronization and find the effective window size for lip generation to be approximately 1.2 seconds.
Authors: Junxing Hu, Hongwen Zhang, Zerui Chen, Mengcheng Li, Yunlong Wang, Yebin Liu, Zhenan Sun
Reconstructing hand-held objects from monocular RGB images is an appealing yet challenging task. In this task, contacts between hands and objects provide important cues for recovering the 3D geometry of the hand-held objects. Though recent works have employed implicit functions to achieve impressive progress, they ignore formulating contacts in their frameworks, which results in producing less realistic object meshes. In this work, we explore how to model contacts in an explicit way to benefit the implicit reconstruction of hand-held objects. Our method consists of two components: explicit contact prediction and implicit shape reconstruction. In the first part, we propose a new subtask of directly estimating 3D hand-object contacts from a single image. The part-level and vertex-level graph-based transformers are cascaded and jointly learned in a coarse-to-fine manner for more accurate contact probabilities. In the second part, we introduce a novel method to diffuse estimated contact states from the hand mesh surface to nearby 3D space and leverage diffused contact probabilities to construct the implicit neural representation for the manipulated object. Benefiting from estimating the interaction patterns between the hand and the object, our method can reconstruct more realistic object meshes, especially for object parts that are in contact with hands. Extensive experiments on challenging benchmarks show that the proposed method outperforms the current state of the arts by a great margin. Our code is publicly available at https://junxinghu.github.io/projects/hoi.html.
Authors: Tao Chu, Pan Zhang, Qiong Liu, Jiaqi Wang
Understanding and modeling the 3D scene from a single image is a practical problem. A recent advance proposes a panoptic 3D scene reconstruction task that performs both 3D reconstruction and 3D panoptic segmentation from a single image. Although having made substantial progress, recent works only focus on top-down approaches that fill 2D instances into 3D voxels according to estimated depth, which hinders their performance by two ambiguities. (1) instance-channel ambiguity: The variable ids of instances in each scene lead to ambiguity during filling voxel channels with 2D information, confusing the following 3D refinement. (2) voxel-reconstruction ambiguity: 2D-to-3D lifting with estimated single view depth only propagates 2D information onto the surface of 3D regions, leading to ambiguity during the reconstruction of regions behind the frontal view surface. In this paper, we propose BUOL, a Bottom-Up framework with Occupancy-aware Lifting to address the two issues for panoptic 3D scene reconstruction from a single image. For instance-channel ambiguity, a bottom-up framework lifts 2D information to 3D voxels based on deterministic semantic assignments rather than arbitrary instance id assignments. The 3D voxels are then refined and grouped into 3D instances according to the predicted 2D instance centers. For voxel-reconstruction ambiguity, the estimated multi-plane occupancy is leveraged together with depth to fill the whole regions of things and stuff. Our method shows a tremendous performance advantage over state-of-the-art methods on synthetic dataset 3D-Front and real-world dataset Matterport3D. Code and models are available in https://github.com/chtsy/buol.
Authors: Shuvendu Roy, Ali Etemad
We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that labelled and unlabelled samples are drawn from the same distribution, which limits the potential for improvement through the use of free-living unlabeled data. Consequently, the generalizability and scalability of semi-supervised learning are often hindered by this assumption. Our method aims to overcome these constraints and effectively utilize unconstrained unlabelled data in semi-supervised learning. UnMixMatch consists of three main components: a supervised learner with hard augmentations that provides strong regularization, a contrastive consistency regularizer to learn underlying representations from the unlabelled data, and a self-supervised loss to enhance the representations that are learnt from the unlabelled data. We perform extensive experiments on 4 commonly used datasets and demonstrate superior performance over existing semi-supervised methods with a performance boost of 4.79%. Extensive ablation and sensitivity studies show the effectiveness and impact of each of the proposed components of our method.
Authors: Aram Davtyan, Paolo Favaro
We propose a novel unsupervised method to autoregressively generate videos from a single frame and a sparse motion input. Our trained model can generate unseen realistic object-to-object interactions. Although our model has never been given the explicit segmentation and motion of each object in the scene during training, it is able to implicitly separate their dynamics and extents. Key components in our method are the randomized conditioning scheme, the encoding of the input motion control, and the randomized and sparse sampling to enable generalization to out of distribution but realistic correlations. Our model, which we call YODA, has therefore the ability to move objects without physically touching them. Through extensive qualitative and quantitative evaluations on several datasets, we show that YODA is on par with or better than state of the art video generation prior work in terms of both controllability and video quality.
Authors: Ruoyu Wang, Yongqi Yang, Zhihao Qian, Ye Zhu, Yu Wu
Originating from the diffusion phenomenon in physics that describes particle movement, the diffusion generative models inherit the characteristics of stochastic random walk in the data space along the denoising trajectory. However, the intrinsic mutual interference among image regions contradicts the need for practical downstream application scenarios where the preservation of low-level pixel information from given conditioning is desired (e.g., customization tasks like personalized generation and inpainting based on a user-provided single image). In this work, we investigate the diffusion (physics) in diffusion (machine learning) properties and propose our Cyclic One-Way Diffusion (COW) method to control the direction of diffusion phenomenon given a pre-trained frozen diffusion model for versatile customization application scenarios, where the low-level pixel information from the conditioning needs to be preserved. Notably, unlike most current methods that incorporate additional conditions by fine-tuning the base text-to-image diffusion model or learning auxiliary networks, our method provides a novel perspective to understand the task needs and is applicable to a wider range of customization scenarios in a learning-free manner. Extensive experiment results show that our proposed COW can achieve more flexible customization based on strict visual conditions in different application settings.
Authors: Moritz Böhle, Navdeeppal Singh, Mario Fritz, Bernt Schiele
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. For this, we propose to replace the linear transformations in DNNs by our novel B-cos transformation. As we show, a sequence (network) of such transformations induces a single linear transformation that faithfully summarises the full model computations. Moreover, the B-cos transformation is designed such that the weights align with relevant signals during optimisation. As a result, those induced linear transformations become highly interpretable and highlight task-relevant features. Importantly, the B-cos transformation is designed to be compatible with existing architectures and we show that it can easily be integrated into virtually all of the latest state of the art models for computer vision - e.g. ResNets, DenseNets, ConvNext models, as well as Vision Transformers - by combining the B-cos-based explanations with normalisation and attention layers, all whilst maintaining similar accuracy on ImageNet. Finally, we show that the resulting explanations are of high visual quality and perform well under quantitative interpretability metrics.
Authors: Liping Zhang, Xiaobo Li, Weitian Chen
Undersampling k-space data in MRI reduces scan time but pose challenges in image reconstruction. Considerable progress has been made in reconstructing accelerated MRI. However, restoration of high-frequency image details in highly undersampled data remains challenging. To address this issue, we propose CAMP-Net, an unrolling-based Consistency-Aware Multi-Prior Network for accelerated MRI reconstruction. CAMP-Net leverages complementary multi-prior knowledge and multi-slice information from various domains to enhance reconstruction quality. Specifically, CAMP-Net comprises three interleaved modules for image enhancement, k-space restoration, and calibration consistency, respectively. These modules jointly learn priors from data in image domain, k-domain, and calibration region, respectively, in data-driven manner during each unrolled iteration. Notably, the encoded calibration prior knowledge extracted from auto-calibrating signals implicitly guides the learning of consistency-aware k-space correlation for reliable interpolation of missing k-space data. To maximize the benefits of image domain and k-domain prior knowledge, the reconstructions are aggregated in a frequency fusion module, exploiting their complementary properties to optimize the trade-off between artifact removal and fine detail preservation. Additionally, we incorporate a surface data fidelity layer during the learning of k-domain and calibration domain priors to prevent degradation of the reconstruction caused by padding-induced data imperfections. We evaluate the generalizability and robustness of our method on three large public datasets with varying acceleration factors and sampling patterns. The experimental results demonstrate that our method outperforms state-of-the-art approaches in terms of both reconstruction quality and $T_2$ mapping estimation, particularly in scenarios with high acceleration factors.
Authors: Chengxu Duan, Zhicheng Zhang, Xiaoli Liu, Yonghao Dang, Jianqin Yin
Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction.
Authors: Lin Xi, Weihai Chen, Xingming Wu, Zhong Liu, Zhengguo Li
Online unsupervised video object segmentation (UVOS) uses the previous frames as its input to automatically separate the primary object(s) from a streaming video without using any further manual annotation. A major challenge is that the model has no access to the future and must rely solely on the history, i.e., the segmentation mask is predicted from the current frame as soon as it is captured. In this work, a novel contrastive motion clustering algorithm with an optical flow as its input is proposed for the online UVOS by exploiting the common fate principle that visual elements tend to be perceived as a group if they possess the same motion pattern. We build a simple and effective auto-encoder to iteratively summarize non-learnable prototypical bases for the motion pattern, while the bases in turn help learn the representation of the embedding network. Further, a contrastive learning strategy based on a boundary prior is developed to improve foreground and background feature discrimination in the representation learning stage. The proposed algorithm can be optimized on arbitrarily-scale data i.e., frame, clip, dataset) and performed in an online fashion. Experiments on $\textit{DAVIS}_{\textit{16}}$, $\textit{FBMS}$, and $\textit{SegTrackV2}$ datasets show that the accuracy of our method surpasses the previous state-of-the-art (SoTA) online UVOS method by a margin of 0.8%, 2.9%, and 1.1%, respectively. Furthermore, by using an online deep subspace clustering to tackle the motion grouping, our method is able to achieve higher accuracy at $3\times$ faster inference time compared to SoTA online UVOS method, and making a good trade-off between effectiveness and efficiency.
Authors: Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan
Denoising diffusion probabilistic models (DDPMs) have been proven capable of synthesizing high-quality images with remarkable diversity when trained on large amounts of data. Typical diffusion models and modern large-scale conditional generative models like text-to-image generative models are vulnerable to overfitting when fine-tuned on extremely limited data. Existing works have explored subject-driven generation using a reference set containing a few images. However, few prior works explore DDPM-based domain-driven generation, which aims to learn the common features of target domains while maintaining diversity. This paper proposes a novel DomainStudio approach to adapt DDPMs pre-trained on large-scale source datasets to target domains using limited data. It is designed to keep the diversity of subjects provided by source domains and get high-quality and diverse adapted samples in target domains. We propose to keep the relative distances between adapted samples to achieve considerable generation diversity. In addition, we further enhance the learning of high-frequency details for better generation quality. Our approach is compatible with both unconditional and conditional diffusion models. This work makes the first attempt to realize unconditional few-shot image generation with diffusion models, achieving better quality and greater diversity than current state-of-the-art GAN-based approaches. Moreover, this work also significantly relieves overfitting for conditional generation and realizes high-quality domain-driven generation, further expanding the applicable scenarios of modern large-scale text-to-image models.
