Depth images and thermal images contain the spatial geometry information and surface temperature information, which can act as complementary information for the RGB modality. However, the quality of the depth and thermal images is often unreliable in some challenging scenarios, which will result in the performance degradation of the two-modal based salient object detection (SOD). Meanwhile, some researchers pay attention to the triple-modal SOD task, where they attempt to explore the complementarity of the RGB image, the depth image, and the thermal image. However, existing triple-modal SOD methods fail to perceive the quality of depth maps and thermal images, which leads to performance degradation when dealing with scenes with low-quality depth and thermal images. Therefore, we propose a quality-aware selective fusion network (QSF-Net) to conduct VDT salient object detection, which contains three subnets including the initial feature extraction subnet, the quality-aware region selection subnet, and the region-guided selective fusion subnet. Firstly, except for extracting features, the initial feature extraction subnet can generate a preliminary prediction map from each modality via a shrinkage pyramid architecture. Then, we design the weakly-supervised quality-aware region selection subnet to generate the quality-aware maps. Concretely, we first find the high-quality and low-quality regions by using the preliminary predictions, which further constitute the pseudo label that can be used to train this subnet. Finally, the region-guided selective fusion subnet purifies the initial features under the guidance of the quality-aware maps, and then fuses the triple-modal features and refines the edge details of prediction maps through the intra-modality and inter-modality attention (IIA) module and the edge refinement (ER) module, respectively. Extensive experiments are performed on VDT-2048
Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made within an image. Additionally, we propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification, object detection, instance segmentation, and semantic segmentation tasks. Our smallest model, GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with less GMACs and a similar number of parameters. Our largest model, GreedyViG-B obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6% decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3% decrease in GMACs. Our work shows that hybrid CNN-GNN architectures not only provide a new avenue for designing efficient models, but that they can also exceed the performance of current state-of-the-art models.
Mamba, an architecture with RNN-like token mixer of state space model (SSM), was recently introduced to address the quadratic complexity of the attention mechanism and subsequently applied to vision tasks. Nevertheless, the performance of Mamba for vision is often underwhelming when compared with convolutional and attention-based models. In this paper, we delve into the essence of Mamba, and conceptually conclude that Mamba is ideally suited for tasks with long-sequence and autoregressive characteristics. For vision tasks, as image classification does not align with either characteristic, we hypothesize that Mamba is not necessary for this task; Detection and segmentation tasks are also not autoregressive, yet they adhere to the long-sequence characteristic, so we believe it is still worthwhile to explore Mamba's potential for these tasks. To empirically verify our hypotheses, we construct a series of models named MambaOut through stacking Mamba blocks while removing their core token mixer, SSM. Experimental results strongly support our hypotheses. Specifically, our MambaOut model surpasses all visual Mamba models on ImageNet image classification, indicating that Mamba is indeed unnecessary for this task. As for detection and segmentation, MambaOut cannot match the performance of state-of-the-art visual Mamba models, demonstrating the potential of Mamba for long-sequence visual tasks. The code is available at https://github.com/yuweihao/MambaOut
Over the past few years, as large language models have ushered in an era of intelligence emergence, there has been an intensified focus on scaling networks. Currently, many network architectures are designed manually, often resulting in sub-optimal configurations. Although Neural Architecture Search (NAS) methods have been proposed to automate this process, they suffer from low search efficiency. This study introduces Differentiable Model Scaling (DMS), increasing the efficiency for searching optimal width and depth in networks. DMS can model both width and depth in a direct and fully differentiable way, making it easy to optimize. We have evaluated our DMS across diverse tasks, ranging from vision tasks to NLP tasks and various network architectures, including CNNs and Transformers. Results consistently indicate that our DMS can find improved structures and outperforms state-of-the-art NAS methods. Specifically, for image classification on ImageNet, our DMS improves the top-1 accuracy of EfficientNet-B0 and Deit-Tiny by 1.4% and 0.6%, respectively, and outperforms the state-of-the-art zero-shot NAS method, ZiCo, by 1.3% while requiring only 0.4 GPU days for searching. For object detection on COCO, DMS improves the mAP of Yolo-v8-n by 2.0%. For language modeling, our pruned Llama-7B outperforms the prior method with lower perplexity and higher zero-shot classification accuracy. We will release our code in the future.
