State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The region-wise features, in spite of aligning well with the proposal locations, may still lack the crucial context information which is necessary for filtering out noisy background detections, as well as recognizing objects possessing no distinctive appearances. To address this issue, we present a simple but effective Hierarchical Context Embedding (HCE) framework, which can be applied as a plug-and-play component, to facilitate the classification ability of a series of region-based detectors by mining contextual cues. Specifically, to advance the recognition of context-dependent object categories, we propose an image-level categorical embedding module which leverages the holistic image-level context to learn object-level concepts. Then, novel RoI features are generated by exploiting hierarchically embedded context information beneath both whole images and interested regions, which are also complementary to conventional RoI features. Moreover, to make full use of our hierarchical contextual RoI features, we propose the early-and-late fusion strategies (i.e., feature fusion and confidence fusion), which can be combined to boost the classification accuracy of region-based detectors. Comprehensive experiments demonstrate that our HCE framework is flexible and generalizable, leading to significant and consistent improvements upon various region-based detectors, including FPN, Cascade R-CNN and Mask R-CNN.
Recent breakthroughs in diffusion models, multimodal pretraining, and efficient finetuning have led to an explosion of text-to-image generative models. Given human evaluation is expensive and difficult to scale, automated methods are critical for evaluating the increasingly large number of new models. However, most current automated evaluation metrics like FID or CLIPScore only offer a holistic measure of image quality or image-text alignment, and are unsuited for fine-grained or instance-level analysis. In this paper, we introduce GenEval, an object-focused framework to evaluate compositional image properties such as object co-occurrence, position, count, and color. We show that current object detection models can be leveraged to evaluate text-to-image models on a variety of generation tasks with strong human agreement, and that other discriminative vision models can be linked to this pipeline to further verify properties like object color. We then evaluate several open-source text-to-image models and analyze their relative generative capabilities on our benchmark. We find that recent models demonstrate significant improvement on these tasks, though they are still lacking in complex capabilities such as spatial relations and attribute binding. Finally, we demonstrate how GenEval might be used to help discover existing failure modes, in order to inform development of the next generation of text-to-image models. Our code to run the GenEval framework is publicly available at https://github.com/djghosh13/geneval.
We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries. Semantic segmentation is a fundamental remote sensing task, and most state-of-the-art methods rely on DCNNs as their workhorse. A major reason for their success is that deep networks learn to accumulate contextual information over very large windows (receptive fields). However, this success comes at a cost, since the associated loss of effecive spatial resolution washes out high-frequency details and leads to blurry object boundaries. Here, we propose to counter this effect by combining semantic segmentation with semantically informed edge detection, thus making class-boundaries explicit in the model, First, we construct a comparatively simple, memory-efficient model by adding boundary detection to the Segnet encoder-decoder architecture. Second, we also include boundary detection in FCN-type models and set up a high-end classifier ensemble. We show that boundary detection significantly improves semantic segmentation with CNNs. Our high-end ensemble achieves > 90% overall accuracy on the ISPRS Vaihingen benchmark.
Person detection is a key problem for many computer vision tasks. While face detection has reached maturity, detecting people under a full variation of camera view-points, human poses, lighting conditions and occlusions is still a difficult challenge. In this work we focus on detecting human heads in natural scenes. Starting from the recent local R-CNN object detector, we extend it with two types of contextual cues. First, we leverage person-scene relations and propose a Global CNN model trained to predict positions and scales of heads directly from the full image. Second, we explicitly model pairwise relations among objects and train a Pairwise CNN model using a structured-output surrogate loss. The Local, Global and Pairwise models are combined into a joint CNN framework. To train and test our full model, we introduce a large dataset composed of 369,846 human heads annotated in 224,740 movie frames. We evaluate our method and demonstrate improvements of person head detection against several recent baselines in three datasets. We also show improvements of the detection speed provided by our model.
