Quantizing open-vocabulary object detection (OVOD) models reduces their memory and computational costs, but extremely low-bit quantization severely degrades both cross-modal (region-text) and intra-modal (region-region) alignments. This multimodal degradation is a unique challenge that prior quantization methods for closed-vocabulary detectors fail to resolve. To overcome this, we propose Quantization-Aware Training with Multimodal Alignment (QATMA), the first multimodal-aware and architecture-agnostic QAT framework tailored for OVOD. QATMA integrates two key components: (i) Curriculum QAT, which partitions the detector by functional roles and progressively expands the quantization scope to suppress error accumulation and ensure stable optimization; and (ii) Text-anchored Pairwise Similarity Distillation, which transfers both region-text and region-region alignments from a full-precision teacher model via pairwise cosine similarities in the joint embedding space. Experimental results on LVIS and COCO zero-shot benchmarks demonstrate that QATMA significantly outperforms existing QAT baselines under extremely low-bit settings, achieving gains of up to 4.3 and 7.6 AP, respectively.
Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in the community. Most existing approaches employ the Faster R-CNN as basic detection framework, yet, due to the lack of tailored considerations for data-scarce scenario, their performance is often not satisfactory. In this paper, we look closely into the conventional Faster R-CNN and analyze its contradictions from two orthogonal perspectives, namely multi-stage (RPN vs. RCNN) and multi-task (classification vs. localization). To resolve these issues, we propose a simple yet effective architecture, named Decoupled Faster R-CNN (DeFRCN). To be concrete, we extend Faster R-CNN by introducing Gradient Decoupled Layer for multi-stage decoupling and Prototypical Calibration Block for multi-task decoupling. The former is a novel deep layer with redefining the feature-forward operation and gradient-backward operation for decoupling its subsequent layer and preceding layer, and the latter is an offline prototype-based classification model with taking the proposals from detector as input and boosting the original classification scores with additional pairwise scores for calibration. Extensive experiments on multiple benchmarks show our framework is remarkably superior to other existing approaches and establishes a new state-of-the-art in few-shot literature.
In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With this approach, the image patches that compose an image or video are organised into a fully connected graph, where the edge between each pair of patches is labeled with a similarity score between patches using features learned by the transformer. Detection and segmentation of salient objects is then formulated as a graph-cut problem and solved using the classical Normalized Cut algorithm. Despite the simplicity of this approach, it achieves state-of-the-art results on several common image and video detection and segmentation tasks. For unsupervised object discovery, this approach outperforms the competing approaches by a margin of 6.1%, 5.7%, and 2.6%, respectively, when tested with the VOC07, VOC12, and COCO20K datasets. For the unsupervised saliency detection task in images, this method improves the score for Intersection over Union (IoU) by 4.4%, 5.6% and 5.2%. When tested with the ECSSD, DUTS, and DUT-OMRON datasets, respectively, compared to current state-of-the-art techniques. This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.
Hyperspectral salient object detection (HSOD) has exhibited remarkable promise across various applications, particularly in intricate scenarios where conventional RGB-based approaches fall short. Despite the considerable progress in HSOD method advancements, two critical challenges require immediate attention. Firstly, existing hyperspectral data dimension reduction techniques incur a loss of spectral information, which adversely affects detection accuracy. Secondly, previous methods insufficiently harness the inherent distinctive attributes of hyperspectral images (HSIs) during the feature extraction process. To address these challenges, we propose a novel approach termed the Distilled Mixed Spectral-Spatial Network (DMSSN), comprising a Distilled Spectral Encoding process and a Mixed Spectral-Spatial Transformer (MSST) feature extraction network. The encoding process utilizes knowledge distillation to construct a lightweight autoencoder for dimension reduction, striking a balance between robust encoding capabilities and low computational costs. The MSST extracts spectral-spatial features through multiple attention head groups, collaboratively enhancing its resistance to intricate scenarios. Moreover, we have created a large-scale HSOD dataset, HSOD-BIT, to tackle the issue of data scarcity in this field and meet the fundamental data requirements of deep network training. Extensive experiments demonstrate that our proposed DMSSN achieves state-of-the-art performance on multiple datasets. We will soon make the code and dataset publicly available on https://github.com/anonymous0519/HSOD-BIT.