Authors: Weinan Song, Yaxuan Zhu, Lei He, Yingnian Wu, Jianwen Xie
This paper studies a novel energy-based cooperative learning framework for multi-domain image-to-image translation. The framework consists of four components: descriptor, translator, style encoder, and style generator. The descriptor is a multi-head energy-based model that represents a multi-domain image distribution. The components of translator, style encoder, and style generator constitute a diversified image generator. Specifically, given an input image from a source domain, the translator turns it into a stylised output image of the target domain according to a style code, which can be inferred by the style encoder from a reference image or produced by the style generator from a random noise. Since the style generator is represented as an domain-specific distribution of style codes, the translator can provide a one-to-many transformation (i.e., diversified generation) between source domain and target domain. To train our framework, we propose a likelihood-based multi-domain cooperative learning algorithm to jointly train the multi-domain descriptor and the diversified image generator (including translator, style encoder, and style generator modules) via multi-domain MCMC teaching, in which the descriptor guides the diversified image generator to shift its probability density toward the data distribution, while the diversified image generator uses its randomly translated images to initialize the descriptor's Langevin dynamics process for efficient sampling.
Authors: Kai Han, Yunhe Wang, Jianyuan Guo, Enhua Wu
The large-scale visual pretraining has significantly improve the performance of large vision models. However, we observe the \emph{low FLOPs pitfall} that the existing low-FLOPs models cannot benefit from large-scale pretraining. In this paper, we introduce a novel design principle, termed ParameterNet, aimed at augmenting the number of parameters in large-scale visual pretraining models while minimizing the increase in FLOPs. We leverage dynamic convolutions to incorporate additional parameters into the networks with only a marginal rise in FLOPs. The ParameterNet approach allows low-FLOPs networks to take advantage of large-scale visual pretraining. Furthermore, we extend the ParameterNet concept to the language domain to enhance inference results while preserving inference speed. Experiments on the large-scale ImageNet-22K have shown the superiority of our ParameterNet scheme. For example, ParameterNet-600M can achieve higher accuracy on ImageNet than the widely-used Swin Transformer (81.6\% \emph{vs.} 80.9\%) and has much lower FLOPs (0.6G \emph{vs.} 4.5G). In the language domain, LLaMA-1B enhanced with ParameterNet achieves 2\% higher accuracy over vanilla LLaMA. The code will be released at \url{https://parameternet.github.io/}.
Authors: Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu, Dong Xu
Even though trained mainly on images, we discover that pretrained diffusion models show impressive power in guiding sketch synthesis. In this paper, we present DiffSketcher, an innovative algorithm that creates \textit{vectorized} free-hand sketches using natural language input. DiffSketcher is developed based on a pre-trained text-to-image diffusion model. It performs the task by directly optimizing a set of B\'ezier curves with an extended version of the score distillation sampling (SDS) loss, which allows us to use a raster-level diffusion model as a prior for optimizing a parametric vectorized sketch generator. Furthermore, we explore attention maps embedded in the diffusion model for effective stroke initialization to speed up the generation process. The generated sketches demonstrate multiple levels of abstraction while maintaining recognizability, underlying structure, and essential visual details of the subject drawn. Our experiments show that DiffSketcher achieves greater quality than prior work. The code and demo of DiffSketcher can be found at https://ximinng.github.io/DiffSketcher-project/.
Authors: Balamurali Murugesan, Rukhshanda Hussain, Rajarshi Bhattacharya, Ismail Ben Ayed, Jose Dolz
Recently, CLIP-based approaches have exhibited remarkable performance on generalization and few-shot learning tasks, fueled by the power of contrastive language-vision pre-training. In particular, prompt tuning has emerged as an effective strategy to adapt the pre-trained language-vision models to downstream tasks by employing task-related textual tokens. Motivated by this progress, in this work we question whether other fundamental problems, such as weakly supervised semantic segmentation (WSSS), can benefit from prompt tuning. Our findings reveal two interesting observations that shed light on the impact of prompt tuning on WSSS. First, modifying only the class token of the text prompt results in a greater impact on the Class Activation Map (CAM), compared to arguably more complex strategies that optimize the context. And second, the class token associated with the image ground truth does not necessarily correspond to the category that yields the best CAM. Motivated by these observations, we introduce a novel approach based on a PrOmpt cLass lEarning (POLE) strategy. Through extensive experiments we demonstrate that our simple, yet efficient approach achieves SOTA performance in a well-known WSSS benchmark. These results highlight not only the benefits of language-vision models in WSSS but also the potential of prompt learning for this problem. The code is available at https://github.com/rB080/WSS_POLE.
Authors: Mark D. McDonnell, Dong Gong, Amin Parveneh, Ehsan Abbasnejad, Anton van den Hengel
Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch paradigm. However, with the increasing prominence of foundation models, pre-trained models equipped with informative representations have become available for various downstream requirements. Several CL methods based on pre-trained models have been explored, either utilizing pre-extracted features directly (which makes bridging distribution gaps challenging) or incorporating adaptors (which may be subject to forgetting). In this paper, we propose a concise and effective approach for CL with pre-trained models. Given that forgetting occurs during parameter updating, we contemplate an alternative approach that exploits training-free random projectors and class-prototype accumulation, which thus bypasses the issue. Specifically, we inject a frozen Random Projection layer with nonlinear activation between the pre-trained model's feature representations and output head, which captures interactions between features with expanded dimensionality, providing enhanced linear separability for class-prototype-based CL. We also demonstrate the importance of decorrelating the class-prototypes to reduce the distribution disparity when using pre-trained representations. These techniques prove to be effective and circumvent the problem of forgetting for both class- and domain-incremental continual learning. Compared to previous methods applied to pre-trained ViT-B/16 models, we reduce final error rates by between 20% and 62% on seven class-incremental benchmarks, despite not using any rehearsal memory. We conclude that the full potential of pre-trained models for simple, effective, and fast CL has not hitherto been fully tapped. Code is at github.com/RanPAC/RanPAC.
Authors: Guillaume Vray, Devavrat Tomar, Jean-Philippe Thiran, Behzad Bozorgtabar
Developing computational pathology models is essential for reducing manual tissue typing from whole slide images, transferring knowledge from the source domain to an unlabeled, shifted target domain, and identifying unseen categories. We propose a practical setting by addressing the above-mentioned challenges in one fell swoop, i.e., source-free open-set domain adaptation. Our methodology focuses on adapting a pre-trained source model to an unlabeled target dataset and encompasses both closed-set and open-set classes. Beyond addressing the semantic shift of unknown classes, our framework also deals with a covariate shift, which manifests as variations in color appearance between source and target tissue samples. Our method hinges on distilling knowledge from a self-supervised vision transformer (ViT), drawing guidance from either robustly pre-trained transformer models or histopathology datasets, including those from the target domain. In pursuit of this, we introduce a novel style-based adversarial data augmentation, serving as hard positives for self-training a ViT, resulting in highly contextualized embeddings. Following this, we cluster semantically akin target images, with the source model offering weak pseudo-labels, albeit with uncertain confidence. To enhance this process, we present the closed-set affinity score (CSAS), aiming to correct the confidence levels of these pseudo-labels and to calculate weighted class prototypes within the contextualized embedding space. Our approach establishes itself as state-of-the-art across three public histopathological datasets for colorectal cancer assessment. Notably, our self-training method seamlessly integrates with open-set detection methods, resulting in enhanced performance in both closed-set and open-set recognition tasks.
Authors: Navot Oz, Nir Sochen, David Mendelovich, Iftach Klapp
Low-cost thermal cameras are inaccurate (usually $\pm 3^\circ C$) and have space-variant nonuniformity across their detector. Both inaccuracy and nonuniformity are dependent on the ambient temperature of the camera. The goal of this work was to estimate temperatures with low-cost infrared cameras, and rectify the nonuniformity.
A nonuniformity simulator that accounts for the ambient temperature was developed. An end-to-end neural network that incorporates both the physical model of the camera and the ambient camera temperature was introduced. The neural network was trained with the simulated nonuniformity data to estimate the object's temperature and correct the nonuniformity, using only a single image and the ambient temperature measured by the camera itself. Results of the proposed method significantly improved the mean temperature error compared to previous works by up to $0.5^\circ C$. In addition, constraining the physical model of the camera with the network lowered the error by an additional $0.1^\circ C$.
The mean temperature error over an extensive validation dataset was $0.37^\circ C$. The method was verified on real data in the field and produced equivalent results.
Authors: Meirui Jiang, Yuan Zhong, Anjie Le, Xiaoxiao Li, Qi Dou
Despite recent progress in enhancing the privacy of federated learning (FL) via differential privacy (DP), the trade-off of DP between privacy protection and performance is still underexplored for real-world medical scenario. In this paper, we propose to optimize the trade-off under the context of client-level DP, which focuses on privacy during communications. However, FL for medical imaging involves typically much fewer participants (hospitals) than other domains (e.g., mobile devices), thus ensuring clients be differentially private is much more challenging. To tackle this problem, we propose an adaptive intermediary strategy to improve performance without harming privacy. Specifically, we theoretically find splitting clients into sub-clients, which serve as intermediaries between hospitals and the server, can mitigate the noises introduced by DP without harming privacy. Our proposed approach is empirically evaluated on both classification and segmentation tasks using two public datasets, and its effectiveness is demonstrated with significant performance improvements and comprehensive analytical studies. Code is available at: https://github.com/med-air/Client-DP-FL.
Authors: Martina Paccini, Giacomo Paschina, Stefano De Beni, Giuseppe Patanè
This paper presents an innovative automatic fusion imaging system that combines 3D CT/MR images with real-time ultrasound (US) acquisition. The system eliminates the need for external physical markers and complex training, making image fusion feasible for physicians with different experience levels. The integrated system involves a portable 3D camera for patient-specific surface acquisition, an electromagnetic tracking system, and US components. The fusion algorithm comprises two main parts: skin segmentation and rigid co-registration, both integrated into the US machine. The co-registration software aligns the surface extracted from CT/MR images with patient-specific coordinates, facilitating rapid and effective fusion. Experimental testing in different settings, including the clinical environment, validates the system's accuracy, computational efficiency, noise robustness, and operator independence. The co-registration error remains under the acceptable range of~$1$ cm.