We present Sparse R-CNN OBB, a novel framework for the detection of oriented objects in SAR images leveraging sparse learnable proposals. The Sparse R-CNN OBB has streamlined architecture and ease of training as it utilizes a sparse set of 300 proposals instead of training a proposals generator on hundreds of thousands of anchors. To the best of our knowledge, Sparse R-CNN OBB is the first to adopt the concept of sparse learnable proposals for the detection of oriented objects, as well as for the detection of ships in Synthetic Aperture Radar (SAR) images. The detection head of the baseline model, Sparse R-CNN, is re-designed to enable the model to capture object orientation. We also fine-tune the model on RSDD-SAR dataset and provide a performance comparison to state-of-the-art models. Experimental results shows that Sparse R-CNN OBB achieves outstanding performance, surpassing other models on both inshore and offshore scenarios. The code is available at: www.github.com/ka-mirul/Sparse-R-CNN-OBB.
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224x224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement. The new network structure, called SPP-net, can generate a fixed-length representation regardless of image size/scale. Pyramid pooling is also robust to object deformations. With these advantages, SPP-net should in general improve all CNN-based image classification methods. On the ImageNet 2012 dataset, we demonstrate that SPP-net boosts the accuracy of a variety of CNN architectures despite their different designs. On the Pascal VOC 2007 and Caltech101 datasets, SPP-net achieves state-of-the-art classification results using a single full-image representation and no fine-tuning. The power of SPP-net is also significant in object detection. Using SPP-net, we compute the feature maps from the entire image only once, and then pool features in arbitrary regions (sub-images) to generate fixed-length representations for training the detectors. This method avoids repeatedly computing the convolutional features. In processing test images, our method is 24-102x faster than the R-CNN method, while achieving better or comparable accuracy on Pascal VOC 2007. In ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2014, our methods rank #2 in object detection and #3 in image classification among all 38 teams. This manuscript also introduces the improvement made for this competition.
인간-로봇 상호작용(HRI) 시스템에서 기술 지표 향상이 실제 사용자 인식 차이로 이어지는지 검증하기 위해, Whisper·Florence-2·LLaMA 3.1 기반 베이스라인(성공률 75%)과 Grounding DINO+SAM·Qwen 3.5 9B로 모듈을 교체한 개선 시스템(성공률 90%)을 24명 참여자 대상 within-subject 실험으로 비교했다. 참여자의 70.83%가 개선 시스템을 선호했으며, 지각 속도·신뢰성·유능함 및 유창성 세 가지 지표 모두 통계적으로 유의미하게 높은 평가를 받아(p < 0.001), 기술적 개선이 실제 인터랙션에서도 사용자에게 지각 가능한 수준임이 확인됐다.
Due to its efficiency and stability, Robust Principal Component Analysis (RPCA) has been emerging as a promising tool for moving object detection. Unfortunately, existing RPCA based methods assume static or quasi-static background, and thereby they may have trouble in coping with the background scenes that exhibit a persistent dynamic behavior. In this work, we shall introduce two techniques to fill in the gap. First, instead of using the raw pixel-value as features that are brittle in the presence of dynamic background, we devise a so-called Gaussian max-pooling operator to estimate a "stable-value" for each pixel. Those stable-values are robust to various background changes and can therefore distinguish effectively the foreground objects from the background. Then, to obtain more accurate results, we further propose a Segmentation Constrained RPCA (SC-RPCA) model, which incorporates the temporal and spatial continuity in images into RPCA. The inference process of SC-RPCA is a group sparsity constrained nuclear norm minimization problem, which is convex and easy to solve. Experimental results on seven videos from the CDCNET 2014 database show the superior performance of the proposed method.
Knowledge Distillation (KD) is a well-known training paradigm in deep neural networks where knowledge acquired by a large teacher model is transferred to a small student. KD has proven to be an effective technique to significantly improve the student's performance for various tasks including object detection. As such, KD techniques mostly rely on guidance at the intermediate feature level, which is typically implemented by minimizing an lp-norm distance between teacher and student activations during training. In this paper, we propose a replacement for the pixel-wise independent lp-norm based on the structural similarity (SSIM). By taking into account additional contrast and structural cues, feature importance, correlation and spatial dependence in the feature space are considered in the loss formulation. Extensive experiments on MSCOCO demonstrate the effectiveness of our method across different training schemes and architectures. Our method adds only little computational overhead, is straightforward to implement and at the same time it significantly outperforms the standard lp-norms. Moreover, more complex state-of-the-art KD methods using attention-based sampling mechanisms are outperformed, including a +3.5 AP gain using a Faster R-CNN R-50 compared to a vanilla model.
