The Segment Anything Model (SAM) is a powerful foundation model that has revolutionised image segmentation. To apply SAM to surgical instrument segmentation, a common approach is to locate precise points or boxes of instruments and then use them as prompts for SAM in a zero-shot manner. However, we observe two problems with this naive pipeline: (1) the domain gap between natural objects and surgical instruments leads to inferior generalisation of SAM; and (2) SAM relies on precise point or box locations for accurate segmentation, requiring either extensive manual guidance or a well-performing specialist detector for prompt preparation, which leads to a complex multi-stage pipeline. To address these problems, we introduce SurgicalSAM, a novel end-to-end efficient-tuning approach for SAM to effectively integrate surgical-specific information with SAM’s pre-trained knowledge for improved generalisation. Specifically, we propose a lightweight prototype-based class prompt encoder for tuning, which directly generates prompt embeddings from class prototypes and eliminates the use of explicit prompts for improved robustness and a simpler pipeline. In addition, to address the low inter-class variance among surgical instrument categories, we propose contrastive prototype learning, further enhancing the discrimination of the class prototypes for more accurate class prompting. The results of extensive experiments on both EndoVis2018 and EndoVis2017 datasets demonstrate that SurgicalSAM achieves state-of-the-art performance while only requiring a small number of tunable parameters. The source code is available at https://github.com/wenxi-yue/SurgicalSAM.
论文检索
输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
Dual-lens super-resolution (SR) is a practical scenario for reference (Ref) based SR by utilizing the telephoto image (Ref) to assist the super-resolution of the low-resolution wide-angle image (LR input). Different from general RefSR, the Ref in dual-lens SR only covers the overlapped field of view (FoV) area. However, current dual-lens SR methods rarely utilize these specific characteristics and directly perform dense matching between the LR input and Ref. Due to the resolution gap between LR and Ref, the matching may miss the best-matched candidate and destroy the consistent structures in the overlapped FoV area. Different from them, we propose to first align the Ref with the center region (namely the overlapped FoV area) of the LR input by combining global warping and local warping to make the aligned Ref be sharp and consistent. Then, we formulate the aligned Ref and LR center as value-key pairs, and the corner region of the LR is formulated as queries. In this way, we propose a kernel-free matching strategy by matching between the LR-corner (query) and LR-center (key) regions, and the corresponding aligned Ref (value) can be warped to the corner region of the target. Our kernel-free matching strategy avoids the resolution gap between LR and Ref, which makes our network have better generalization ability. In addition, we construct a DuSR-Real dataset with (LR, Ref, HR) triples, where the LR and HR are well aligned. Experiments on three datasets demonstrate that our method outperforms the second-best method by a large margin. Our code and dataset are available at https://github.com/ZifanCui/KeDuSR.
SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization
PDF ↗In this paper, we introduce Segmentation-Driven Deformation Multi-View Stereo (SD-MVS), a method that can effectively tackle challenges in 3D reconstruction of textureless areas. We are the first to adopt the Segment Anything Model (SAM) to distinguish semantic instances in scenes and further leverage these constraints for pixelwise patch deformation on both matching cost and propagation. Concurrently, we propose a unique refinement strategy that combines spherical coordinates and gradient descent on normals and pixelwise search interval on depths, significantly improving the completeness of reconstructed 3D model. Furthermore, we adopt the Expectation-Maximization (EM) algorithm to alternately optimize the aggregate matching cost and hyperparameters, effectively mitigating the problem of parameters being excessively dependent on empirical tuning. Evaluations on the ETH3D high-resolution multi-view stereo benchmark and the Tanks and Temples dataset demonstrate that our method can achieve state-of-the-art results with less time consumption.
Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution
PDF ↗Image super-resolution is a fundamentally ill-posed problem because multiple valid high-resolution images exist for one low-resolution image. Super-resolution methods based on diffusion probabilistic models can deal with the ill-posed nature by learning the distribution of high-resolution images conditioned on low-resolution images, avoiding the problem of blurry images in PSNR-oriented methods. However, existing diffusion-based super-resolution methods have high time consumption with the use of iterative sampling, while the quality and consistency of generated images are less than ideal due to problems like color shifting. In this paper, we propose Efficient Conditional Diffusion Model with Probability Flow Sampling (ECDP) for image super-resolution. To reduce the time consumption, we design a continuous-time conditional diffusion model for image super-resolution, which enables the use of probability flow sampling for efficient generation. Additionally, to improve the consistency of generated images, we propose a hybrid parametrization for the denoiser network, which interpolates between the data-predicting parametrization and the noise-predicting parametrization for different noise scales. Moreover, we design an image quality loss as a complement to the score matching loss of diffusion models, further improving the consistency and quality of super-resolution. Extensive experiments on DIV2K, ImageNet, and CelebA demonstrate that our method achieves higher super-resolution quality than existing diffusion-based image super-resolution methods while having lower time consumption. Our code is available at https://github.com/Yuan-Yutao/ECDP.