Authors: Kun Yuan, Vinkle Srivastav, Tong Yu, Joel L. Lavanchy, Pietro Mascagni, Nassir Navab, Nicolas Padoy
Recent advancements in surgical computer vision applications have been driven by fully-supervised methods, primarily using only visual data. These methods rely on manually annotated surgical videos to predict a fixed set of object categories, limiting their generalizability to unseen surgical procedures and downstream tasks. In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective supervisory signals for multi-modal representation learning without relying on manual annotations. We address the surgery-specific linguistic challenges present in surgical video lectures by employing multiple complementary automatic speech recognition systems to generate text transcriptions. We then present a novel method, SurgVLP - Surgical Vision Language Pre-training, for multi-modal representation learning. SurgVLP constructs a new contrastive learning objective to align video clip embeddings with the corresponding multiple text embeddings by bringing them together within a joint latent space. To effectively show the representation capability of the learned joint latent space, we introduce several vision-and-language tasks for surgery, such as text-based video retrieval, temporal activity grounding, and video captioning, as benchmarks for evaluation. We further demonstrate that without using any labeled ground truth, our approach can be employed for traditional vision-only surgical downstream tasks, such as surgical tool, phase, and triplet recognition. The code will be made available at https://github.com/CAMMA-public/SurgVLP
Authors: Wei Jiang, Jiayu Yang, Yongqi Zhai, Feng Gao, Ronggang Wang
Recently, learned image compression has achieved impressive performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in enhancing rate-distortion performance. However, existing global context modules rely on computationally intensive quadratic complexity computations to capture global correlations. This quadratic complexity imposes limitations on the potential of high-resolution image coding. Moreover, effectively capturing local, global, and channel-wise contexts with acceptable even linear complexity within a single entropy model remains a challenge. To address these limitations, we propose the Linear Complexity Attention-based Multi-Reference Entropy Model (MEM++). MEM++ effectively captures the diverse range of correlations inherent in the latent representation. Specifically, the latent representation is first divided into multiple slices. When compressing a particular slice, the previously compressed slices serve as its channel-wise contexts. To capture local contexts without sacrificing performance, we introduce a novel checkerboard attention module. Additionally, to capture global contexts, we propose the linear complexity attention-based global correlations capturing by leveraging the decomposition of the softmax operation. The attention map of the previously decoded slice is implicitly computed and employed to predict global correlations in the current slice. Based on MEM++, we propose image compression model MLIC++. Extensive experimental evaluations demonstrate that our MLIC++ achieves state-of-the-art performance, reducing BD-rate by 13.39% on the Kodak dataset compared to VTM-17.0 in PSNR. Furthermore, MLIC++ exhibits linear GPU memory consumption with resolution, making it highly suitable for high-resolution image coding. Code and pre-trained models are available at https://github.com/JiangWeibeta/MLIC.
Authors: Xianqiang Lyu, Junhui Hou
This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a multi-stage architecture that mimics the optimization process of solving an inverse imaging problem in a data-driven fashion. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. Additionally, DCUNet includes a content-associated deep compensation module at each optimization stage to suppress noise and illumination map estimation errors. To properly mine and leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module that comprehensively exploits redundant information in LF images. The experimental results on both simulated and real datasets demonstrate the superiority of our DCUNet over state-of-the-art methods, both qualitatively and quantitatively. Moreover, DCUNet preserves the essential geometric structure of enhanced LF images much better. The code will be publicly available at https://github.com/lyuxianqiang/LFLL-DCU.
Authors: Teresa Klatzer, Paul Dobson, Yoann Altmann, Marcelo Pereyra, Jesús María Sanz-Serna, Konstantinos C. Zygalakis
This paper presents a new accelerated proximal Markov chain Monte Carlo methodology to perform Bayesian inference in imaging inverse problems with an underlying convex geometry. The proposed strategy takes the form of a stochastic relaxed proximal-point iteration that admits two complementary interpretations. For models that are smooth or regularised by Moreau-Yosida smoothing, the algorithm is equivalent to an implicit midpoint discretisation of an overdamped Langevin diffusion targeting the posterior distribution of interest. This discretisation is asymptotically unbiased for Gaussian targets and shown to converge in an accelerated manner for any target that is $\kappa$-strongly log-concave (i.e., requiring in the order of $\sqrt{\kappa}$ iterations to converge, similarly to accelerated optimisation schemes), comparing favorably to [M. Pereyra, L. Vargas Mieles, K.C. Zygalakis, SIAM J. Imaging Sciences, 13,2 (2020), pp. 905-935] which is only provably accelerated for Gaussian targets and has bias. For models that are not smooth, the algorithm is equivalent to a Leimkuhler-Matthews discretisation of a Langevin diffusion targeting a Moreau-Yosida approximation of the posterior distribution of interest, and hence achieves a significantly lower bias than conventional unadjusted Langevin strategies based on the Euler-Maruyama discretisation. For targets that are $\kappa$-strongly log-concave, the provided non-asymptotic convergence analysis also identifies the optimal time step which maximizes the convergence speed. The proposed methodology is demonstrated through a range of experiments related to image deconvolution with Gaussian and Poisson noise, with assumption-driven and data-driven convex priors. Source codes for the numerical experiments of this paper are available from https://github.com/MI2G/accelerated-langevin-imla.
Authors: Jonathan Cui, David A. Araujo, Suman Saha, Md. Faisal Kabir
Despite their simpler information fusion designs compared with Vision Transformers and Convolutional Neural Networks, Vision MLP architectures have demonstrated strong performance and high data efficiency in recent research. However, existing works such as CycleMLP and Vision Permutator typically model spatial information in equal-size spatial regions and do not consider cross-scale spatial interactions. Further, their token mixers only model 1- or 2-axis correlations, avoiding 3-axis spatial-channel mixing due to its computational demands. We therefore propose CS-Mixer, a hierarchical Vision MLP that learns dynamic low-rank transformations for spatial-channel mixing through cross-scale local and global aggregation. The proposed methodology achieves competitive results on popular image recognition benchmarks without incurring substantially more compute. Our largest model, CS-Mixer-L, reaches 83.2% top-1 accuracy on ImageNet-1k with 13.7 GFLOPs and 94 M parameters.
Authors: Nazanin Moradinasab, Rebecca A. Deaton, Laura S. Shankman, Gary K. Owens, Donald E. Brown
Recently, deep learning-based methods achieved promising performance in nuclei detection and classification applications. However, training deep learning-based methods requires a large amount of pixel-wise annotated data, which is time-consuming and labor-intensive, especially in 3D images. An alternative approach is to adapt weak-annotation methods, such as labeling each nucleus with a point, but this method does not extend from 2D histopathology images (for which it was originally developed) to 3D immunofluorescent images. The reason is that 3D images contain multiple channels (z-axis) for nuclei and different markers separately, which makes training using point annotations difficult. To address this challenge, we propose the Label-efficient Contrastive learning-based (LECL) model to detect and classify various types of nuclei in 3D immunofluorescent images. Previous methods use Maximum Intensity Projection (MIP) to convert immunofluorescent images with multiple slices to 2D images, which can cause signals from different z-stacks to falsely appear associated with each other. To overcome this, we devised an Extended Maximum Intensity Projection (EMIP) approach that addresses issues using MIP. Furthermore, we performed a Supervised Contrastive Learning (SCL) approach for weakly supervised settings. We conducted experiments on cardiovascular datasets and found that our proposed framework is effective and efficient in detecting and classifying various types of nuclei in 3D immunofluorescent images.
Authors: Jiaying Lu, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Baochen Sun, Carl Yang, Jie Yang
Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is their constrained semantic grounding ability, which pertains to connecting language to the physical-world entities or concepts referenced in images. Therefore, a crucial need arises for a comprehensive study to assess the semantic grounding ability of widely used LVLMs. Despite the significance, sufficient investigation in this direction is currently lacking. Our work bridges this gap by designing a pipeline for generating large-scale evaluation datasets covering fine-grained semantic information, such as color, number, material, etc., along with a thorough assessment of seven popular LVLMs' semantic grounding ability. Results highlight prevalent misgrounding across various aspects and degrees. To address this issue, we propose a data-centric enhancement method that aims to improve LVLMs' semantic grounding ability through multimodal instruction tuning on fine-grained conversations. Experiments on enhanced LVLMs demonstrate notable improvements in addressing misgrounding issues.
Authors: Bo Zhang, Xinyu Cai, Jiakang Yuan, Donglin Yang, Jianfei Guo, Xiangchao Yan, Renqiu Xia, Botian Shi, Min Dou, Tao Chen, Si Liu, Junchi Yan, Yu Qiao
Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the previous domain knowledge can be hardly directly deployed to a new domain without additional costs. In this paper, we provide a new perspective and approach of alleviating the domain shifts, by proposing a Reconstruction-Simulation-Perception (ReSimAD) scheme. Specifically, the implicit reconstruction process is based on the knowledge from the previous old domain, aiming to convert the domain-related knowledge into domain-invariant representations, e.g., 3D scene-level meshes. Besides, the point clouds simulation process of multiple new domains is conditioned on the above reconstructed 3D meshes, where the target-domain-like simulation samples can be obtained, thus reducing the cost of collecting and annotating new-domain data for the subsequent perception process. For experiments, we consider different cross-domain situations such as Waymo-to-KITTI, Waymo-to-nuScenes, Waymo-to-ONCE, etc, to verify the zero-shot target-domain perception using ReSimAD. Results demonstrate that our method is beneficial to boost the domain generalization ability, even promising for 3D pre-training.
Authors: Jiazhen Wang, Bin Liu, Changtao Miao, Zhiwei Zhao, Wanyi Zhuang, Qi Chu, Nenghai Yu
AI-synthesized text and images have gained significant attention, particularly due to the widespread dissemination of multi-modal manipulations on the internet, which has resulted in numerous negative impacts on society. Existing methods for multi-modal manipulation detection and grounding primarily focus on fusing vision-language features to make predictions, while overlooking the importance of modality-specific features, leading to sub-optimal results. In this paper, we construct a simple and novel transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. To achieve this, we introduce visual/language pre-trained encoders and dual-branch cross-attention (DCA) to extract and fuse modality-unique features. Furthermore, we design decoupled fine-grained classifiers (DFC) to enhance modality-specific feature mining and mitigate modality competition. Moreover, we propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality using learnable queries, thereby improving the discovery of forged details. Extensive experiments on the $\rm DGM^4$ dataset demonstrate the superior performance of our proposed model compared to state-of-the-art approaches.
Authors: Utkarsh Singhal, Carlos Esteves, Ameesh Makadia, Stella X. Yu
Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too much or too little invariance can hurt, and the correct amount is unknown a priori and dependent on the instance. Ideally, the appropriate invariance would be learned from data and inferred at test-time.
We treat invariance as a prediction problem. Given any image, we use a normalizing flow to predict a distribution over transformations and average the predictions over them. Since this distribution only depends on the instance, we can align instances before classifying them and generalize invariance across classes. The same distribution can also be used to adapt to out-of-distribution poses. This normalizing flow is trained end-to-end and can learn a much larger range of transformations than Augerino and InstaAug. When used as data augmentation, our method shows accuracy and robustness gains on CIFAR 10, CIFAR10-LT, and TinyImageNet.