드문 상호작용은 학습 데이터에서 희소하게 나타나기 때문에 롱테일 인간-객체 상호작용(HOI) 검출은 여전히 어렵다. 테스트 관측은 추가적인 시각적 증거를 제공하지만, 기존의 캐시 기반 방법은 일반적으로 클래스 전반에 균일한 메모리 용량을 할당하여 과소 표현된 상호작용의 유용한 특징을 포착하는 능력이 제한된다. 이 문제를 해결하기 위해, 우리는 빈도 인식 용량 할당과 신뢰도-다양성 결합 샘플 선택을 통해 테스트 시점 캐시를 적응적으로 구성하는, 학습이 필요 없는 플러그 앤 플레이 프레임워크인 Adaptive Diversity Cache(ADC)를 제안한다. 구체적으로, 빈도 인식 캐시 적응은 빈도 의존적 우선순위와 가중 로그 할당 목적함수를 이용해 과소 표현된 상호작용에 더 큰 용량을 할당하고, 남은 슬롯은 선별된 증강 뷰로 채운다. 신뢰도-다양성 결합 캐시 선택은 예측 신뢰도와 국소 특징 다양성을 결합하여 유용한 캐시 항목을 유지한다. 이후 캐시 검색을 통해 고정된 검출기의 예측을 정제한다. 세 가지 기반 검출기에 대한 HICO-DET와 V-COCO 실험은 일관된 개선을 보여준다. HICO-DET에서 ADC는 드문 상호작용의 평균 정밀도(mAP)를 4.02--8.57 퍼센트 포인트 향상시키며, 드물지 않은 상호작용의 성능도 개선한다. 온라인 적응은 드문 상호작용에서 2.87--7.36 퍼센트 포인트의 추가 향상을 달성한다. 이러한 결과는 적응형 테스트 시점 메모리가 기존 HOI 검출기를 효과적으로 보완하고 롱테일 검출 성능을 향상시킴을 보여준다.
LiDAR–4D 레이더 융합 기반 3D 객체 검출이 학습에서 보지 못한 날씨 유형·강도 조합에서 성능이 급격히 저하되는 개방형 날씨 일반화 문제를 다루며, DCDA(Dual-Critic Guided Diffusion Alignment)는 4D 레이더 조건부 확산 정렬로 열화된 LiDAR BEV 특징을 복원하되 검출 유도 비평가와 날씨 적대적 비평가로 의미론적·분포적 일관성을 동시에 강제한다. 명시적 날씨 모델링이나 쌍(paired) 데이터 없이 학습되며, K-Radar 기반 개방형 날씨 벤치마크에서 기존 최고 성능 방법 대비 type-open·severity-open·type+severity-open 프로토콜 전반에 걸쳐 평균 3D AP를 최대 5.2%p 향상시켰다.
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research efforts have quickly led to the design of novel algorithms able to reduce the impact of the catastrophic forgetting phenomenon in deep neural networks. Due to this surge of interest in the field, many competitions have been held in recent years, as they are an excellent opportunity to stimulate research in promising directions. This paper summarizes the ideas, design choices, rules, and results of the challenge held at the 3rd Continual Learning in Computer Vision (CLVision) Workshop at CVPR 2022. The focus of this competition is the complex continual object detection task, which is still underexplored in literature compared to classification tasks. The challenge is based on the challenge version of the novel EgoObjects dataset, a large-scale egocentric object dataset explicitly designed to benchmark continual learning algorithms for egocentric category-/instance-level object understanding, which covers more than 1k unique main objects and 250+ categories in around 100k video frames.
Detecting the three-dimensional position and orientation of objects using a single RGB camera is a foundational task in computer vision with many important applications. Traditionally, 3D object detection methods are trained in a fully-supervised setup, requiring vast amounts of human annotations, which are laborious, costly, and do not scale well with the ever-increasing amounts of data being captured. In this paper, we present the first method to train 3D object detectors for monocular RGB cameras without domain-specific human annotations, thus making orders of magnitude more data available for training. Thanks to newly proposed Canonical Object Space, the method can not only exploit data across a variety of datasets and camera setups to train a single 3D detector, but unlike previous work it also works out of the box in previously unseen camera setups. All this is crucial for practical applications, where the data and cameras are extremely heterogeneous. The method is evaluated on two standard autonomous driving datasets, where it outperforms previous works, which, unlike our method, still rely on 2D human annotations.