The popularity of Machine Learning as a Service (MLaaS) has led to increased concerns about Model Stealing Attacks (MSA), which aim to craft a clone model by querying MLaaS. Currently, most research on MSA assumes that MLaaS can provide soft labels and that the attacker has a proxy dataset with a similar distribution. However, this fails to encapsulate the more practical scenario where only hard labels are returned by MLaaS and the data distribution remains elusive. Furthermore, most existing work focuses solely on stealing the model accuracy, neglecting the model robustness, while robustness is essential in security-sensitive scenarios, e.g, face-scan payment. Notably, improving model robustness often necessitates the use of expensive techniques such as adversarial training, thereby further making stealing robustness a more lucrative prospect. In response to these identified gaps, we introduce a novel Data-Free Hard-Label Robustness Stealing (DFHL-RS) attack in this paper, which enables the stealing of both model accuracy and robustness by simply querying hard labels of the target model without the help of any natural data. Comprehensive experiments demonstrate the effectiveness of our method. The clone model achieves a clean accuracy of 77.86% and a robust accuracy of 39.51% against AutoAttack, which are only 4.71% and 8.40% lower than the target model on the CIFAR-10 dataset, significantly exceeding the baselines. Our code is available at: https://github.com/LetheSec/DFHL-RS-Attack.
As an essential computer vision task, Continual Semantic Segmentation (CSS) has received a lot of attention. However, security issues regarding this task have not been fully studied. To bridge this gap, we study the problem of attacks in CSS in this paper. We first propose a new task, namely, attacks on incremental samples in CSS, and reveal that the attacks on incremental samples corrupt the performance of CSS in both old and new classes. Moreover, we present an adversarial sample generation method based on class shift, namely Class Shift Attack (CS-Attack), which is an offline and easy-to-implement approach for CSS. CS-Attack is able to significantly degrade the performance of models on both old and new classes without knowledge of the incremental learning approach, which undermines the original purpose of the incremental learning, i.e., learning new classes while retaining old knowledge. Experiments show that on the popular datasets Pascal VOC, ADE20k, and Cityscapes, our approach easily degrades the performance of currently popular CSS methods, which reveals the importance of security in CSS.
Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression
PDF ↗Uncertainty quantification is critical for deploying deep neural networks (DNNs) in real-world applications. An Auxiliary Uncertainty Estimator (AuxUE) is one of the most effective means to estimate the uncertainty of the main task prediction without modifying the main task model. To be considered robust, an AuxUE must be capable of maintaining its performance and triggering higher uncertainties while encountering Out-of-Distribution (OOD) inputs, i.e., to provide robust aleatoric and epistemic uncertainty. However, for vision regression tasks, current AuxUE designs are mainly adopted for aleatoric uncertainty estimates, and AuxUE robustness has not been explored. In this work, we propose a generalized AuxUE scheme for more robust uncertainty quantification on regression tasks. Concretely, to achieve a more robust aleatoric uncertainty estimation, different distribution assumptions are considered for heteroscedastic noise, and Laplace distribution is finally chosen to approximate the prediction error. For epistemic uncertainty, we propose a novel solution named Discretization-Induced Dirichlet pOsterior (DIDO), which models the Dirichlet posterior on the discretized prediction error. Extensive experiments on age estimation, monocular depth estimation, and super-resolution tasks show that our proposed method can provide robust uncertainty estimates in the face of noisy inputs and that it can be scalable to both image-level and pixel-wise tasks.