Authors: Hao Li, Jingkuan Song, Lianli Gao, Xiaosu Zhu, Heng Tao Shen
Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. In this paper, we propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity. Concretely, we first construct a set of various learnable prototypes for each modality to represent the entire semantics subspace. Then Dempster-Shafer Theory and Subjective Logic Theory are utilized to build an evidential theoretical framework by associating evidence with Dirichlet Distribution parameters. The PAU model induces accurate uncertainty and reliable predictions for cross-modal retrieval. Extensive experiments are performed on four major benchmark datasets of MSR-VTT, MSVD, DiDeMo, and MS-COCO, demonstrating the effectiveness of our method. The code is accessible at https://github.com/leolee99/PAU.
Authors: Huiyuan Tian, Li Zhang, Shijian Li, Min Yao, Gang Pan
A longstanding challenge in Super-Resolution (SR) is how to efficiently enhance high-frequency details in Low-Resolution (LR) images while maintaining semantic coherence. This is particularly crucial in practical applications where SR models are often deployed on low-power devices. To address this issue, we propose an innovative asymmetric SR architecture featuring Multi-Depth Branch Module (MDBM). These MDBMs contain branches of different depths, designed to capture high- and low-frequency information simultaneously and efficiently. The hierarchical structure of MDBM allows the deeper branch to gradually accumulate fine-grained local details under the contextual guidance of the shallower branch. We visualize this process using feature maps, and further demonstrate the rationality and effectiveness of this design using proposed novel Fourier spectral analysis methods. Moreover, our model exhibits more significant spectral differentiation between branches than existing branch networks. This suggests that MDBM reduces feature redundancy and offers a more effective method for integrating high- and low-frequency information. Extensive qualitative and quantitative evaluations on various datasets show that our model can generate structurally consistent and visually realistic HR images. It achieves state-of-the-art (SOTA) results at a very fast inference speed. Our code is available at https://github.com/thy960112/MDBN.
Authors: Mathew Mithra Noel, Venkataraman Muthiah-Nakarajan
Higher order artificial neurons whose outputs are computed by applying an activation function to a higher order multinomial function of the inputs have been considered in the past, but did not gain acceptance due to the extra parameters and computational cost. However, higher order neurons have significantly greater learning capabilities since the decision boundaries of higher order neurons can be complex surfaces instead of just hyperplanes. The boundary of a single quadratic neuron can be a general hyper-quadric surface allowing it to learn many nonlinearly separable datasets. Since quadratic forms can be represented by symmetric matrices, only $\frac{n(n+1)}{2}$ additional parameters are needed instead of $n^2$. A quadratic Logistic regression model is first presented. Solutions to the XOR problem with a single quadratic neuron are considered. The complete vectorized equations for both forward and backward propagation in feedforward networks composed of quadratic neurons are derived. A reduced parameter quadratic neural network model with just $ n $ additional parameters per neuron that provides a compromise between learning ability and computational cost is presented. Comparison on benchmark classification datasets are used to demonstrate that a final layer of quadratic neurons enables networks to achieve higher accuracy with significantly fewer hidden layer neurons. In particular this paper shows that any dataset composed of $\mathcal{C}$ bounded clusters can be separated with only a single layer of $\mathcal{C}$ quadratic neurons.
Authors: Ran Tian, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik, Andrea Bajcsy
When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards will inevitably use visual representations. Recently there has been excitement in using representations from pre-trained visual models, but key to making these work in robotics is fine-tuning, which is typically done via proxy tasks like dynamics prediction or enforcing temporal cycle-consistency. However, all these proxy tasks bypass the human's input on what matters to them, exacerbating spurious correlations and ultimately leading to robot behaviors that are misaligned with user preferences. In this work, we propose that robots should leverage human feedback to align their visual representations with the end-user and disentangle what matters for the task. We propose Representation-Aligned Preference-based Learning (RAPL), a method for solving the visual representation alignment problem and visual reward learning problem through the lens of preference-based learning and optimal transport. Across experiments in X-MAGICAL and in robotic manipulation, we find that RAPL's reward consistently generates preferred robot behaviors with high sample efficiency, and shows strong zero-shot generalization when the visual representation is learned from a different embodiment than the robot's.
Authors: Eleonora Breci (1), Luca Guarnera (1), Sebastiano Battiato (1) ((1) University of Catania)
Handwritten document analysis is an area of forensic science, with the goal of establishing authorship of documents through examination of inherent characteristics. Law enforcement agencies use standard protocols based on manual processing of handwritten documents. This method is time-consuming, is often subjective in its evaluation, and is not replicable. To overcome these limitations, in this paper we present a framework capable of extracting and analyzing intrinsic measures of manuscript documents related to text line heights, space between words, and character sizes using image processing and deep learning techniques. The final feature vector for each document involved consists of the mean and standard deviation for every type of measure collected. By quantifying the Euclidean distance between the feature vectors of the documents to be compared, authorship can be discerned. Our study pioneered the comparison between traditionally handwritten documents and those produced with digital tools (e.g., tablets). Experimental results demonstrate the ability of our method to objectively determine authorship in different writing media, outperforming the state of the art.
Authors: Zijie Pan, Jiachen Lu, Xiatian Zhu, Li Zhang
High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed to overcome this constraint by harnessing image generative models, pretrained on extensive curated web datasets, using knowledge transfer techniques like Score Distillation Sampling (SDS). Efficiently addressing the requirements of high-resolution rendering often necessitates the adoption of latent representation-based models, such as the Latent Diffusion Model (LDM). In this framework, a significant challenge arises: To compute gradients for individual image pixels, it is necessary to backpropagate gradients from the designated latent space through the frozen components of the image model, such as the VAE encoder used within LDM. However, this gradient propagation pathway has never been optimized, remaining uncontrolled during training. We find that the unregulated gradients adversely affect the 3D model's capacity in acquiring texture-related information from the image generative model, leading to poor quality appearance synthesis. To address this overarching challenge, we propose an innovative operation termed Pixel-wise Gradient Clipping (PGC) designed for seamless integration into existing 3D generative models, thereby enhancing their synthesis quality. Specifically, we control the magnitude of stochastic gradients by clipping the pixel-wise gradients efficiently, while preserving crucial texture-related gradient directions. Despite this simplicity and minimal extra cost, extensive experiments demonstrate the efficacy of our PGC in enhancing the performance of existing 3D generative models for high-resolution object rendering.
Authors: Hussain Alasmawi, Leanne Bricker, Mohammad Yaqub
Ultrasound is the primary imaging modality in clinical practice during pregnancy. More than 140M fetuses are born yearly, resulting in numerous scans. The availability of a large volume of fetal ultrasound scans presents the opportunity to train robust machine learning models. However, the abundance of scans also has its challenges, as manual labeling of each image is needed for supervised methods. Labeling is typically labor-intensive and requires expertise to annotate the images accurately. This study presents an unsupervised approach for automatically clustering ultrasound images into a large range of fetal views, reducing or eliminating the need for manual labeling. Our Fetal Ultrasound Semantic Clustering (FUSC) method is developed using a large dataset of 88,063 images and further evaluated on an additional unseen dataset of 8,187 images achieving over 92% clustering purity. The result of our investigation hold the potential to significantly impact the field of fetal ultrasound imaging and pave the way for more advanced automated labeling solutions. Finally, we make the code and the experimental setup publicly available to help advance the field.
Authors: Taehyo Kim, Hai Shu, Qiran Jia, Mony de Leon
Voxel-based multiple testing is widely used in neuroimaging data analysis. Traditional false discovery rate (FDR) control methods often ignore the spatial dependence among the voxel-based tests and thus suffer from substantial loss of testing power. While recent spatial FDR control methods have emerged, their validity and optimality remain questionable when handling the complex spatial dependencies of the brain. Concurrently, deep learning methods have revolutionized image segmentation, a task closely related to voxel-based multiple testing. In this paper, we propose DeepFDR, a novel spatial FDR control method that leverages unsupervised deep learning-based image segmentation to address the voxel-based multiple testing problem. Numerical studies, including comprehensive simulations and Alzheimer's disease FDG-PET image analysis, demonstrate DeepFDR's superiority over existing methods. DeepFDR not only excels in FDR control and effectively diminishes the false nondiscovery rate, but also boasts exceptional computational efficiency highly suited for tackling large-scale neuroimaging data.
Authors: Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski, Stephan Günnemann
Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoothing is a powerful framework for making models provably robust against small changes to their inputs - by guaranteeing robustness of the majority vote when randomly adding noise before classification. Yet, certifying robustness on such complex data via randomized smoothing is challenging when adversaries do not arbitrarily perturb entire objects (e.g. images) but only a subset of their entities (e.g. pixels). As a solution, we introduce hierarchical randomized smoothing: We partially smooth objects by adding random noise only on a randomly selected subset of their entities. By adding noise in a more targeted manner than existing methods we obtain stronger robustness guarantees while maintaining high accuracy. We initialize hierarchical smoothing using different noising distributions, yielding novel robustness certificates for discrete and continuous domains. We experimentally demonstrate the importance of hierarchical smoothing in image and node classification, where it yields superior robustness-accuracy trade-offs. Overall, hierarchical smoothing is an important contribution towards models that are both - certifiably robust to perturbations and accurate.
Authors: Zitong Chen, Chau Pham, Siqi Wang, Michael Doron, Nikita Moshkov, Bryan A. Plummer, Juan C. Caicedo
Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on instruments and experimental goals. Yet, there has not been a systemic attempt to create and evaluate neural networks that are invariant to the number and type of channels. As a result, trained models remain specific to individual studies and are hardly reusable for other microscopy settings. In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework. In addition, we adapted several existing techniques to create channel-adaptive models and compared their performance on this benchmark to fixed-channel, baseline models. We find that channel-adaptive models can generalize better to out-of-domain tasks and can be computationally efficient. We contribute a curated dataset (https://doi.org/10.5281/zenodo.7988357) and an evaluation API (https://github.com/broadinstitute/MorphEm.git) to facilitate objective comparisons in future research and applications.
Authors: Lunjun Zhang, Yuwen Xiong, Ze Yang, Sergio Casas, Rui Hu, Raquel Urtasun
Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling world models on robotic applications such as autonomous driving has been somewhat less rapid than scaling language models with Generative Pre-trained Transformers (GPT). We identify two reasons as major bottlenecks: dealing with complex and unstructured observation space, and having a scalable generative model. Consequently, we propose a novel world modeling approach that first tokenizes sensor observations with VQVAE, then predicts the future via discrete diffusion. To efficiently decode and denoise tokens in parallel, we recast Masked Generative Image Transformer into the discrete diffusion framework with a few simple changes, resulting in notable improvement. When applied to learning world models on point cloud observations, our model reduces prior SOTA Chamfer distance by more than 65% for 1s prediction, and more than 50% for 3s prediction, across NuScenes, KITTI Odometry, and Argoverse2 datasets. Our results demonstrate that discrete diffusion on tokenized agent experience can unlock the power of GPT-like unsupervised learning for robotic agents.