The superior performances of pre-trained foundation models in various visual tasks underscore their potential to enhance the 2D models' open-vocabulary ability. Existing methods explore analogous applications in the 3D space. However, most of them only center around knowledge extraction from singular foundation models, which limits the open-vocabulary ability of 3D models. We hypothesize that leveraging complementary pre-trained knowledge from various foundation models can improve knowledge transfer from 2D pre-trained visual language models to the 3D space. In this work, we propose FM-OV3D, a method of Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection, which improves the open-vocabulary localization and recognition abilities of 3D model by blending knowledge from multiple pre-trained foundation models, achieving true open-vocabulary without facing constraints from original 3D datasets. Specifically, to learn the open-vocabulary 3D localization ability, we adopt the open-vocabulary localization knowledge of the Grounded-Segment-Anything model. For open-vocabulary 3D recognition ability, We leverage the knowledge of generative foundation models, including GPT-3 and Stable Diffusion models, and cross-modal discriminative models like CLIP. The experimental results on two popular benchmarks for open-vocabulary 3D object detection show that our model efficiently learns knowledge from multiple foundation models to enhance the open-vocabulary ability of the 3D model and successfully achieves state-of-the-art performance in open-vocabulary 3D object detection tasks. Code is released at https://github.com/dmzhang0425/FM-OV3D.git.
Visual anomaly detection is essential and commonly used for many tasks in the field of computer vision. Recent anomaly detection datasets mainly focus on industrial automated inspection, medical image analysis and video surveillance. In order to broaden the application and research of anomaly detection in unmanned supermarkets and smart manufacturing, we introduce the supermarket goods anomaly detection (GoodsAD) dataset. It contains 6124 high-resolution images of 484 different appearance goods divided into 6 categories. Each category contains several common different types of anomalies such as deformation, surface damage and opened. Anomalies contain both texture changes and structural changes. It follows the unsupervised setting and only normal (defect-free) images are used for training. Pixel-precise ground truth regions are provided for all anomalies. Moreover, we also conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods. This initial benchmark indicates that some methods which perform well on the industrial anomaly detection dataset (e.g., MVTec AD), show poor performance on our dataset. This is a comprehensive, multi-object dataset for supermarket goods anomaly detection that focuses on real-world applications.
Duplicate removal is a critical step to accomplish a reasonable amount of predictions in prevalent proposal-based object detection frameworks. Albeit simple and effective, most previous algorithms utilize a greedy process without making sufficient use of properties of input data. In this work, we design a new two-stage framework to effectively select the appropriate proposal candidate for each object. The first stage suppresses most of easy negative object proposals, while the second stage selects true positives in the reduced proposal set. These two stages share the same network structure, \ie, an encoder and a decoder formed as recurrent neural networks (RNN) with global attention and context gate. The encoder scans proposal candidates in a sequential manner to capture the global context information, which is then fed to the decoder to extract optimal proposals. In our extensive experiments, the proposed method outperforms other alternatives by a large margin.
In this technical report, we briefly introduce the solution of our team "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021. By conducting several experiments with popular image enhancement methods and image transfer methods, we pulled the low light image and the normal image to a more closer domain. And it is observed that using these data to training can achieve better performance. We also adapt several popular object detection frameworks, e.g., DetectoRS, Cascade-RCNN, and large backbone like Swin-transformer. Finally, we ensemble several models which achieved mAP 74.89 on the testing set, ranking 1st on the final leaderboard.
Detecting objects and their 6D poses from only RGB images is an important task for many robotic applications. While deep learning methods have made significant progress in visual object detection and segmentation, the object pose estimation task is still challenging. In this paper, we introduce an end-toend deep learning framework, named Deep-6DPose, that jointly detects, segments, and most importantly recovers 6D poses of object instances from a single RGB image. In particular, we extend the recent state-of-the-art instance segmentation network Mask R-CNN with a novel pose estimation branch to directly regress 6D object poses without any post-refinements. Our key technical contribution is the decoupling of pose parameters into translation and rotation so that the rotation can be regressed via a Lie algebra representation. The resulting pose regression loss is differential and unconstrained, making the training tractable. The experiments on two standard pose benchmarking datasets show that our proposed approach compares favorably with the state-of-the-art RGB-based multi-stage pose estimation methods. Importantly, due to the end-to-end architecture, Deep-6DPose is considerably faster than competing multi-stage methods, offers an inference speed of 10 fps that is well suited for robotic applications.
