In the technical report, we present a novel transformer-based framework for nuScenes lidar-based object detection task, termed Spatial Expansion Group Transformer (SEGT). To efficiently handle the irregular and sparse nature of point cloud, we propose migrating the voxels into distinct specialized ordered fields with the general spatial expansion strategies, and employ group attention mechanisms to extract the exclusive feature maps within each field. Subsequently, we integrate the feature representations across different ordered fields by alternately applying diverse expansion strategies, thereby enhancing the model's ability to capture comprehensive spatial information. The method was evaluated on the nuScenes lidar-based object detection test dataset, achieving an NDS score of 73.9 without Test-Time Augmentation (TTA) and 74.5 with TTA, demonstrating the effectiveness of the proposed method. Notably, our method ranks the 1st place in the nuScenes lidar-based object detection task.
In current multimodal tasks, models typically freeze the encoder and decoder while adapting intermediate layers to task-specific goals, such as region captioning. Region-level visual understanding presents significant challenges for large-scale vision-language models. While limited spatial awareness is a known issue, coarse-grained pretraining, in particular, exacerbates the difficulty of optimizing latent representations for effective encoder-decoder alignment. We propose AlignCap, a framework designed to enhance region-level understanding through fine-grained alignment of latent spaces. Our approach introduces a novel latent feature refinement module that enhances conditioned latent space representations to improve region-level captioning performance. We also propose an innovative alignment strategy, the semantic space alignment module, which boosts the quality of multimodal representations. Additionally, we incorporate contrastive learning in a novel manner within both modules to further enhance region-level captioning performance. To address spatial limitations, we employ a General Object Detection (GOD) method as a data preprocessing pipeline that enhances spatial reasoning at the regional level. Extensive experiments demonstrate that our approach significantly improves region-level captioning performance across various tasks
Recent research on universal object detection aims to introduce language in a SoTA closed-set detector and then generalize the open-set concepts by constructing large-scale (text-region) datasets for training. However, these methods face two main challenges: (i) how to efficiently use the prior information in the prompts to genericise objects and (ii) how to reduce alignment bias in the downstream tasks, both leading to sub-optimal performance in some scenarios beyond pre-training. To address these challenges, we propose a strong universal detection foundation model called CP-DETR, which is competitive in almost all scenarios, with only one pre-training weight. Specifically, we design an efficient prompt visual hybrid encoder that enhances the information interaction between prompt and visual through scale-by-scale and multi-scale fusion modules. Then, the hybrid encoder is facilitated to fully utilize the prompted information by prompt multi-label loss and auxiliary detection head. In addition to text prompts, we have designed two practical concept prompt generation methods, visual prompt and optimized prompt, to extract abstract concepts through concrete visual examples and stably reduce alignment bias in downstream tasks. With these effective designs, CP-DETR demonstrates superior universal detection performance in a broad spectrum of scenarios. For example, our Swin-T backbone model achieves 47.6 zero-shot AP on LVIS, and the Swin-L backbone model achieves 32.2 zero-shot AP on ODinW35. Furthermore, our visual prompt generation method achieves 68.4 AP on COCO val by interactive detection, and the optimized prompt achieves 73.1 fully-shot AP on ODinW13.
Remote sensing has evolved from simple image acquisition to complex systems capable of integrating and processing visual and textual data. This review examines the development and application of multi-modal language models (MLLMs) in remote sensing, focusing on their ability to interpret and describe satellite imagery using natural language. We cover the technical underpinnings of MLLMs, including dual-encoder architectures, Transformer models, self-supervised and contrastive learning, and cross-modal integration. The unique challenges of remote sensing data--varying spatial resolutions, spectral richness, and temporal changes--are analyzed for their impact on MLLM performance. Key applications such as scene description, object detection, change detection, text-to-image retrieval, image-to-text generation, and visual question answering are discussed to demonstrate their relevance in environmental monitoring, urban planning, and disaster response. We review significant datasets and resources supporting the training and evaluation of these models. Challenges related to computational demands, scalability, data quality, and domain adaptation are highlighted. We conclude by proposing future research directions and technological advancements to further enhance MLLM utility in remote sensing.