This work examines the reproducibility and benchmarking of state-of-the-art real-time object detection models. As object detection models are often used in real-world contexts, such as robotics, where inference time is paramount, simply measuring models' accuracy is not enough to compare them. We thus compare a large variety of object detection models' accuracy and inference speed on multiple graphics cards. In addition to this large benchmarking attempt, we also reproduce the following models from scratch using PyTorch on the MS COCO 2017 dataset: DETR, RTMDet, ViTDet and YOLOv7. More importantly, we propose a unified training and evaluation pipeline, based on MMDetection's features, to better compare models. Our implementation of DETR and ViTDet could not achieve accuracy or speed performances comparable to what is declared in the original papers. On the other hand, reproduced RTMDet and YOLOv7 could match such performances. Studied papers are also found to be generally lacking for reproducibility purposes. As for MMDetection pretrained models, speed performances are severely reduced with limited computing resources (larger, more accurate models even more so). Moreover, results exhibit a strong trade-off between accuracy and speed, prevailed by anchor-free models - notably RTMDet or YOLOx models. The code used is this paper and all the experiments is available in the repository at https://github.com/Don767/segdet_mlcr2024.
3D occupancy, an advanced perception technology for driving scenarios, represents the entire scene without distinguishing between foreground and background by quantifying the physical space into a grid map. The widely adopted projection-first deformable attention, efficient in transforming image features into 3D representations, encounters challenges in aggregating multi-view features due to sensor deployment constraints. To address this issue, we propose our learning-first view attention mechanism for effective multi-view feature aggregation. Moreover, we showcase the scalability of our view attention across diverse multi-view 3D tasks, including map construction and 3D object detection. Leveraging the proposed view attention as well as an additional multi-frame streaming temporal attention, we introduce ViewFormer, a vision-centric transformer-based framework for spatiotemporal feature aggregation. To further explore occupancy-level flow representation, we present FlowOcc3D, a benchmark built on top of existing high-quality datasets. Qualitative and quantitative analyses on this benchmark reveal the potential to represent fine-grained dynamic scenes. Extensive experiments show that our approach significantly outperforms prior state-of-the-art methods. The codes are available at \url{https://github.com/ViewFormerOcc/ViewFormer-Occ}.
Toward desirable saliency prediction, the types and numbers of inputs for a salient object detection (SOD) algorithm may dynamically change in many real-life applications. However, existing SOD algorithms are mainly designed or trained for one particular type of inputs, failing to be generalized to other types of inputs. Consequentially, more types of SOD algorithms need to be prepared in advance for handling different types of inputs, raising huge hardware and research costs. Differently, in this paper, we propose a new type of SOD task, termed Arbitrary Modality SOD (AM SOD). The most prominent characteristics of AM SOD are that the modality types and modality numbers will be arbitrary or dynamically changed. The former means that the inputs to the AM SOD algorithm may be arbitrary modalities such as RGB, depths, or even any combination of them. While, the latter indicates that the inputs may have arbitrary modality numbers as the input type is changed, e.g. single-modality RGB image, dual-modality RGB-Depth (RGB-D) images or triple-modality RGB-Depth-Thermal (RGB-D-T) images. Accordingly, a preliminary solution to the above challenges, \i.e. a modality switch network (MSN), is proposed in this paper. In particular, a modality switch feature extractor (MSFE) is first designed to extract discriminative features from each modality effectively by introducing some modality indicators, which will generate some weights for modality switching. Subsequently, a dynamic fusion module (DFM) is proposed to adaptively fuse features from a variable number of modalities based on a novel Transformer structure. Finally, a new dataset, named AM-XD, is constructed to facilitate research on AM SOD. Extensive experiments demonstrate that our AM SOD method can effectively cope with changes in the type and number of input modalities for robust salient object detection.
Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its practical deployment. In this paper, we propose a post-training quantization (PTQ) framework for Segment Anything Model, namely PTQ4SAM. First, we investigate the inherent bottleneck of SAM quantization attributed to the bimodal distribution in post-Key-Linear activations. We analyze its characteristics from both per-tensor and per-channel perspectives, and propose a Bimodal Integration strategy, which utilizes a mathematically equivalent sign operation to transform the bimodal distribution into a relatively easy-quantized normal distribution offline. Second, SAM encompasses diverse attention mechanisms (i.e., self-attention and two-way cross-attention), resulting in substantial variations in the post-Softmax distributions. Therefore, we introduce an Adaptive Granularity Quantization for Softmax through searching the optimal power-of-two base, which is hardware-friendly. Extensive experimental results across various vision tasks (instance segmentation, semantic segmentation and object detection), datasets and model variants show the superiority of PTQ4SAM. For example, when quantizing SAM-L to 6-bit, we achieve lossless accuracy for instance segmentation, about 0.5\% drop with theoretical 3.9$\times$ acceleration. The code is available at \url{https://github.com/chengtao-lv/PTQ4SAM}.