We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visualized explanation technique for interpreting the predictions of object detectors. Utilizing the gradients of detector targets flowing into the intermediate feature maps, ODAM produces heat maps that show the influence of regions on the detector's decision for each predicted attribute. Compared to previous works classification activation maps (CAM), ODAM generates instance-specific explanations rather than class-specific ones. We show that ODAM is applicable to both one-stage detectors and two-stage detectors with different types of detector backbones and heads, and produces higher-quality visual explanations than the state-of-the-art both effectively and efficiently. We next propose a training scheme, Odam-Train, to improve the explanation ability on object discrimination of the detector through encouraging consistency between explanations for detections on the same object, and distinct explanations for detections on different objects. Based on the heat maps produced by ODAM with Odam-Train, we propose Odam-NMS, which considers the information of the model's explanation for each prediction to distinguish the duplicate detected objects. We present a detailed analysis of the visualized explanations of detectors and carry out extensive experiments to validate the effectiveness of the proposed ODAM.
Measuring structured object understanding in vision foundation models remains challenging due to inconsistent evaluation protocols and limited part-level supervision. Semantic correspondence (SC) evaluates this capability by testing whether object parts can be matched across instances and categories under large variations in appearance, viewpoint, and geometry. To enable a systematic SC evaluation, we introduce SOCO, a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. In addition, SOCO includes keypoint language descriptions, enabling the evaluation of large vision-language models (LVLMs) and their fine-grained part-level understanding. Comprehensive experiments reveal that (i) vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories and only partially capture object-part position, (ii) LVLMs are stronger at text-prompted part localization than at visual-reference cross-image matching, exposing a gap between language-grounded localization and fine-grained visual correspondence, and (iii) correspondence performance predicts performance on dense downstream tasks, including segmentation, tracking, 3D pose estimation, and 3D detection, more strongly than ImageNet classification. Together, these findings position SOCO as a benchmark for structured, part-level representation quality in vision and multimodal foundation models.
Object-centric visual representations are important for physical-world perception, but existing visual pretraining methods often capture semantic categories without preserving the identity and coherence of individual instances. We present a biologically inspired framework that learns object-centric representations for single images from raw videos. Our approach uses motion boundaries as a source of object-level grouping: off-the-shelf optical flow and clustering produce pseudo-instance masks, which supervise a single-image encoder with pixel-level pairwise metric learning. The framework requires neither human annotations nor camera calibration. We first obtain 195 million pseudo-labeled frames from 7,163 hours of driving and web videos, then expand the supervision to 421 million frames with Motion-Verified Self-Training, which combines model proposals with motion evidence. We train encoders up to Swin-H and distill the learned representations into a family of Swin backbones. Across monocular depth estimation, 3D object detection, 3D occupancy prediction, and end-to-end planning, the resulting models achieve competitive or superior performance relative to supervised and self-supervised pretraining baselines, with particularly strong transfer on geometry- and instance-sensitive tasks. These results show that motion-derived supervision can teach static image encoders to represent visual instances, providing a complementary direction for scalable visual pretraining.
실제 환경의 애플리케이션에서는 6D 자세 추정(6D pose estimation)이 정확하고 빠르며 미확인 객체(unseen object)로 확장 가능할 것을 요구합니다. 본 논문에서는 최대 90도의 회전 편차를 갖는 후보 자세를 보정하는 제로샷(zero-shot) 광각 자세 보정 모델인 WAPR을 소개합니다. 검출된 객체 인스턴스당 단 12개의 후보 자세만으로도, WAPR은 프레임당 1초 이내의 빠른 추론(inference)을 지원하며 초당 최대 25개의 검출된 객체 인스턴스에 달하는 자세 추정 처리량을 달성합니다. 회전 대칭 객체에 대한 광각 학습(training)을 지원하기 위해, WAPR은 회전 대칭 사전 정보(prior)를 활용하여 손실(loss) 계산 전에 대칭적으로 동등한 목표 자세를 정규화합니다. 나아가 이러한 사전 정보를 포함하는 대규모 6D 학습 데이터셋인 SA6D를 구축합니다. SA6D는 944개의 GSO 스캔에 대해 KASAL 기반 회전 대칭 사전 정보를 확보하고, 기하학 및 텍스처 증강을 통해 약 5만 개의 증강 객체 인스턴스와 약 2백만 개의 렌더링된 RGB-D 이미지로 확장합니다. 또한 각도 균형 손실(angle-balanced loss)은 정보량이 적은 대규모 오차 케이스의 영향을 줄임으로써 다양한 각도 범위 전반에서 학습을 안정화합니다. 7개의 BOP 핵심 데이터셋(dataset)에 대한 실험을 통해 WAPR이 고속 및 비제약 추론 설정 모두에서 미확인 객체 6D 자세 위치 추정 및 검출 부문 최고 수준(SOTA)의 성능을 달성함을 보여줍니다. 프로젝트 페이지: https://github.com/WangYuLin-SEU/WAPR.