Spatial contexts, such as the backgrounds and surroundings, are considered critical in Human-Object Interaction (HOI) recognition, especially when the instance-centric foreground is blurred or occluded. Recent advancements in HOI detectors are usually built upon detection transformer pipelines. While such an object-detection-oriented paradigm shows promise in localizing objects, its exploration of spatial context is often insufficient for accurately recognizing human actions. To enhance the capabilities of object detectors for HOI detection, we present a dual-branch framework named ContextHOI, which efficiently captures both object detection features and spatial contexts. In the context branch, we train the model to extract informative spatial context without requiring additional hand-craft background labels. Furthermore, we introduce context-aware spatial and semantic supervision to the context branch to filter out irrelevant noise and capture informative contexts. ContextHOI achieves state-of-the-art performance on the HICO-DET and v-coco benchmarks. For further validation, we construct a novel benchmark, HICO-ambiguous, which is a subset of HICO-DET that contains images with occluded or impaired instance cues. Extensive experiments across all benchmarks, complemented by visualizations, underscore the enhancements provided by ContextHOI, especially in recognizing interactions involving occluded or blurred instances.
The rapid increase of space assets represented by small satellites in low Earth orbit can enable ubiquitous digital services for everyone. However, due to the dynamic space environment, numerous space objects, complex atmospheric conditions, and unexpected events can easily introduce adverse conditions affecting space safety, operations, and sustainability of the outer space environment. This challenge calls for responsive, effective satellite object detection (SOD) solutions that allow a small satellite to assess and respond to collision risks, with the consideration of constrained resources on a small satellite platform. This paper discusses the SOD tasks and onboard deep learning (DL) approach to the tasks. Two new DL models are proposed, called GELAN-ViT and GELAN-RepViT, which incorporate vision transformer (ViT) into the Generalized Efficient Layer Aggregation Network (GELAN) architecture and address limitations by separating the convolutional neural network and ViT paths. These models outperform the state-of-the-art YOLOv9-t in terms of mean average precision (mAP) and computational costs. On the SOD dataset, our proposed models can achieve around 95% mAP50 with giga-floating point operations (GFLOPs) reduced by over 5.0. On the VOC 2012 dataset, they can achieve $\geq$ 60.7% mAP50 with GFLOPs reduced by over 5.2.
Object detection using LiDAR point clouds relies on a large amount of human-annotated samples when training the underlying detectors' deep neural networks. However, generating 3D bounding box annotation for a large-scale dataset could be costly and time-consuming. Alternatively, unsupervised domain adaptation (UDA) enables a given object detector to operate on a novel new data, with unlabeled training dataset, by transferring the knowledge learned from training labeled \textit{source domain} data to the new unlabeled \textit{target domain}. Pseudo label strategies, which involve training the 3D object detector using target-domain predicted bounding boxes from a pre-trained model, are commonly used in UDA. However, these pseudo labels often introduce noise, impacting performance. In this paper, we introduce the Domain Adaptive LIdar (DALI) object detection framework to address noise at both distribution and instance levels. Firstly, a post-training size normalization (PTSN) strategy is developed to mitigate bias in pseudo label size distribution by identifying an unbiased scale after network training. To address instance-level noise between pseudo labels and corresponding point clouds, two pseudo point clouds generation (PPCG) strategies, ray-constrained and constraint-free, are developed to generate pseudo point clouds for each instance, ensuring the consistency between pseudo labels and pseudo points during training. We demonstrate the effectiveness of our method on the publicly available and popular datasets KITTI, Waymo, and nuScenes. We show that the proposed DALI framework achieves state-of-the-art results and outperforms leading approaches on most of the domain adaptation tasks. Our code is available at \href{https://github.com/xiaohulugo/T-RO2024-DALI}{https://github.com/xiaohulugo/T-RO2024-DALI}.