In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting. However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD). In this paper, we identify the overlooked problem of foreground shift as the main reason for this. Foreground shift only occurs when replaying images of previous tasks and refers to the fact that their background might contain foreground objects of the current task. To overcome this problem, a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem. In addition, we propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model. ABR significantly reduces forgetting of previous classes while maintaining high plasticity in current classes. Moreover, it considerably reduces the storage requirements when compared to standard image replay. Comprehensive experiments on Pascal-VOC and COCO datasets support the state-of-the-art performance of our model.
Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of existing works face two problems: the low recall of RPN in unseen classes and the confusion of unseen classes with background. In this paper, we present the first method that combines DETR and meta-learning to perform zero-shot object detection, named Meta-ZSDETR, where model training is formalized as an individual episode based meta-learning task. Different from Faster R-CNN based methods that firstly generate class-agnostic proposals, and then classify them with visual-semantic alignment module, Meta-ZSDETR directly predict class-specific boxes with class-specific queries and further filter them with the predicted accuracy from classification head. The model is optimized with meta-contrastive learning, which contains a regression head to generate the coordinates of class-specific boxes, a classification head to predict the accuracy of generated boxes, and a contrastive head that utilizes the proposed contrastive-reconstruction loss to further separate different classes in visual space. We conduct extensive experiments on two benchmark datasets MS COCO and PASCAL VOC. Experimental results show that our method outperforms the existing ZSD methods by a large margin.
Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the trained clean weather, they struggle in unseen adverse weather conditions with the domain gap. In this paper, we propose a Domain Generalization based approach, named V2X-DGW, for LiDAR-based 3D object detection on multi-agent perception system under adverse weather conditions. Our research aims to not only maintain favorable multi-agent performance in the clean weather but also promote the performance in the unseen adverse weather conditions by learning only on the clean weather data. To realize the Domain Generalization, we first introduce the Adaptive Weather Augmentation (AWA) to mimic the unseen adverse weather conditions, and then propose two alignments for generalizable representation learning: Trust-region Weather-invariant Alignment (TWA) and Agent-aware Contrastive Alignment (ACA). To evaluate this research, we add Fog, Rain, Snow conditions on two publicized multi-agent datasets based on physics-based models, resulting in two new datasets: OPV2V-w and V2XSet-w. Extensive experiments demonstrate that our V2X-DGW achieved significant improvements in the unseen adverse weathers.
The complexity of event-based object detection (OD) poses considerable challenges. Spiking Neural Networks (SNNs) show promising results and pave the way for efficient event-based OD. Despite this success, the path to efficient SNNs on embedded devices remains a challenge. This is due to the size of the networks required to accomplish the task and the ability of devices to take advantage of SNNs benefits. Even when "edge" devices are considered, they typically use embedded GPUs that consume tens of watts. In response to these challenges, our research introduces an embedded neuromorphic testbench that utilizes the SPiking Low-power Event-based ArchiTecture (SPLEAT) accelerator. Using an extended version of the Qualia framework, we can train, evaluate, quantize, and deploy spiking neural networks on an FPGA implementation of SPLEAT. We used this testbench to load a state-of-the-art SNN solution, estimate the performance loss associated with deploying the network on dedicated hardware, and run real-world event-based OD on neuromorphic hardware specifically designed for low-power spiking neural networks. Remarkably, our embedded spiking solution, which includes a model with 1.08 million parameters, operates efficiently with 490 mJ per prediction.
Precise perception of the environment is essential in highly automated driving systems, which rely on machine learning tasks such as object detection and segmentation. Compression of sensor data is commonly used for data handling, while virtualization is used for hardware-in-the-loop validation. Both methods can alter sensor data and degrade model performance. This necessitates a systematic approach to quantifying image validity. This paper presents a four-step framework to evaluate the impact of image modifications on machine learning tasks. First, a dataset with modified images is prepared to ensure one-to-one matching image pairs, enabling measurement of deviations resulting from compression and virtualization. Second, image deviations are quantified by comparing the effects of compression and virtualization against original camera-based sensor data. Third, the performance of state-of-the-art object detection models is analyzed to determine how altered input data affects perception tasks, including bounding box accuracy and reliability. Finally, a correlation analysis is performed to identify relationships between image quality and model performance. As a result, the LPIPS metric achieves the highest correlation between image deviation and machine learning performance across all evaluated machine learning tasks.