Authors: Yu Zhou, Jan Sollmann, Jianxu Chen
With the fast development of modern microscopes and bioimaging techniques, an unprecedentedly large amount of imaging data are being generated, stored, analyzed, and even shared through networks. The size of the data poses great challenges for current data infrastructure. One common way to reduce the data size is by image compression. This present study analyzes classic and deep learning based image compression methods, and their impact on deep learning based image processing models. Deep learning based label-free prediction models (i.e., predicting fluorescent images from bright field images) are used as an example application for comparison and analysis. Effective image compression methods could help reduce the data size significantly without losing necessary information, and therefore reduce the burden on data management infrastructure and permit fast transmission through the network for data sharing or cloud computing. To compress images in such a wanted way, multiple classical lossy image compression techniques are compared to several AI-based compression models provided by and trained with the CompressAI toolbox using python. These different compression techniques are compared in compression ratio, multiple image similarity measures and, most importantly, the prediction accuracy from label-free models on compressed images. We found that AI-based compression techniques largely outperform the classic ones and will minimally affect the downstream label-free task in 2D cases. In the end, we hope the present study could shed light on the potential of deep learning based image compression and the impact of image compression on downstream deep learning based image analysis models.
Authors: Elisa Warner, Joonsang Lee, William Hsu, Tanveer Syeda-Mahmood, Charles Kahn, Olivier Gevaert, Arvind Rao
Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also questions practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers. Despite advancements, challenges such as data biases and the scarcity of "big data" in many biomedical domains persist. We conclude with a discussion on effective innovation and collaborative efforts to further the miss
Authors: Hunor Laczkó, Meysam Madadi, Sergio Escalera, Jordi Gonzalez
RGB cloth generation has been deeply studied in the related literature, however, 3D garment generation remains an open problem. In this paper, we build a conditional variational autoencoder for 3D garment generation and draping. We propose a pyramid network to add garment details progressively in a canonical space, i.e. unposing and unshaping the garments w.r.t. the body. We study conditioning the network on surface normal UV maps, as an intermediate representation, which is an easier problem to optimize than 3D coordinates. Our results on two public datasets, CLOTH3D and CAPE, show that our model is robust, controllable in terms of detail generation by the use of multi-resolution pyramids, and achieves state-of-the-art results that can highly generalize to unseen garments, poses, and shapes even when training with small amounts of data.
Authors: Longyun Liao, Andrew Mitchell, Rong Zheng
In this paper, we present the novel task of estimating the extrinsic parameters of a virtual camera relative to a real camera in exercise videos with a mirror. This task poses a significant challenge in scenarios where the views from the real and mirrored cameras have no overlap or share salient features. To address this issue, prior knowledge of a human body and 2D joint locations are utilized to estimate the camera extrinsic parameters when a person is in front of a mirror. We devise a modified eight-point algorithm to obtain an initial estimation from 2D joint locations. The 2D joint locations are then refined subject to human body constraints. Finally, a RANSAC algorithm is employed to remove outliers by comparing their epipolar distances to a predetermined threshold. MirrorCalib is evaluated on both synthetic and real datasets and achieves a rotation error of 0.62{\deg}/1.82{\deg} and a translation error of 37.33/69.51 mm on the synthetic/real dataset, which outperforms the state-of-art method.
Authors: Mason Wang, Samuel Clarke, Jui-Hsien Wang, Ruohan Gao, Jiajun Wu
A room's acoustic properties are a product of the room's geometry, the objects within the room, and their specific positions. A room's acoustic properties can be characterized by its impulse response (RIR) between a source and listener location, or roughly inferred from recordings of natural signals present in the room. Variations in the positions of objects in a room can effect measurable changes in the room's acoustic properties, as characterized by the RIR. Existing datasets of RIRs either do not systematically vary positions of objects in an environment, or they consist of only simulated RIRs. We present SoundCam, the largest dataset of unique RIRs from in-the-wild rooms publicly released to date. It includes 5,000 10-channel real-world measurements of room impulse responses and 2,000 10-channel recordings of music in three different rooms, including a controlled acoustic lab, an in-the-wild living room, and a conference room, with different humans in positions throughout each room. We show that these measurements can be used for interesting tasks, such as detecting and identifying humans, and tracking their positions.
Authors: Yihong Luo, Siya Qiu, Xingjian Tao, Yujun Cai, Jing Tang
In this paper, we propose a novel generative model that utilizes a conditional Energy-Based Model (EBM) for enhancing Variational Autoencoder (VAE), termed Energy-Calibrated VAE (EC-VAE). Specifically, VAEs often suffer from blurry generated samples due to the lack of a tailored training on the samples generated in the generative direction. On the other hand, EBMs can generate high-quality samples but require expensive Markov Chain Monte Carlo (MCMC) sampling. To address these issues, we introduce a conditional EBM for calibrating the generative direction of VAE during training, without requiring it for the generation at test time. In particular, we train EC-VAE upon both the input data and the calibrated samples with adaptive weight to enhance efficacy while avoiding MCMC sampling at test time. Furthermore, we extend the calibration idea of EC-VAE to variational learning and normalizing flows, and apply EC-VAE to an additional application of zero-shot image restoration via neural transport prior and range-null theory. We evaluate the proposed method with two applications, including image generation and zero-shot image restoration, and the experimental results show that our method achieves the state-of-the-art performance over single-step non-adversarial generation. Our code is available at https://github.com/DJ-LYH/EC-VAE.
Authors: Lucas R. Schwengber, Lucas Resende, Paulo Orenstein, Roberto I. Oliveira
Hashing is at the heart of large-scale image similarity search, and recent methods have been substantially improved through deep learning techniques. Such algorithms typically learn continuous embeddings of the data. To avoid a subsequent costly binarization step, a common solution is to employ loss functions that combine a similarity learning term (to ensure similar images are grouped to nearby embeddings) and a quantization penalty term (to ensure that the embedding entries are close to binarized entries, e.g., -1 or 1). Still, the interaction between these two terms can make learning harder and the embeddings worse. We propose an alternative quantization strategy that decomposes the learning problem in two stages: first, perform similarity learning over the embedding space with no quantization; second, find an optimal orthogonal transformation of the embeddings so each coordinate of the embedding is close to its sign, and then quantize the transformed embedding through the sign function. In the second step, we parametrize orthogonal transformations using Householder matrices to efficiently leverage stochastic gradient descent. Since similarity measures are usually invariant under orthogonal transformations, this quantization strategy comes at no cost in terms of performance. The resulting algorithm is unsupervised, fast, hyperparameter-free and can be run on top of any existing deep hashing or metric learning algorithm. We provide extensive experimental results showing that this approach leads to state-of-the-art performance on widely used image datasets, and, unlike other quantization strategies, brings consistent improvements in performance to existing deep hashing algorithms.
Authors: Michael Kölle, Jonas Maurer, Philipp Altmann, Leo Sünkel, Jonas Stein, Claudia Linnhoff-Popien
Quantum computing offers the potential for superior computational capabilities, particularly for data-intensive tasks. However, the current state of quantum hardware puts heavy restrictions on input size. To address this, hybrid transfer learning solutions have been developed, merging pre-trained classical models, capable of handling extensive inputs, with variational quantum circuits. Yet, it remains unclear how much each component -- classical and quantum -- contributes to the model's results. We propose a novel hybrid architecture: instead of utilizing a pre-trained network for compression, we employ an autoencoder to derive a compressed version of the input data. This compressed data is then channeled through the encoder part of the autoencoder to the quantum component. We assess our model's classification capabilities against two state-of-the-art hybrid transfer learning architectures, two purely classical architectures and one quantum architecture. Their accuracy is compared across four datasets: Banknote Authentication, Breast Cancer Wisconsin, MNIST digits, and AudioMNIST. Our research suggests that classical components significantly influence classification in hybrid transfer learning, a contribution often mistakenly ascribed to the quantum element. The performance of our model aligns with that of a variational quantum circuit using amplitude embedding, positioning it as a feasible alternative.
Authors: Chun Bao, Jie Cao, Yaqian Ning, Tianhua Zhao, Zhijun Li, Zechen Wang, Li Zhang, Qun Hao
Infrared small target detection based on deep learning offers unique advantages in separating small targets from complex and dynamic backgrounds. However, the features of infrared small targets gradually weaken as the depth of convolutional neural network (CNN) increases. To address this issue, we propose a novel method for detecting infrared small targets called improved dense nested attention network (IDNANet), which is based on the transformer architecture. We preserve the dense nested structure of dense nested attention network (DNANet) and introduce the Swin-transformer during feature extraction stage to enhance the continuity of features. Furthermore, we integrate the ACmix attention structure into the dense nested structure to enhance the features of intermediate layers. Additionally, we design a weighted dice binary cross-entropy (WD-BCE) loss function to mitigate the negative impact of foreground-background imbalance in the samples. Moreover, we develop a dataset specifically for infrared small targets, called BIT-SIRST. The dataset comprises a significant amount of real-world targets and manually annotated labels, as well as synthetic data and corresponding labels. We have evaluated the effectiveness of our method through experiments conducted on public datasets. In comparison to other state-of-the-art methods, our approach outperforms in terms of probability of detection ($P_d$), false-alarm rate ($F_a$), and mean intersection of union ($mIoU$). The $mIoU$ reaches 90.89\% on the NUDT-SIRST dataset and 79.72\% on the SIRST dataset.
Authors: Keqing Du, Xinyu Yang, Hang Chen
Integrating deep learning and causal discovery has increased the interpretability of Temporal Action Segmentation (TAS) tasks. However, frame-level causal relationships exist many complicated noises outside the segment-level, making it infeasible to directly express macro action semantics. Thus, we propose Causal Abstraction Segmentation Refiner (CASR), which can refine TAS results from various models by enhancing video causality in marginalizing frame-level casual relationships. Specifically, we define the equivalent frame-level casual model and segment-level causal model, so that the causal adjacency matrix constructed from marginalized frame-level causal relationships has the ability to represent the segmnet-level causal relationships. CASR works out by reducing the difference in the causal adjacency matrix between we constructed and pre-segmentation results of backbone models. In addition, we propose a novel evaluation metric Causal Edit Distance (CED) to evaluate the causal interpretability. Extensive experimental results on mainstream datasets indicate that CASR significantly surpasses existing various methods in action segmentation performance, as well as in causal explainability and generalization.