Electric scooters (e-scooters) have rapidly emerged as a popular mode of transportation in urban areas, yet they pose significant safety challenges. In the United States, the rise of e-scooters has been marked by a concerning increase in related injuries and fatalities. Recently, while deep-learning object detection holds paramount significance in autonomous vehicles to avoid potential collisions, its application in the context of e-scooters remains relatively unexplored. This paper addresses this gap by assessing the effectiveness and efficiency of cutting-edge object detectors designed for e-scooters. To achieve this, the first comprehensive benchmark involving 22 state-of-the-art YOLO object detectors, including five versions (YOLOv3, YOLOv5, YOLOv6, YOLOv7, and YOLOv8), has been established for real-time traffic object detection using a self-collected dataset featuring e-scooters. The detection accuracy, measured in terms of [email omitted], ranges from 27.4% (YOLOv7-E6E) to 86.8% (YOLOv5s). All YOLO models, particularly YOLOv3-tiny, have displayed promising potential for real-time object detection in the context of e-scooters. Both the traffic scene dataset (https://zenodo.org/records/10578641) and software program codes (https://github.com/DongChen06/ScooterDet) for model benchmarking in this study are publicly available, which will not only improve e-scooter safety with advanced object detection but also lay the groundwork for tailored solutions, promising a safer and more sustainable urban micromobility landscape.
Object detection algorithms particularly those based on YOLO have demonstrated remarkable efficiency in balancing speed and accuracy. However, their application in brain tumour detection remains underexplored. This study proposes RepVGG-GELAN, a novel YOLO architecture enhanced with RepVGG, a reparameterized convolutional approach for object detection tasks particularly focusing on brain tumour detection within medical images. RepVGG-GELAN leverages the RepVGG architecture to improve both speed and accuracy in detecting brain tumours. Integrating RepVGG into the YOLO framework aims to achieve a balance between computational efficiency and detection performance. This study includes a spatial pyramid pooling-based Generalized Efficient Layer Aggregation Network (GELAN) architecture which further enhances the capability of RepVGG. Experimental evaluation conducted on a brain tumour dataset demonstrates the effectiveness of RepVGG-GELAN surpassing existing RCS-YOLO in terms of precision and speed. Specifically, RepVGG-GELAN achieves an increased precision of 4.91% and an increased AP50 of 2.54% over the latest existing approach while operating at 240.7 GFLOPs. The proposed RepVGG-GELAN with GELAN architecture presents promising results establishing itself as a state-of-the-art solution for accurate and efficient brain tumour detection in medical images. The implementation code is publicly available at https://github.com/ThensiB/RepVGG-GELAN.
Deep learning has made significant progress in computer vision, specifically in image classification, object detection, and semantic segmentation. The skip connection has played an essential role in the architecture of deep neural networks,enabling easier optimization through residual learning during the training stage and improving accuracy during testing. Many neural networks have inherited the idea of residual learning with skip connections for various tasks, and it has been the standard choice for designing neural networks. This survey provides a comprehensive summary and outlook on the development of skip connections in deep neural networks. The short history of skip connections is outlined, and the development of residual learning in deep neural networks is surveyed. The effectiveness of skip connections in the training and testing stages is summarized, and future directions for using skip connections in residual learning are discussed. Finally, we summarize seminal papers, source code, models, and datasets that utilize skip connections in computer vision, including image classification, object detection, semantic segmentation, and image reconstruction. We hope this survey could inspire peer researchers in the community to develop further skip connections in various forms and tasks and the theory of residual learning in deep neural networks. The project page can be found at https://github.com/apple1986/Residual_Learning_For_Images
We introduce an innovative, simple, effective segmentation-free approach for outcome prediction in head \& neck cancer (HNC) patients. By harnessing deep learning-based feature extraction techniques and multi-angle maximum intensity projections (MA-MIPs) applied to Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) volumes, our proposed method eliminates the need for manual segmentations of regions-of-interest (ROIs) such as primary tumors and involved lymph nodes. Instead, a state-of-the-art object detection model is trained to perform automatic cropping of the head and neck region on the PET volumes. A pre-trained deep convolutional neural network backbone is then utilized to extract deep features from MA-MIPs obtained from 72 multi-angel axial rotations of the cropped PET volumes. These deep features extracted from multiple projection views of the PET volumes are then aggregated and fused, and employed to perform recurrence-free survival analysis on a cohort of 489 HNC patients. The proposed approach outperforms the best performing method on the target dataset for the task of recurrence-free survival analysis. By circumventing the manual delineation of the malignancies on the FDG PET-CT images, our approach eliminates the dependency on subjective interpretations and highly enhances the reproducibility of the proposed survival analysis method.