Infrared-visible object detection (IVOD) seeks to harness the complementary information in infrared and visible images, thereby enhancing the performance of detectors in complex environments. However, existing methods often neglect the frequency characteristics of complementary information, such as the abundant high-frequency details in visible images and the valuable low-frequency thermal information in infrared images, thus constraining detection performance. To solve this problem, we introduce a novel Frequency-Driven Feature Decomposition Network for IVOD, called FD2-Net, which effectively captures the unique frequency representations of complementary information across multimodal visual spaces. Specifically, we propose a feature decomposition encoder, wherein the high-frequency unit (HFU) utilizes discrete cosine transform to capture representative high-frequency features, while the low-frequency unit (LFU) employs dynamic receptive fields to model the multi-scale context of diverse objects. Next, we adopt a parameter-free complementary strengths strategy to enhance multimodal features through seamless inter-frequency recoupling. Furthermore, we innovatively design a multimodal reconstruction mechanism that recovers image details lost during feature extraction, further leveraging the complementary information from infrared and visible images to enhance overall representational capacity. Extensive experiments demonstrate that FD2-Net outperforms state-of-the-art (SOTA) models across various IVOD benchmarks, i.e. LLVIP (96.2% mAP), FLIR (82.9% mAP), and M3FD (83.5% mAP).
We tackle the challenging problem of Open-Set Object Detection (OSOD), which aims to detect both known and unknown objects in unlabelled images. The main difficulty arises from the absence of supervision for these unknown classes, making it challenging to distinguish them from the background. Existing OSOD detectors either fail to properly exploit or inadequately leverage the abundant unlabeled unknown objects in training data, restricting their performance. To address these limitations, we propose UADet, an Uncertainty-Aware Open-Set Object Detector that considers appearance and geometric uncertainty. By integrating these uncertainty measures, UADet effectively reduces the number of unannotated instances incorrectly utilized or omitted by previous methods. Extensive experiments on OSOD benchmarks demonstrate that UADet substantially outperforms previous state-of-the-art (SOTA) methods in detecting both known and unknown objects, achieving a 1.8x improvement in unknown recall while maintaining high performance on known classes. When extended to Open World Object Detection (OWOD), our method shows significant advantages over the current SOTA method, with average improvements of 13.8% and 6.9% in unknown recall on M-OWODB and S-OWODB benchmarks, respectively. Extensive results validate the effectiveness of our uncertainty-aware approach across different open-set scenarios.
Recently, we have witnessed the rise of novel ``event-based'' camera sensors for high-speed, low-power video capture. Rather than recording discrete image frames, these sensors output asynchronous ``event'' tuples with microsecond precision, only when the brightness change of a given pixel exceeds a certain threshold. Although these sensors have enabled compelling new computer vision applications, these applications often require expensive, power-hungry GPU systems, rendering them incompatible for deployment on the low-power devices for which event cameras are optimized. Whereas receiver-driven rate adaptation is a crucial feature of modern video streaming solutions, this topic is underexplored in the realm of event-based vision systems. On a real-world event camera dataset, we first demonstrate that a state-of-the-art object detection application is resilient to dramatic data loss, and that this loss may be weighted towards the end of each temporal window. We then propose a scalable streaming method for event-based data based on Media Over QUIC, prioritizing object detection performance and low latency. The application server can receive complementary event data across several streams simultaneously, and drop streams as needed to maintain a certain latency. With a latency target of 5 ms for end-to-end transmission across a small network, we observe an average reduction in detection mAP as low as 0.36. With a more relaxed latency target of 50 ms, we observe an average mAP reduction as low as 0.19.
Image reflection removal is crucial for restoring image quality. Distorted images can negatively impact tasks like object detection and image segmentation. In this paper, we present a novel approach for image reflection removal using a single image. Instead of focusing on model architecture, we introduce a new training technique that can be generalized to image-to-image problems, with input and output being similar in nature. This technique is embodied in our multi-step loss mechanism, which has proven effective in the reflection removal task. Additionally, we address the scarcity of reflection removal training data by synthesizing a high-quality, non-linear synthetic dataset called RefGAN using Pix2Pix GAN. This dataset significantly enhances the model's ability to learn better patterns for reflection removal. We also utilize a ranged depth map, extracted from the depth estimation of the ambient image, as an auxiliary feature, leveraging its property of lacking depth estimations for reflections. Our approach demonstrates superior performance on the SIR^2 benchmark and other real-world datasets, proving its effectiveness by outperforming other state-of-the-art models.