Authors: Matías Tailanian, Marina Gardella, Álvaro Pardo, Pablo Musé
From its acquisition in the camera sensors to its storage, different operations are performed to generate the final image. This pipeline imprints specific traces into the image to form a natural watermark. Tampering with an image disturbs these traces; these disruptions are clues that are used by most methods to detect and locate forgeries. In this article, we assess the capabilities of diffusion models to erase the traces left by forgers and, therefore, deceive forensics methods. Such an approach has been recently introduced for adversarial purification, achieving significant performance. We show that diffusion purification methods are well suited for counter-forensics tasks. Such approaches outperform already existing counter-forensics techniques both in deceiving forensics methods and in preserving the natural look of the purified images. The source code is publicly available at https://github.com/mtailanian/diff-cf.
Authors: Shicheng Xu, Danyang Hou, Liang Pang, Jingcheng Deng, Jun Xu, Huawei Shen, Xueqi Cheng
With the advancement of generation models, AI-generated content (AIGC) is becoming more realistic, flooding the Internet. A recent study suggests that this phenomenon causes source bias in text retrieval for web search. Specifically, neural retrieval models tend to rank generated texts higher than human-written texts. In this paper, we extend the study of this bias to cross-modal retrieval. Firstly, we successfully construct a suitable benchmark to explore the existence of the bias. Subsequent extensive experiments on this benchmark reveal that AI-generated images introduce an invisible relevance bias to text-image retrieval models. Specifically, our experiments show that text-image retrieval models tend to rank the AI-generated images higher than the real images, even though the AI-generated images do not exhibit more visually relevant features to the query than real images. This invisible relevance bias is prevalent across retrieval models with varying training data and architectures. Furthermore, our subsequent exploration reveals that the inclusion of AI-generated images in the training data of the retrieval models exacerbates the invisible relevance bias. The above phenomenon triggers a vicious cycle, which makes the invisible relevance bias become more and more serious. To elucidate the potential causes of invisible relevance and address the aforementioned issues, we introduce an effective training method aimed at alleviating the invisible relevance bias. Subsequently, we apply our proposed debiasing method to retroactively identify the causes of invisible relevance, revealing that the AI-generated images induce the image encoder to embed additional information into their representation. This information exhibits a certain consistency across generated images with different semantics and can make the retriever estimate a higher relevance score.
Authors: Jonathan Roberts, Timo Lüddecke, Rehan Sheikh, Kai Han, Samuel Albanie
Multimodal large language models (MLLMs) have shown remarkable capabilities across a broad range of tasks but their knowledge and abilities in the geographic and geospatial domains are yet to be explored, despite potential wide-ranging benefits to navigation, environmental research, urban development, and disaster response. We conduct a series of experiments exploring various vision capabilities of MLLMs within these domains, particularly focusing on the frontier model GPT-4V, and benchmark its performance against open-source counterparts. Our methodology involves challenging these models with a small-scale geographic benchmark consisting of a suite of visual tasks, testing their abilities across a spectrum of complexity. The analysis uncovers not only where such models excel, including instances where they outperform humans, but also where they falter, providing a balanced view of their capabilities in the geographic domain. To enable the comparison and evaluation of future models, our benchmark will be publicly released.
Authors: Trung-Hieu Hoang, Duc Minh Vo, Minh N. Do
Current test-time adaptation (TTA) approaches aim to adapt to environments that change continuously. Yet, when the environments not only change but also recur in a correlated manner over time, such as in the case of day-night surveillance cameras, it is unclear whether the adaptability of these methods is sustained after a long run. This study aims to examine the error accumulation of TTA models when they are repeatedly exposed to previous testing environments, proposing a novel testing setting called episodic TTA. To study this phenomenon, we design a simulation of TTA process on a simple yet representative $\epsilon$-perturbed Gaussian Mixture Model Classifier and derive the theoretical findings revealing the dataset- and algorithm-dependent factors that contribute to the gradual degeneration of TTA methods through time. Our investigation has led us to propose a method, named persistent TTA (PeTTA). PeTTA senses the model divergence towards a collapsing and adjusts the adaptation strategy of TTA, striking a balance between two primary objectives: adaptation and preventing model collapse. The stability of PeTTA in the face of episodic TTA scenarios has been demonstrated through a set of comprehensive experiments on various benchmarks.
Authors: Amber Yijia Zheng, Raymond A. Yeh
Advancements in text-to-image models and fine-tuning methods have led to the increasing risk of malicious adaptation, i.e., fine-tuning to generate harmful unauthorized content. Recent works, e.g., Glaze or MIST, have developed data-poisoning techniques which protect the data against adaptation methods. In this work, we consider an alternative paradigm for protection. We propose to ``immunize'' the model by learning model parameters that are difficult for the adaptation methods when fine-tuning malicious content; in short IMMA. Empirical results show IMMA's effectiveness against malicious adaptations, including mimicking the artistic style and learning of inappropriate/unauthorized content, over three adaptation methods: LoRA, Textual-Inversion, and DreamBooth.
Authors: Jian Zhu, Yu Cui, Zhangmin Huang, Xingyu Li, Lei Liu, Lingfang Zeng, Li-Rong Dai
The multi-view hash method converts heterogeneous data from multiple views into binary hash codes, which is one of the critical technologies in multimedia retrieval. However, the current methods mainly explore the complementarity among multiple views while lacking confidence learning and fusion. Moreover, in practical application scenarios, the single-view data contain redundant noise. To conduct the confidence learning and eliminate unnecessary noise, we propose a novel Adaptive Confidence Multi-View Hashing (ACMVH) method. First, a confidence network is developed to extract useful information from various single-view features and remove noise information. Furthermore, an adaptive confidence multi-view network is employed to measure the confidence of each view and then fuse multi-view features through a weighted summation. Lastly, a dilation network is designed to further enhance the feature representation of the fused features. To the best of our knowledge, we pioneer the application of confidence learning into the field of multimedia retrieval. Extensive experiments on two public datasets show that the proposed ACMVH performs better than state-of-the-art methods (maximum increase of 3.24%). The source code is available at https://github.com/HackerHyper/ACMVH.
Authors: Candi Zheng, Yuan Lan
Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a sampling method that provides first-principle non-linear correction for classifier-free guided DDPMs. Such correction forces the guided DDPMs to respect the Fokker-Planck equation of their underlying diffusion process, in a way that is training-free, derivative-free, and compatible with existing sampling methods. Experiments show that characteristic guidance enhances control and reduces color and exposure issues in image generation, proving effective in diverse applications ranging from latent space sampling to solving physics problems like magnet phase transitions.
Authors: Qiaosi Tang, Ranjala Ratnayake, Gustavo Seabra, Zhe Jiang, Ruogu Fang, Lina Cui, Yousong Ding, Tamer Kahveci, Jiang Bian, Chenglong Li, Hendrik Luesch, Yanjun Li
Morphological profiling is a valuable tool in phenotypic drug discovery. The advent of high-throughput automated imaging has enabled the capturing of a wide range of morphological features of cells or organisms in response to perturbations at the single-cell resolution. Concurrently, significant advances in machine learning and deep learning, especially in computer vision, have led to substantial improvements in analyzing large-scale high-content images at high-throughput. These efforts have facilitated understanding of compound mechanism-of-action (MOA), drug repurposing, characterization of cell morphodynamics under perturbation, and ultimately contributing to the development of novel therapeutics. In this review, we provide a comprehensive overview of the recent advances in the field of morphological profiling. We summarize the image profiling analysis workflow, survey a broad spectrum of analysis strategies encompassing feature engineering- and deep learning-based approaches, and introduce publicly available benchmark datasets. We place a particular emphasis on the application of deep learning in this pipeline, covering cell segmentation, image representation learning, and multimodal learning. Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.
Authors: Kun Yuan, Manasi Kattel, Joel L. Lavanchy, Nassir Navab, Vinkle Srivastav, Nicolas Padoy
Modern operating room is becoming increasingly complex, requiring innovative intra-operative support systems. While the focus of surgical data science has largely been on video analysis, integrating surgical computer vision with language capabilities is emerging as a necessity. Our work aims to advance Visual Question Answering (VQA) in the surgical context with scene graph knowledge, addressing two main challenges in the current surgical VQA systems: removing question-condition bias in the surgical VQA dataset and incorporating scene-aware reasoning in the surgical VQA model design. First, we propose a Surgical Scene Graph-based dataset, SSG-QA, generated by employing segmentation and detection models on publicly available datasets. We build surgical scene graphs using spatial and action information of instruments and anatomies. These graphs are fed into a question engine, generating diverse QA pairs. Our SSG-QA dataset provides a more complex, diverse, geometrically grounded, unbiased, and surgical action-oriented dataset compared to existing surgical VQA datasets. We then propose SSG-QA-Net, a novel surgical VQA model incorporating a lightweight Scene-embedded Interaction Module (SIM), which integrates geometric scene knowledge in the VQA model design by employing cross-attention between the textual and the scene features. Our comprehensive analysis of the SSG-QA dataset shows that SSG-QA-Net outperforms existing methods across different question types and complexities. We highlight that the primary limitation in the current surgical VQA systems is the lack of scene knowledge to answer complex queries. We present a novel surgical VQA dataset and model and show that results can be significantly improved by incorporating geometric scene features in the VQA model design. The source code and the dataset will be made publicly available at: https://github.com/CAMMA-public/SSG-QA
Authors: Muktabh Mayank Srivastava
Retail product or packaged grocery goods images need to classified in various computer vision applications like self checkout stores, supply chain automation and retail execution evaluation. Previous works explore ways to finetune deep models for this purpose. But because of the fact that finetuning a large model or even linear layer for a pretrained backbone requires to run at least a few epochs of gradient descent for every new retail product added in classification range, frequent retrainings are needed in a real world scenario. In this work, we propose finetuning the vision encoder of a CLIP model in a way that its embeddings can be easily used for nearest neighbor based classification, while also getting accuracy close to or exceeding full finetuning. A nearest neighbor based classifier needs no incremental training for new products, thus saving resources and wait time.
Authors: Chaojian Li, Bichen Wu, Peter Vajda, Yingyan (Celine)Lin
Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Nevertheless, achieving real-time NeRF rendering in large-scale scenes has presented challenges, often leading to the adoption of either intricate baked mesh representations with a substantial number of triangles or resource-intensive ray marching in baked representations. We challenge these conventions, observing that high-quality geometry, represented by meshes with substantial triangles, is not necessary for achieving photorealistic rendering quality. Consequently, we propose MixRT, a novel NeRF representation that includes a low-quality mesh, a view-dependent displacement map, and a compressed NeRF model. This design effectively harnesses the capabilities of existing graphics hardware, thus enabling real-time NeRF rendering on edge devices. Leveraging a highly-optimized WebGL-based rendering framework, our proposed MixRT attains real-time rendering speeds on edge devices (over 30 FPS at a resolution of 1280 x 720 on a MacBook M1 Pro laptop), better rendering quality (0.2 PSNR higher in indoor scenes of the Unbounded-360 datasets), and a smaller storage size (less than 80% compared to state-of-the-art methods).