As human-machine interaction continues to evolve, the capacity for environmental perception is becoming increasingly crucial. Integrating the two most common types of sensory data, images, and point clouds, can enhance detection accuracy. Currently, there is no existing model capable of detecting an object's position in both point clouds and images while also determining their corresponding relationship. This information is invaluable for human-machine interactions, offering new possibilities for their enhancement. In light of this, this paper introduces an end-to-end Consistency Object Detection (COD) algorithm framework that requires only a single forward inference to simultaneously obtain an object's position in both point clouds and images and establish their correlation. Furthermore, to assess the accuracy of the object correlation between point clouds and images, this paper proposes a new evaluation metric, Consistency Precision (CP). To verify the effectiveness of the proposed framework, an extensive set of experiments has been conducted on the KITTI and DAIR-V2X datasets. The study also explored how the proposed consistency detection method performs on images when the calibration parameters between images and point clouds are disturbed, compared to existing post-processing methods. The experimental results demonstrate that the proposed method exhibits excellent detection performance and robustness, achieving end-to-end consistency detection. The source code will be made publicly available at https://github.com/xifen523/COD.
In the pursuit of refining precise perception models for fully autonomous driving, continual online model training becomes essential. Federated Learning (FL) within vehicular networks offers an efficient mechanism for model training while preserving raw sensory data integrity. Yet, FL struggles with non-identically distributed data (e.g., quantity skew), leading to suboptimal convergence rates during model training. In previous work, we introduced FedLA, an innovative Label-Aware aggregation method addressing data heterogeneity in FL for generic scenarios. In this paper, we introduce FedProx+LA, a novel FL method building upon the state-of-the-art FedProx and FedLA to tackle data heterogeneity, which is specifically tailored for vehicular networks. We evaluate the efficacy of FedProx+LA in continuous online object detection model training. Through a comparative analysis against conventional and state-of-the-art methods, our findings reveal the superior convergence rate of FedProx+LA. Notably, if the label distribution is very heterogeneous, our FedProx+LA approach shows substantial improvements in detection performance compared to baseline methods, also outperforming our previous FedLA approach. Moreover, both FedLA and FedProx+LA increase convergence speed by 30% compared to baseline methods.
Instance perception tasks (object detection, instance segmentation, pose estimation, counting) play a key role in industrial applications of visual models. As supervised learning methods suffer from high labeling cost, few-shot learning methods which effectively learn from a limited number of labeled examples are desired. Existing few-shot learning methods primarily focus on a restricted set of tasks, presumably due to the challenges involved in designing a generic model capable of representing diverse tasks in a unified manner. In this paper, we propose UniFS, a universal few-shot instance perception model that unifies a wide range of instance perception tasks by reformulating them into a dynamic point representation learning framework. Additionally, we propose Structure-Aware Point Learning (SAPL) to exploit the higher-order structural relationship among points to further enhance representation learning. Our approach makes minimal assumptions about the tasks, yet it achieves competitive results compared to highly specialized and well optimized specialist models. Codes and data are available at https://github.com/jin-s13/UniFS.