Point scene understanding is a challenging task to process real-world scene point cloud, which aims at segmenting each object, estimating its pose, and reconstructing its mesh simultaneously. Recent state-of-the-art method first segments each object and then processes them independently with multiple stages for the different sub-tasks. This leads to a complex pipeline to optimize and makes it hard to leverage the relationship constraints between multiple objects. In this work, we propose a novel Disentangled Object-Centric TRansformer (DOCTR) that explores object-centric representation to facilitate learning with multiple objects for the multiple sub-tasks in a unified manner. Each object is represented as a query, and a Transformer decoder is adapted to iteratively optimize all the queries involving their relationship. In particular, we introduce a semantic-geometry disentangled query (SGDQ) design that enables the query features to attend separately to semantic information and geometric information relevant to the corresponding sub-tasks. A hybrid bipartite matching module is employed to well use the supervisions from all the sub-tasks during training. Qualitative and quantitative experimental results demonstrate that our method achieves state-of-the-art performance on the challenging ScanNet dataset. Code is available at https://github.com/SAITPublic/DOCTR.
This paper aims to design monocular depth estimation models with better generalization abilities. To this end, we have conducted quantitative analysis and discovered two important insights. First, the Simulation Correlation phenomenon, commonly seen in long-tailed classification problems, also exists in monocular depth estimation, indicating that the imbalanced depth distribution in training data may be the cause of limited generalization ability. Second, the imbalanced and long-tail distribution of depth values extends beyond the dataset scale, and also manifests within each individual image, further exacerbating the challenge of monocular depth estimation. Motivated by the above findings, we propose the Distance-aware Multi-Expert (DME) depth estimation model. Unlike prior methods that handle different depth range indiscriminately, DME adopts a divide-and-conquer philosophy where each expert is responsible for depth estimation of regions within a specific depth range. As such, the depth distribution seen by each expert is more uniform and can be more easily predicted. A pixel-level routing module is further designed and learned to stitch the prediction of all experts into the final depth map. Experiments show that DME achieves state-of-the-art performance on both NYU-Depth v2 and KITTI, and also delivers favorable zero-shot generalization capability on unseen datasets.
Although there has been significant progress in category-level object pose estimation in recent years, there is still considerable room for improvement. In this paper, we propose a novel transformer-based category-level 6D pose estimation method called CatFormer to enhance the accuracy pose estimation. CatFormer comprises three main parts: a coarse deformation part, a fine deformation part, and a recurrent refinement part. In the coarse and fine deformation sections, we introduce a transformer-based deformation module that performs point cloud deformation and completion in the feature space. Additionally, after each deformation, we incorporate a transformer-based graph module to adjust fused features and establish geometric and topological relationships between points based on these features. Furthermore, we present an end-to-end recurrent refinement module that enables the prior point cloud to deform multiple times according to real scene features. We evaluate CatFormer's performance by training and testing it on CAMERA25 and REAL275 datasets. Experimental results demonstrate that CatFormer surpasses state-of-the-art methods. Moreover, we extend the usage of CatFormer to instance-level object pose estimation on the LINEMOD dataset, as well as object pose estimation in real-world scenarios. The experimental results validate the effectiveness and generalization capabilities of CatFormer. Our code and the supplemental materials are avaliable at https://github.com/BIT-robot-group/CatFormer.
Recent advances in zero-shot text-to-3D human generation, which employ the human model prior (e.g., SMPL) or Score Distillation Sampling (SDS) with pre-trained text-to-image diffusion models, have been groundbreaking. However, SDS may provide inaccurate gradient directions under the weak diffusion guidance, as it tends to produce over-smoothed results and generate body textures that are inconsistent with the detailed mesh geometry. Therefore, directly leveraging existing strategies for high-fidelity text-to-3D human texturing is challenging. In this work, we propose a model called PaintHuman to addresses the challenges from two perspectives. We first propose a novel score function, Denoised Score Distillation (DSD), which directly modifies the SDS by introducing negative gradient components to iteratively correct the gradient direction and generate high-quality textures. In addition, we use the depth map as a geometric guide to ensure that the texture is semantically aligned to human mesh surfaces. To guarantee the quality of rendered results, we employ geometry-aware networks to predict surface materials and render realistic human textures. Extensive experiments, benchmarked against state-of-the-art (SoTA) methods, validate the efficacy of our approach.Project page: https://painthuman.github.io/.