Authors: Ruiyuan Zhang, Jiaxiang Liu, Zexi Li, Hao Dong, Jie Fu, Chao Wu
Geometric fracture assembly presents a challenging practical task in archaeology and 3D computer vision. Previous methods have focused solely on assembling fragments based on semantic information, which has limited the quantity of objects that can be effectively assembled. Therefore, there is a need to develop a scalable framework for geometric fracture assembly without relying on semantic information. To improve the effectiveness of assembling geometric fractures without semantic information, we propose a co-creation space comprising several assemblers capable of gradually and unambiguously assembling fractures. Additionally, we introduce a novel loss function, i.e., the geometric-based collision loss, to address collision issues during the fracture assembly process and enhance the results. Our framework exhibits better performance on both PartNet and Breaking Bad datasets compared to existing state-of-the-art frameworks. Extensive experiments and quantitative comparisons demonstrate the effectiveness of our proposed framework, which features linear computational complexity, enhanced abstraction, and improved generalization. Our code is publicly available at https://github.com/Ruiyuan-Zhang/CCS.
Authors: Abraham Woubie, Enoch Solomon, Eyael Solomon Emiru
In various verification systems, Restricted Boltzmann Machines (RBMs) have demonstrated their efficacy in both front-end and back-end processes. In this work, we propose the use of RBMs to the image clustering tasks. RBMs are trained to convert images into image embeddings. We employ the conventional bottom-up Agglomerative Hierarchical Clustering (AHC) technique. To address the challenge of limited test face image data, we introduce Agglomerative Hierarchical Clustering based Method for Image Clustering using Restricted Boltzmann Machine (AHC-RBM) with two major steps. Initially, a universal RBM model is trained using all available training dataset. Subsequently, we train an adapted RBM model using the data from each test image. Finally, RBM vectors which is the embedding vector is generated by concatenating the visible-to-hidden weight matrices of these adapted models, and the bias vectors. These vectors effectively preserve class-specific information and are utilized in image clustering tasks. Our experimental results, conducted on two benchmark image datasets (MS-Celeb-1M and DeepFashion), demonstrate that our proposed approach surpasses well-known clustering algorithms such as k-means, spectral clustering, and approximate Rank-order.
Authors: Zixuan Huang, Stefan Stojanov, Anh Thai, Varun Jampani, James M. Rehg
We study the problem of single-image zero-shot 3D shape reconstruction. Recent works learn zero-shot shape reconstruction through generative modeling of 3D assets, but these models are computationally expensive at train and inference time. In contrast, the traditional approach to this problem is regression-based, where deterministic models are trained to directly regress the object shape. Such regression methods possess much higher computational efficiency than generative methods. This raises a natural question: is generative modeling necessary for high performance, or conversely, are regression-based approaches still competitive? To answer this, we design a strong regression-based model, called ZeroShape, based on the converging findings in this field and a novel insight. We also curate a large real-world evaluation benchmark, with objects from three different real-world 3D datasets. This evaluation benchmark is more diverse and an order of magnitude larger than what prior works use to quantitatively evaluate their models, aiming at reducing the evaluation variance in our field. We show that ZeroShape not only achieves superior performance over state-of-the-art methods, but also demonstrates significantly higher computational and data efficiency.
Authors: Cheng-En Wu, Azadeh Davoodi, Yu Hen Hu
This paper presents a novel approach to network pruning, targeting block pruning in deep neural networks for edge computing environments. Our method diverges from traditional techniques that utilize proxy metrics, instead employing a direct block removal strategy to assess the impact on classification accuracy. This hands-on approach allows for an accurate evaluation of each block's importance. We conducted extensive experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using ResNet architectures. Our results demonstrate the efficacy of our method, particularly on large-scale datasets like ImageNet with ResNet50, where it excelled in reducing model size while retaining high accuracy, even when pruning a significant portion of the network. The findings underscore our method's capability in maintaining an optimal balance between model size and performance, especially in resource-constrained edge computing scenarios.
Authors: Zhengze Xu, Dongyue Wu, Changqian Yu, Xiangxiang Chu, Nong Sang, Changxin Gao
Recent real-time semantic segmentation methods usually adopt an additional semantic branch to pursue rich long-range context. However, the additional branch incurs undesirable computational overhead and slows inference speed. To eliminate this dilemma, we propose SCTNet, a single branch CNN with transformer semantic information for real-time segmentation. SCTNet enjoys the rich semantic representations of an inference-free semantic branch while retaining the high efficiency of lightweight single branch CNN. SCTNet utilizes a transformer as the training-only semantic branch considering its superb ability to extract long-range context. With the help of the proposed transformer-like CNN block CFBlock and the semantic information alignment module, SCTNet could capture the rich semantic information from the transformer branch in training. During the inference, only the single branch CNN needs to be deployed. We conduct extensive experiments on Cityscapes, ADE20K, and COCO-Stuff-10K, and the results show that our method achieves the new state-of-the-art performance. The code and model is available at https://github.com/xzz777/SCTNet
Authors: Yuming Huang, Yingpin Chen, Changhui Wu, Hanrong Xie, Binhui Song, Hui Wang
The Swin Transformer image super-resolution reconstruction network only relies on the long-range relationship of window attention and shifted window attention to explore features. This mechanism has two limitations. On the one hand, it only focuses on global features while ignoring local features. On the other hand, it is only concerned with spatial feature interactions while ignoring channel features and channel interactions, thus limiting its non-linear mapping ability. To address the above limitations, this paper proposes enhanced Swin Transformer modules via alternating aggregation of local-global features. In the local feature aggregation stage, we introduce a shift convolution to realize the interaction between local spatial information and channel information. Then, a block sparse global perception module is introduced in the global feature aggregation stage. In this module, we reorganize the spatial information first, then send the recombination information into a multi-layer perceptron unit to implement the global perception. After that, a multi-scale self-attention module and a low-parameter residual channel attention module are introduced to realize information aggregation at different scales. Finally, the proposed network is validated on five publicly available datasets. The experimental results show that the proposed network outperforms the other state-of-the-art super-resolution networks.
Authors: Qianliang Wu, Haobo Jiang, Yaqing Ding, Lei Luo, Jin Xie, Jian Yang
Efficiently finding optimal correspondences between point clouds is crucial for solving both rigid and non-rigid point cloud registration problems. Existing methods often rely on geometric or semantic feature embedding to establish correspondences and estimate transformations or flow fields. Recently, state-of-the-art methods have employed RAFT-like iterative updates to refine the solution. However, these methods have certain limitations. Firstly, their iterative refinement design lacks transparency, and their iterative updates follow a fixed path during the refinement process, which can lead to suboptimal results. Secondly, these methods overlook the importance of refining or optimizing correspondences (or matching matrices) as a precursor to solving transformations or flow fields. They typically compute candidate correspondences based on distances in the point feature space. However, they only project the candidate matching matrix into some matrix space once with Sinkhorn or dual softmax operations to obtain final correspondences. This one-shot projected matching matrix may be far from the globally optimal one, and these approaches do not consider the distribution of the target matching matrix. In this paper, we propose a novel approach that exploits the Denoising Diffusion Model to predict a searching gradient for the optimal matching matrix within the Doubly Stochastic Matrix Space. During the reverse denoising process, our method iteratively searches for better solutions along this denoising gradient, which points towards the maximum likelihood direction of the target matching matrix. Our method offers flexibility by allowing the search to start from any initial matching matrix provided by the online backbone or white noise. Experimental evaluations on the 3DMatch/3DLoMatch and 4DMatch/4DLoMatch datasets demonstrate the effectiveness of our newly designed framework.
Authors: Saravanabalagi Ramachandran, Nathaniel Cibik, Ganesh Sistu, John McDonald
Motion segmentation is a complex yet indispensable task in autonomous driving. The challenges introduced by the ego-motion of the cameras, radial distortion in fisheye lenses, and the need for temporal consistency make the task more complicated, rendering traditional and standard Convolutional Neural Network (CNN) approaches less effective. The consequent laborious data labeling, representation of diverse and uncommon scenarios, and extensive data capture requirements underscore the imperative of synthetic data for improving machine learning model performance. To this end, we employ the PD-WoodScape synthetic dataset developed by Parallel Domain, alongside the WoodScape fisheye dataset. Thus, we present the WoodScape fisheye motion segmentation challenge for autonomous driving, held as part of the CVPR 2023 Workshop on Omnidirectional Computer Vision (OmniCV). As one of the first competitions focused on fisheye motion segmentation, we aim to explore and evaluate the potential and impact of utilizing synthetic data in this domain. In this paper, we provide a detailed analysis on the competition which attracted the participation of 112 global teams and a total of 234 submissions. This study delineates the complexities inherent in the task of motion segmentation, emphasizes the significance of fisheye datasets, articulate the necessity for synthetic datasets and the resultant domain gap they engender, outlining the foundational blueprint for devising successful solutions. Subsequently, we delve into the details of the baseline experiments and winning methods evaluating their qualitative and quantitative results, providing with useful insights.
Authors: Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Yusen Hu, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Bin Luo, Yifeng Geng, Xuansong Xie, Jingren Zhou
This paper introduces the WordArt Designer API, a novel framework for user-driven artistic typography synthesis utilizing Large Language Models (LLMs) on ModelScope. We address the challenge of simplifying artistic typography for non-professionals by offering a dynamic, adaptive, and computationally efficient alternative to traditional rigid templates. Our approach leverages the power of LLMs to understand and interpret user input, facilitating a more intuitive design process. We demonstrate through various case studies how users can articulate their aesthetic preferences and functional requirements, which the system then translates into unique and creative typographic designs. Our evaluations indicate significant improvements in user satisfaction, design flexibility, and creative expression over existing systems. The WordArt Designer API not only democratizes the art of typography but also opens up new possibilities for personalized digital communication and design.
Authors: Zeyu Li, Jingsheng Gao, Tong Yu, Suncheng Xiang, Jiacheng Ruan, Ting Liu, Yuzhuo Fu
Existing research on audio classification faces challenges in recognizing attributes of passive underwater vessel scenarios and lacks well-annotated datasets due to data privacy concerns. In this study, we introduce CLAPP (Contrastive Language-Audio Pre-training in Passive Underwater Vessel Classification), a novel model. Our aim is to train a neural network using a wide range of vessel audio and vessel state text pairs obtained from an oceanship dataset. CLAPP is capable of directly learning from raw vessel audio data and, when available, from carefully curated labels, enabling improved recognition of vessel attributes in passive underwater vessel scenarios. Model's zero-shot capability allows predicting the most relevant vessel state description for a given vessel audio, without directly optimizing for the task. Our approach aims to solve 2 challenges: vessel audio-text classification and passive underwater vessel audio attribute recognition. The proposed method achieves new state-of-the-art results on both Deepship and Shipsear public datasets, with a notable margin of about 7%-13% for accuracy compared to prior methods on zero-shot task.