Autonomous driving requires robust perception models trained on high-quality, large-scale multi-view driving videos for tasks like 3D object detection, segmentation and trajectory prediction. While world models provide a cost-effective solution for generating realistic driving videos, challenges remain in ensuring these videos adhere to fundamental physical principles, such as relative and absolute motion, spatial relationship like occlusion and spatial consistency, and temporal consistency. To address these, we propose DrivePhysica, an innovative model designed to generate realistic multi-view driving videos that accurately adhere to essential physical principles through three key advancements: (1) a Coordinate System Aligner module that integrates relative and absolute motion features to enhance motion interpretation, (2) an Instance Flow Guidance module that ensures precise temporal consistency via efficient 3D flow extraction, and (3) a Box Coordinate Guidance module that improves spatial relationship understanding and accurately resolves occlusion hierarchies. Grounded in physical principles, we achieve state-of-the-art performance in driving video generation quality (3.96 FID and 38.06 FVD on the Nuscenes dataset) and downstream perception tasks. Our project homepage: https://metadrivescape.github.io/papers_project/DrivePhysica/page.html
Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities of the corresponding category between the teacher and student while lacking a mechanism for cross-category comparison. Besides, KL-Div is problematic when applied to intermediate layers, as it cannot handle non-overlapping distributions and is unaware of geometry of the underlying manifold. To address these downsides, we propose a methodology of Wasserstein Distance (WD) based knowledge distillation. Specifically, we propose a logit distillation method called WKD-L based on discrete WD, which performs cross-category comparison of probabilities and thus can explicitly leverage rich interrelations among categories. Moreover, we introduce a feature distillation method called WKD-F, which uses a parametric method for modeling feature distributions and adopts continuous WD for transferring knowledge from intermediate layers. Comprehensive evaluations on image classification and object detection have shown (1) for logit distillation WKD-L outperforms very strong KL-Div variants; (2) for feature distillation WKD-F is superior to the KL-Div counterparts and state-of-the-art competitors. The source code is available at https://peihuali.org/WKD
Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual perception models. However, developing such attacks remains challenging due to diverse real-world backgrounds and the requirement for maintaining visual naturality. Building upon this challenge, we reformulate physical adversarial attacks as a one-shot patch-generation problem. Our approach generates adversarial patches through a deep generative model that considers the specific scene context, enabling direct physical deployment in matching environments. The primary challenge lies in simultaneously achieving two objectives: generating adversarial patches that effectively mislead object detection systems while determining contextually appropriate placement within the scene. We propose MAGIC (Mastering Physical Adversarial Generation In Context), a novel framework powered by multi-modal LLM agents to address these challenges. MAGIC automatically understands scene context and orchestrates adversarial patch generation through the synergistic interaction of language and vision capabilities. MAGIC orchestrates three specialized LLM agents: The adv-patch generation agent (GAgent) masters the creation of deceptive patches through strategic prompt engineering for text-to-image models. The adv-patch deployment agent (DAgent) ensures contextual coherence by determining optimal placement strategies based on scene understanding. The self-examination agent (EAgent) completes this trilogy by providing critical oversight and iterative refinement of both processes. We validate our method on both digital and physical level, \ie, nuImage and manually captured real scenes, where both statistical and visual results prove that our MAGIC is powerful and effectively for attacking wide-used object detection systems.
The application of TensorFlow pre-trained models in deep learning is explored, with an emphasis on practical guidance for tasks such as image classification and object detection. The study covers modern architectures, including ResNet, MobileNet, and EfficientNet, and demonstrates the effectiveness of transfer learning through real-world examples and experiments. A comparison of linear probing and model fine-tuning is presented, supplemented by visualizations using techniques like PCA, t-SNE, and UMAP, allowing for an intuitive understanding of the impact of these approaches. The work provides complete example code and step-by-step instructions, offering valuable insights for both beginners and advanced users. By integrating theoretical concepts with hands-on practice, the paper equips readers with the tools necessary to address deep learning challenges efficiently.
Modern robotic perception is highly dependent on neural networks. It is well known that neural network-based perception can be unreliable in real-world deployment, especially in difficult imaging conditions. Out-of-distribution detection is commonly proposed as a solution for ensuring reliability in real-world deployment. Previous work has shown that normalizing flow models can be used for out-of-distribution detection to improve reliability of robotic perception tasks. Specifically, camera parameters can be optimized with respect to the likelihood output from a normalizing flow, which allows a perception system to adapt to difficult vision scenarios. With this work we propose to use the absolute gradient values from a normalizing flow, which allows the perception system to optimize local regions rather than the whole image. By setting up a table top picking experiment with exceptionally difficult lighting conditions, we show that our method achieves a 60% higher success rate for an object detection task compared to previous methods.