We consider the problem of multiclass road sign detection using a classification function with multiplicative kernel comprised from two kernels. We show that problems of detection and within-foreground classification can be jointly solved by using one kernel to measure object-background differences and another one to account for within-class variations. The main idea behind this approach is that road signs from different foreground variations can share features that discriminate them from backgrounds. The classification function training is accomplished using SVM, thus feature sharing is obtained through support vector sharing. Training yields a family of linear detectors, where each detector corresponds to a specific foreground training sample. The redundancy among detectors is alleviated using k-medoids clustering. Finally, we report detection and classification results on a set of road sign images obtained from a camera on a moving vehicle.
Advances in machine learning and deep neural networks for object detection, coupled with lower cost and power requirements of cameras, led to promising vision-based solutions for sUAS detection. However, solely relying on the visible spectrum has previously led to reliability issues in low contrast scenarios such as sUAS flying below the treeline and against bright sources of light. Alternatively, due to the relatively high heat signatures emitted from sUAS during flight, a long-wave infrared (LWIR) sensor is able to produce images that clearly contrast the sUAS from its background. However, compared to widely available visible spectrum sensors, LWIR sensors have lower resolution and may produce more false positives when exposed to birds or other heat sources. This research work proposes combining the advantages of the LWIR and visible spectrum sensors using machine learning for vision-based detection of sUAS. Utilizing the heightened background contrast from the LWIR sensor combined and synchronized with the relatively increased resolution of the visible spectrum sensor, a deep learning model was trained to detect the sUAS through previously difficult environments. More specifically, the approach demonstrated effective detection of multiple sUAS flying above and below the treeline, in the presence of heat sources, and glare from the sun. Our approach achieved a detection rate of 71.2 +- 8.3%, improving by 69% when compared to LWIR and by 30.4% when visible spectrum alone, and achieved false alarm rate of 2.7 +- 2.6%, decreasing by 74.1% and by 47.1% when compared to LWIR and visible spectrum alone, respectively, on average, for single and multiple drone scenarios, controlled for the same confidence metric of the machine learning object detector of at least 50%. Videos of the solution's performance can be seen at https://sites.google.com/view/tamudrone-spie2020/.
Existing approaches for autonomous control of pan-tilt-zoom (PTZ) cameras use multiple stages where object detection and localization are performed separately from the control of the PTZ mechanisms. These approaches require manual labels and suffer from performance bottlenecks due to error propagation across the multi-stage flow of information. The large size of object detection neural networks also makes prior solutions infeasible for real-time deployment in resource-constrained devices. We present an end-to-end deep reinforcement learning (RL) solution called Eagle to train a neural network policy that directly takes images as input to control the PTZ camera. Training reinforcement learning is cumbersome in the real world due to labeling effort, runtime environment stochasticity, and fragile experimental setups. We introduce a photo-realistic simulation framework for training and evaluation of PTZ camera control policies. Eagle achieves superior camera control performance by maintaining the object of interest close to the center of captured images at high resolution and has up to 17% more tracking duration than the state-of-the-art. Eagle policies are lightweight (90x fewer parameters than Yolo5s) and can run on embedded camera platforms such as Raspberry PI (33 FPS) and Jetson Nano (38 FPS), facilitating real-time PTZ tracking for resource-constrained environments. With domain randomization, Eagle policies trained in our simulator can be transferred directly to real-world scenarios.