Step Vulnerability Guided Mean Fluctuation Adversarial Attack against Conditional Diffusion Models
PDF ↗The high-quality generation results of conditional diffusion models have brought about concerns regarding privacy and copyright issues. As a possible technique for preventing the abuse of diffusion models, the adversarial attack against diffusion models has attracted academic attention recently. In this work, utilizing the phenomenon that diffusion models are highly sensitive to the mean value of the input noise, we propose the Mean Fluctuation Attack (MFA) to introduce mean fluctuations by shifting the mean values of the estimated noises during the reverse process. In addition, we reveal that the vulnerability of different reverse steps against adversarial attacks actually varies significantly. By modeling the step vulnerability and using it as guidance to sample the target steps for generating adversarial examples, the effectiveness of adversarial attacks can be substantially enhanced. Extensive experiments show that our algorithm can steadily cause the mean shift of the predicted noises so as to disrupt the entire reverse generation process and degrade the generation results significantly. We also demonstrate that the step vulnerability is intrinsic to the reverse process by verifying its effectiveness in an attack method other than MFA. Code and Supplementary is available at https://github.com/yuhongwei22/MFA
Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of spatial invariance in the data-forwarding process. In this study, we present a novel approach, termed Spatial Transform Decoupling (STD), providing a simple-yet-effective solution for oriented object detection with ViTs. Built upon stacked ViT blocks, STD utilizes separate network branches to predict the position, size, and angle of bounding boxes, effectively harnessing the spatial transform potential of ViTs in a divide-and-conquer fashion. Moreover, by aggregating cascaded activation masks (CAMs) computed upon the regressed parameters, STD gradually enhances features within regions of interest (RoIs), which complements the self-attention mechanism. Without bells and whistles, STD achieves state-of-the-art performance on the benchmark datasets including DOTA-v1.0 (82.24% mAP) and HRSC2016 (98.55% mAP), which demonstrates the effectiveness of the proposed method. Source code is available at https://github.com/yuhongtian17/Spatial-Transform-Decoupling.
MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding
PDF ↗In perception, multiple sensory information is integrated to map visual information from 2D views onto 3D objects, which is beneficial for understanding in 3D environments. But in terms of a single 2D view rendered from different angles, only limited partial information can be provided. The richness and value of Multi-view 2D information can provide superior self-supervised signals for 3D objects. In this paper, we propose a novel self-supervised point cloud representation learning method, MM-Point, which is driven by intra-modal and inter-modal similarity objectives. The core of MM-Point lies in the Multi-modal interaction and transmission between 3D objects and multiple 2D views at the same time. In order to more effectively simultaneously perform the consistent cross-modal objective of 2D multi-view information based on contrastive learning, we further propose Multi-MLP and Multi-level Augmentation strategies. Through carefully designed transformation strategies, we further learn Multi-level invariance in 2D Multi-views. MM-Point demonstrates state-of-the-art (SOTA) performance in various downstream tasks. For instance, it achieves a peak accuracy of 92.4% on the synthetic dataset ModelNet40, and a top accuracy of 87.8% on the real-world dataset ScanObjectNN, comparable to fully supervised methods. Additionally, we demonstrate its effectiveness in tasks such as few-shot classification, 3D part segmentation and 3D semantic segmentation.
Large-scale language-image pre-trained models (e.g., CLIP) have shown superior performances on many cross-modal retrieval tasks. However, the problem of transferring the knowledge learned from such models to video-based person re-identification (ReID) has barely been explored. In addition, there is a lack of decent text descriptions in current ReID benchmarks. To address these issues, in this work, we propose a novel one-stage text-free CLIP-based learning framework named TF-CLIP for video-based person ReID. More specifically, we extract the identity-specific sequence feature as the CLIP-Memory to replace the text feature. Meanwhile, we design a Sequence-Specific Prompt (SSP) module to update the CLIP-Memory online. To capture temporal information, we further propose a Temporal Memory Diffusion (TMD) module, which consists of two key components: Temporal Memory Construction (TMC) and Memory Diffusion (MD). Technically, TMC allows the frame-level memories in a sequence to communicate with each other, and to extract temporal information based on the relations within the sequence. MD further diffuses the temporal memories to each token in the original features to obtain more robust sequence features. Extensive experiments demonstrate that our proposed method shows much better results than other state-of-the-art methods on MARS, LS-VID and iLIDS-VID.