We present a deep learning method for end-to-end monocular 3D object detection and metric shape retrieval. We propose a novel loss formulation by lifting 2D detection, orientation, and scale estimation into 3D space. Instead of optimizing these quantities separately, the 3D instantiation allows to properly measure the metric misalignment of boxes. We experimentally show that our 10D lifting of sparse 2D Regions of Interests (RoIs) achieves great results both for 6D pose and recovery of the textured metric geometry of instances. This further enables 3D synthetic data augmentation via inpainting recovered meshes directly onto the 2D scenes. We evaluate on KITTI3D against other strong monocular methods and demonstrate that our approach doubles the AP on the 3D pose metrics on the official test set, defining the new state of the art.
This paper considers arbitrary document detection performed on a mobile device. The classical contour-based approach often fails in cases featuring occlusion, complex background, or blur. The region-based approach, which relies on the contrast between object and background, does not have application limitations, however, its known implementations are highly resource-consuming. We propose a modification of the contour-based method, in which the competing contour location hypotheses are ranked according to the contrast between the areas inside and outside the border. In the experiments, such modification allows for the decrease of alternatives ordering errors by 40% and the decrease of the overall detection errors by 10%. The proposed method provides unmatched state-of-the-art performance on the open MIDV-500 dataset, and it demonstrates results comparable with state-of-the-art performance on the SmartDoc dataset.
How do we build a general and broad object detection system? We use all labels of all concepts ever annotated. These labels span diverse datasets with potentially inconsistent taxonomies. In this paper, we present a simple method for training a unified detector on multiple large-scale datasets. We use dataset-specific training protocols and losses, but share a common detection architecture with dataset-specific outputs. We show how to automatically integrate these dataset-specific outputs into a common semantic taxonomy. In contrast to prior work, our approach does not require manual taxonomy reconciliation. Experiments show our learned taxonomy outperforms a expert-designed taxonomy in all datasets. Our multi-dataset detector performs as well as dataset-specific models on each training domain, and can generalize to new unseen dataset without fine-tuning on them. Code is available at https://github.com/xingyizhou/UniDet.
Intelligent resident surveillance is one of the most essential smart community services. The increasing demand for security needs surveillance systems to be able to detect anomalies in surveillance scenes. Employing high-capacity computational devices for intelligent surveillance in residential societies is costly and not feasible. Therefore, we propose anomaly detection for intelligent surveillance using CPU-only edge devices. A modular framework to capture object-level inferences and tracking is developed. To cope with partial occlusions, posture deformations, and complex scenes, we employed feature encoding and trajectory association governed by two metrices complementing to each other. The elements of an anomaly detection framework are optimized to run on CPU-only edge devices with sufficient frames per second (FPS). The experimental results indicate the proposed method is feasible and achieves satisfactory results in real-life scenarios.
Multiscale convolutional neural network (CNN) has demonstrated remarkable capabilities in solving various vision problems. However, fusing features of different scales alwaysresults in large model sizes, impeding the application of multiscale CNNs in RGB-D saliency detection. In this paper, we propose a customized feature fusion module, called Saliency Enhanced Feature Fusion (SEFF), for RGB-D saliency detection. SEFF utilizes saliency maps of the neighboring scales to enhance the necessary features for fusing, resulting in more representative fused features. Our multiscale RGB-D saliency detector uses SEFF and processes images with three different scales. SEFF is used to fuse the features of RGB and depth images, as well as the features of decoders at different scales. Extensive experiments on five benchmark datasets have demonstrated the superiority of our method over ten SOTA saliency detectors.
This survey explores the adaptation of visual transformer models in Autonomous Driving, a transition inspired by their success in Natural Language Processing. Surpassing traditional Recurrent Neural Networks in tasks like sequential image processing and outperforming Convolutional Neural Networks in global context capture, as evidenced in complex scene recognition, Transformers are gaining traction in computer vision. These capabilities are crucial in Autonomous Driving for real-time, dynamic visual scene processing. Our survey provides a comprehensive overview of Vision Transformer applications in Autonomous Driving, focusing on foundational concepts such as self-attention, multi-head attention, and encoder-decoder architecture. We cover applications in object detection, segmentation, pedestrian detection, lane detection, and more, comparing their architectural merits and limitations. The survey concludes with future research directions, highlighting the growing role of Vision Transformers in Autonomous Driving.