Authors: Yichen Zhu, Minjie Zhu, Ning Liu, Zhicai Ou, Xiaofeng Mou, Jian Tang
In this paper, we introduce LLaVA-$\phi$ (LLaVA-Phi), an efficient multi-modal assistant that harnesses the power of the recently advanced small language model, Phi-2, to facilitate multi-modal dialogues. LLaVA-Phi marks a notable advancement in the realm of compact multi-modal models. It demonstrates that even smaller language models, with as few as 2.7B parameters, can effectively engage in intricate dialogues that integrate both textual and visual elements, provided they are trained with high-quality corpora. Our model delivers commendable performance on publicly available benchmarks that encompass visual comprehension, reasoning, and knowledge-based perception. Beyond its remarkable performance in multi-modal dialogue tasks, our model opens new avenues for applications in time-sensitive environments and systems that require real-time interaction, such as embodied agents. It highlights the potential of smaller language models to achieve sophisticated levels of understanding and interaction, while maintaining greater resource efficiency.The project is available at {https://github.com/zhuyiche/llava-phi}.
Authors: Hui Zeng, Biwei Chen, Anjie Peng
Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks. Yet, making a targeted AE transferable across unknown models remains challenging. In this paper, to alleviate the overfitting dilemma common in an AE crafted by existing simple iterative attacks, we propose fine-tuning it in the feature space. Specifically, starting with an AE generated by a baseline attack, we encourage the features conducive to the target class and discourage the features to the original class in a middle layer of the source model. Extensive experiments demonstrate that only a few iterations of fine-tuning can boost existing attacks' targeted transferability nontrivially and universally. Our results also verify that the simple iterative attacks can yield comparable or even better transferability than the resource-intensive methods, which rest on training target-specific classifiers or generators with additional data. The code is available at: github.com/zengh5/TA_feature_FT.
Authors: Navapat Nananukul, Hamid Soltanian-zadeh, Mohammad Rostami
Automatic semantic segmentation of magnetic resonance imaging (MRI) images using deep neural networks greatly assists in evaluating and planning treatments for various clinical applications. However, training these models is conditioned on the availability of abundant annotated data to implement the end-to-end supervised learning procedure. Even if we annotate enough data, MRI images display considerable variability due to factors such as differences in patients, MRI scanners, and imaging protocols. This variability necessitates retraining neural networks for each specific application domain, which, in turn, requires manual annotation by expert radiologists for all new domains. To relax the need for persistent data annotation, we develop a method for unsupervised federated domain adaptation using multiple annotated source domains. Our approach enables the transfer of knowledge from several annotated source domains to adapt a model for effective use in an unannotated target domain. Initially, we ensure that the target domain data shares similar representations with each source domain in a latent embedding space, modeled as the output of a deep encoder, by minimizing the pair-wise distances of the distributions for the target domain and the source domains. We then employ an ensemble approach to leverage the knowledge obtained from all domains. We provide theoretical analysis and perform experiments on the MICCAI 2016 multi-site dataset to demonstrate our method is effective.
Authors: Xin He, Longhui Wei, Lingxi Xie, Qi Tian
Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months. The prevailing trend involves adopting data-driven methodologies, wherein diverse instruction-following datasets are collected. However, a prevailing challenge persists in these approaches, specifically in relation to the limited visual perception ability, as CLIP-like encoders employed for extracting visual information from inputs. Though these encoders are pre-trained on billions of image-text pairs, they still grapple with the information loss dilemma, given that textual captions only partially capture the contents depicted in images. To address this limitation, this paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism. Specifically, we introduce a novel method that incorporates multi-task encoders and visual tools into the existing MLLMs training and inference pipeline, aiming to provide a more comprehensive and accurate summarization of visual inputs. Extensive experiments have evaluated its effectiveness of advancing MLLMs, showcasing improved visual perception achieved through the integration of visual experts.
Authors: Zeju Li, Chao Zhang, Xiaoyan Wang, Ruilong Ren, Yifan Xu, Ruifei Ma, Xiangde Liu
The remarkable potential of multi-modal large language models (MLLMs) in comprehending both vision and language information has been widely acknowledged. However, the scarcity of 3D scenes-language pairs in comparison to their 2D counterparts, coupled with the inadequacy of existing approaches in understanding of 3D scenes by LLMs, poses a significant challenge. In response, we collect and construct an extensive dataset comprising 75K instruction-response pairs tailored for 3D scenes. This dataset addresses tasks related to 3D VQA, 3D grounding, and 3D conversation. To further enhance the integration of 3D spatial information into LLMs, we introduce a novel and efficient prompt tuning paradigm, 3DMIT. This paradigm eliminates the alignment stage between 3D scenes and language and extends the instruction prompt with the 3D modality information including the entire scene and segmented objects. We evaluate the effectiveness of our method across diverse tasks in the 3D scene domain and find that our approach serves as a strategic means to enrich LLMs' comprehension of the 3D world. Our code is available at https://github.com/staymylove/3DMIT.
Authors: Chenhongyi Yang, Tianwei Lin, Lichao Huang, Elliot J. Crowley
In this work, we present WidthFormer, a novel transformer-based Bird's-Eye-View (BEV) 3D detection method tailored for real-time autonomous-driving applications. WidthFormer is computationally efficient, robust and does not require any special engineering effort to deploy. In this work, we propose a novel 3D positional encoding mechanism capable of accurately encapsulating 3D geometric information, which enables our model to generate high-quality BEV representations with only a single transformer decoder layer. This mechanism is also beneficial for existing sparse 3D object detectors. Inspired by the recently-proposed works, we further improve our model's efficiency by vertically compressing the image features when serving as attention keys and values. We also introduce two modules to compensate for potential information loss due to feature compression. Experimental evaluation on the widely-used nuScenes 3D object detection benchmark demonstrates that our method outperforms previous approaches across different 3D detection architectures. More importantly, our model is highly efficient. For example, when using $256\times 704$ input images, it achieves 1.5 ms and 2.8 ms latency on NVIDIA 3090 GPU and Horizon Journey-5 computation solutions, respectively. Furthermore, WidthFormer also exhibits strong robustness to different degrees of camera perturbations. Our study offers valuable insights into the deployment of BEV transformation methods in real-world, complex road environments. Code is available at https://github.com/ChenhongyiYang/WidthFormer .
Authors: Jingtao Sun, Yaonan Wang, Danwei Wang
Tracking the object 6-DoF pose is crucial for various downstream robot tasks and real-world applications. In this paper, we investigate the real-world robot task of aerial vision guidance for aerial robotics manipulation, utilizing category-level 6-DoF pose tracking. Aerial conditions inevitably introduce special challenges, such as rapid viewpoint changes in pitch and roll and inter-frame differences. To support these challenges in task, we firstly introduce a robust category-level 6-DoF pose tracker (Robust6DoF). This tracker leverages shape and temporal prior knowledge to explore optimal inter-frame keypoint pairs, generated under a priori structural adaptive supervision in a coarse-to-fine manner. Notably, our Robust6DoF employs a Spatial-Temporal Augmentation module to deal with the problems of the inter-frame differences and intra-class shape variations through both temporal dynamic filtering and shape-similarity filtering. We further present a Pose-Aware Discrete Servo strategy (PAD-Servo), serving as a decoupling approach to implement the final aerial vision guidance task. It contains two servo action policies to better accommodate the structural properties of aerial robotics manipulation. Exhaustive experiments on four well-known public benchmarks demonstrate the superiority of our Robust6DoF. Real-world tests directly verify that our Robust6DoF along with PAD-Servo can be readily used in real-world aerial robotic applications.
Authors: Casper Fibaek, Luke Camilleri, Andreas Luyts, Nikolaos Dionelis, Bertrand Le Saux
Massive amounts of unlabelled data are captured by Earth Observation (EO) satellites, with the Sentinel-2 constellation generating 1.6 TB of data daily. This makes Remote Sensing a data-rich domain well suited to Machine Learning (ML) solutions. However, a bottleneck in applying ML models to EO is the lack of annotated data as annotation is a labour-intensive and costly process. As a result, research in this domain has focused on Self-Supervised Learning and Foundation Model approaches. This paper addresses the need to evaluate different Foundation Models on a fair and uniform benchmark by introducing the PhilEO Bench, a novel evaluation framework for EO Foundation Models. The framework comprises of a testbed and a novel 400 GB Sentinel-2 dataset containing labels for three downstream tasks, building density estimation, road segmentation, and land cover classification. We present experiments using our framework evaluating different Foundation Models, including Prithvi and SatMAE, at multiple n-shots and convergence rates.
Authors: Yinghui Xing, Litao Qu, Shizhou Zhang, Kai Zhang, Yanning Zhang
Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution. When taking original MS and PAN images as inputs, they always obtain sub-optimal results due to the scale variation. In this paper, we propose to explore the self-supervised representation of pansharpening by designing a cross-predictive diffusion model, named CrossDiff. It has two-stage training. In the first stage, we introduce a cross-predictive pretext task to pre-train the UNet structure based on conditional DDPM, while in the second stage, the encoders of the UNets are frozen to directly extract spatial and spectral features from PAN and MS, and only the fusion head is trained to adapt for pansharpening task. Extensive experiments show the effectiveness and superiority of the proposed model compared with state-of-the-art supervised and unsupervised methods. Besides, the cross-sensor experiments also verify the generalization ability of proposed self-supervised representation learners for other satellite's datasets. We will release our code for reproducibility.
Authors: Chenbin Pan, Burhaneddin Yaman, Tommaso Nesti, Abhirup Mallik, Alessandro G Allievi, Senem Velipasalar, Liu Ren
Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning. While vision-only autonomous driving methods have recently achieved notable performance, through enhanced scene understanding, several key issues, including lack of reasoning, low generalization performance and long-tail scenarios, still need to be addressed. In this paper, we present VLP, a novel Vision-Language-Planning framework that exploits language models to bridge the gap between linguistic understanding and autonomous driving. VLP enhances autonomous driving systems by strengthening both the source memory foundation and the self-driving car's contextual understanding. VLP achieves state-of-the-art end-to-end planning performance on the challenging NuScenes dataset by achieving 35.9\% and 60.5\% reduction in terms of average L2 error and collision rates, respectively, compared to the previous best method. Moreover, VLP shows improved performance in challenging long-tail scenarios and strong generalization capabilities when faced with new urban environments.