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models
PDF ↗Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the “pre-training & finetuning” learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this paper, we delve into a new problem: using a pre-trained multimodal source model to create adversarial image-text pairs and then transferring them to attack the target VQA models. Correspondingly, we propose a novel VQATTACK model, which can iteratively generate both im- age and text perturbations with the designed modules: the large language model (LLM)-enhanced image attack and the cross-modal joint attack module. At each iteration, the LLM-enhanced image attack module first optimizes the latent representation-based loss to generate feature-level image perturbations. Then it incorporates an LLM to further enhance the image perturbations by optimizing the designed masked answer anti-recovery loss. The cross-modal joint attack module will be triggered at a specific iteration, which updates the image and text perturbations sequentially. Notably, the text perturbation updates are based on both the learned gradients in the word embedding space and word synonym-based substitution. Experimental results on two VQA datasets with five validated models demonstrate the effectiveness of the proposed VQATTACK in the transferable attack setting, compared with state-of-the-art baselines. This work reveals a significant blind spot in the “pre-training & fine-tuning” paradigm on VQA tasks. The source code can be found in the link https://github.com/ericyinyzy/VQAttack.
In this paper, we focus on the open-set panoptic segmentation (OPS) task to circumvent the data explosion problem. Different from the close-set setting, OPS targets to detect both known and unknown categories, where the latter is not annotated during training. Different from existing work that only selects a few common categories as unknown ones, we move forward to the real-world scenario by considering the various tail categories (~1k). To this end, we first build a new dataset with long-tail distribution for the OPS task. Based on this dataset, we additionally add a new class type for unknown classes and re-define the training annotations to make the OPS definition more complete and reasonable. Moreover, we analyze the influence of several significant factors in the OPS task and explore the upper bound of performance on unknown classes with different settings. Furthermore, based on the analyses, we design an effective two-phase framework for the OPS task, including thing-agnostic map generation and unknown segment mining. We further adopt semi-supervised learning to improve the OPS performance. Experimental results on different datasets validate the effectiveness of our method.
Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we propose Point Deformable Network (PDNet), a concise MLP-based network that can capture long-range relations with strong representation ability. Specifically, we put forward Point Deformable Aggregation Module (PDAM) to improve representation capability in both long-range dependency and adaptive aggregation among points. For each query point, PDAM aggregates information from deformable reference points rather than points in limited local areas. The deformable reference points are generated data-dependent, and we initialize them according to the input point positions. Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest. We also suggest estimating the normal vector for point clouds and applying Enhanced Normal Embedding (ENE) to the geometric extractors to improve the representation ability of single-point. Extensive experiments and ablation studies on various benchmarks demonstrate the effectiveness and superiority of our PDNet.
Gaze estimation methods often experience significant performance degradation when evaluated across different domains, due to the domain gap between the testing and training data. Existing methods try to address this issue using various domain generalization approaches, but with little success because of the limited diversity of gaze datasets, such as appearance, wearable, and image quality. To overcome these limitations, we propose a novel framework called CLIP-Gaze that utilizes a pre-trained vision-language model to leverage its transferable knowledge. Our framework is the first to leverage the vision-and-language cross-modality approach for gaze estimation task. Specifically, we extract gaze-relevant feature by pushing it away from gaze-irrelevant features which can be flexibly constructed via language descriptions. To learn more suitable prompts, we propose a personalized context optimization method for text prompt tuning. Furthermore, we utilize the relationship among gaze samples to refine the distribution of gaze-relevant features, thereby improving the generalization capability of the gaze estimation model. Extensive experiments demonstrate the excellent performance of CLIP-Gaze over existing methods on four cross-domain evaluations.
Efficient Look-Up Table from Expanded Convolutional Network for Accelerating Image Super-resolution
PDF ↗The look-up table (LUT) has recently shown its practicability and effectiveness in super-resolution (SR) tasks due to its low computational cost and hardware independence. However, most existing methods focus on improving the performance of SR, neglecting the demand for high-speed SR on low-computational edge devices. In this paper, we propose an efficient expanded convolution (EC) layer, which expands the output size of regular convolution to enlarge the receptive field (RF) indirectly. It can increase the size of the LUT corresponding to the network linearly with the increase of RF. Additionally, after introducing the EC, multiple LUTs are merged into one LUT, achieving faster running speed while maintaining SR performance. More specifically, we expand the coverage of the convolutional output so that the output at the current position covers the target position and its surroundings, forming an overlapping sliding window at the output end. We sum up the overlapping parts of the sliding window as the output, thereby achieving the effect of enlarging the RF size. Moreover, by expanding the numerical range of the accumulated results and rescaling them to [0,255], the method can mitigate the error caused by quantization output. Experiments indicate that the proposed method performs better than the baseline method and is faster than other LUT-based SR methods.