Unsupervised object discovery is becoming an essential line of research for tackling recognition problems that require decomposing an image into entities, such as semantic segmentation and object detection. Recently, object-centric methods that leverage self-supervision have gained popularity, due to their simplicity and adaptability to different settings and conditions. However, those methods do not exploit effective techniques already employed in modern self-supervised approaches. In this work, we consider an object-centric approach in which DINO ViT features are reconstructed via a set of queried representations called slots. Based on that, we propose a masking scheme on input features that selectively disregards the background regions, inducing our model to focus more on salient objects during the reconstruction phase. Moreover, we extend the slot attention to a multi-query approach, allowing the model to learn multiple sets of slots, producing more stable masks. During training, these multiple sets of slots are learned independently while, at test time, these sets are merged through Hungarian matching to obtain the final slots. Our experimental results and ablations on the PASCAL-VOC 2012 dataset show the importance of each component and highlight how their combination consistently improves object localization. Our source code is available at: https://github.com/rishavpramanik/maskedmultiqueryslot
Semi-supervised 3D object detection can benefit from the promising pseudo-labeling technique when labeled data is limited. However, recent approaches have overlooked the impact of noisy pseudo-labels during training, despite efforts to enhance pseudo-label quality through confidence-based filtering. In this paper, we examine the impact of noisy pseudo-labels on IoU-based target assignment and propose the Reliable Student framework, which incorporates two complementary approaches to mitigate errors. First, it involves a class-aware target assignment strategy that reduces false negative assignments in difficult classes. Second, it includes a reliability weighting strategy that suppresses false positive assignment errors while also addressing remaining false negatives from the first step. The reliability weights are determined by querying the teacher network for confidence scores of the student-generated proposals. Our work surpasses the previous state-of-the-art on KITTI 3D object detection benchmark on point clouds in the semi-supervised setting. On 1% labeled data, our approach achieves a 6.2% AP improvement for the pedestrian class, despite having only 37 labeled samples available. The improvements become significant for the 2% setting, achieving 6.0% AP and 5.7% AP improvements for the pedestrian and cyclist classes, respectively.
In real-world scenarios, using multiple modalities like visible (RGB) and infrared (IR) can greatly improve the performance of a predictive task such as object detection (OD). Multimodal learning is a common way to leverage these modalities, where multiple modality-specific encoders and a fusion module are used to improve performance. In this paper, we tackle a different way to employ RGB and IR modalities, where only one modality or the other is observed by a single shared vision encoder. This realistic setting requires a lower memory footprint and is more suitable for applications such as autonomous driving and surveillance, which commonly rely on RGB and IR data. However, when learning a single encoder on multiple modalities, one modality can dominate the other, producing uneven recognition results. This work investigates how to efficiently leverage RGB and IR modalities to train a common transformer-based OD vision encoder, while countering the effects of modality imbalance. For this, we introduce a novel training technique to Mix Patches (MiPa) from the two modalities, in conjunction with a patch-wise modality agnostic module, for learning a common representation of both modalities. Our experiments show that MiPa can learn a representation to reach competitive results on traditional RGB/IR benchmarks while only requiring a single modality during inference. Our code is available at: https://github.com/heitorrapela/MiPa.
Collective Perception has attracted significant attention in recent years due to its advantage for mitigating occlusion and expanding the field-of-view, thereby enhancing reliability, efficiency, and, most crucially, decision-making safety. However, developing collective perception models is highly resource demanding due to extensive requirements of processing input data for many agents, usually dozens of images and point clouds for a single frame. This not only slows down the model development process for collective perception but also impedes the utilization of larger models. In this paper, we propose an agent-based training framework that handles the deep learning modules and agent data separately to have a cleaner data flow structure. This framework not only provides an API for flexibly prototyping the data processing pipeline and defining the gradient calculation for each agent, but also provides the user interface for interactive training, testing and data visualization. Training experiment results of four collective object detection models on the prominent collective perception benchmark OPV2V show that the agent-based training can significantly reduce the GPU memory consumption and training time while retaining inference performance. The framework and model implementations are available at \url{https://github.com/YuanYunshuang/CoSense3D}
Monocular 3D object detection poses a significant challenge in 3D scene understanding due to its inherently ill-posed nature in monocular depth estimation. Existing methods heavily rely on supervised learning using abundant 3D labels, typically obtained through expensive and labor-intensive annotation on LiDAR point clouds. To tackle this problem, we propose a novel weakly supervised 3D object detection framework named VSRD (Volumetric Silhouette Rendering for Detection) to train 3D object detectors without any 3D supervision but only weak 2D supervision. VSRD consists of multi-view 3D auto-labeling and subsequent training of monocular 3D object detectors using the pseudo labels generated in the auto-labeling stage. In the auto-labeling stage, we represent the surface of each instance as a signed distance field (SDF) and render its silhouette as an instance mask through our proposed instance-aware volumetric silhouette rendering. To directly optimize the 3D bounding boxes through rendering, we decompose the SDF of each instance into the SDF of a cuboid and the residual distance field (RDF) that represents the residual from the cuboid. This mechanism enables us to optimize the 3D bounding boxes in an end-to-end manner by comparing the rendered instance masks with the ground truth instance masks. The optimized 3D bounding boxes serve as effective training data for 3D object detection. We conduct extensive experiments on the KITTI-360 dataset, demonstrating that our method outperforms the existing weakly supervised 3D object detection methods. The code is available at https://github.com/skmhrk1209/VSRD.