Autonomous Vehicles (AVs) use natural images and videos as input to understand the real world by overlaying and inferring digital elements, facilitating proactive detection in an effort to assure safety. A crucial aspect of this process is real-time, accurate object recognition through automatic scene analysis. While traditional methods primarily concentrate on 2D object detection, exploring 3D object detection, which involves projecting 3D bounding boxes into the three-dimensional environment, holds significance and can be notably enhanced using the AR ecosystem. This study examines an AI model's ability to deduce 3D bounding boxes in the context of real-time scene analysis while producing and evaluating the model's performance and processing time, in the virtual domain, which is then applied to AVs. This work also employs a synthetic dataset that includes artificially generated images mimicking various environmental, lighting, and spatiotemporal states. This evaluation is oriented in handling images featuring objects in diverse weather conditions, captured with varying camera settings. These variations pose more challenging detection and recognition scenarios, which the outcomes of this work can help achieve competitive results under most of the tested conditions.
Vision-based target tracking is crucial for unmanned surface vehicles (USVs) to perform tasks such as inspection, monitoring, and surveillance. However, real-time tracking in complex maritime environments is challenging due to dynamic camera movement, low visibility, and scale variation. Typically, object detection methods combined with filtering techniques are commonly used for tracking, but they often lack robustness, particularly in the presence of camera motion and missed detections. Although advanced tracking methods have been proposed recently, their application in maritime scenarios is limited. To address this gap, this study proposes a vision-guided object-tracking framework for USVs, integrating state-of-the-art tracking algorithms with low-level control systems to enable precise tracking in dynamic maritime environments. We benchmarked the performance of seven distinct trackers, developed using advanced deep learning techniques such as Siamese Networks and Transformers, by evaluating them on both simulated and real-world maritime datasets. In addition, we evaluated the robustness of various control algorithms in conjunction with these tracking systems. The proposed framework was validated through simulations and real-world sea experiments, demonstrating its effectiveness in handling dynamic maritime conditions. The results show that SeqTrack, a Transformer-based tracker, performed best in adverse conditions, such as dust storms. Among the control algorithms evaluated, the linear quadratic regulator controller (LQR) demonstrated the most robust and smooth control, allowing for stable tracking of the USV.
Current video retrieval systems, especially those used in competitions, primarily focus on querying individual keyframes or images rather than encoding an entire clip or video segment. However, queries often describe an action or event over a series of frames, not a specific image. This results in insufficient information when analyzing a single frame, leading to less accurate query results. Moreover, extracting embeddings solely from images (keyframes) does not provide enough information for models to encode higher-level, more abstract insights inferred from the video. These models tend to only describe the objects present in the frame, lacking a deeper understanding. In this work, we propose a system that integrates the latest methodologies, introducing a novel pipeline that extracts multimodal data, and incorporate information from multiple frames within a video, enabling the model to abstract higher-level information that captures latent meanings, focusing on what can be inferred from the video clip, rather than just focusing on object detection in one single image.
Deploying radar object detection models on resource-constrained edge devices like the Raspberry Pi poses significant challenges due to the large size of the model and the limited computational power and the memory of the Pi. In this work, we explore the efficiency of Depthwise Separable Convolutions in radar object detection networks and integrate them into our model. Additionally, we introduce a novel Feature Enhancement and Compression (FEC) module to the PointPillars feature encoder to further improve the model performance. With these innovations, we propose the DSFEC-L model and its two versions, which outperform the baseline (23.9 mAP of Car class, 20.72 GFLOPs) on nuScenes dataset: 1). An efficient DSFEC-M model with a 14.6% performance improvement and a 60% reduction in GFLOPs. 2). A deployable DSFEC-S model with a 3.76% performance improvement and a remarkable 78.5% reduction in GFLOPs. Despite marginal performance gains, our deployable model achieves an impressive 74.5% reduction in runtime on the Raspberry Pi compared to the baseline.