Recent studies on unsupervised object detection based on spatial attention have achieved promising results. Models, such as AIR and SPAIR, output "what" and "where" latent variables that represent the attributes and locations of objects in a scene, respectively. Most of the previous studies concentrate on the "where" localization performance; however, we claim that acquiring "what" object attributes is also essential for representation learning. This paper presents a framework, GMAIR, for unsupervised object detection. It incorporates spatial attention and a Gaussian mixture in a unified deep generative model. GMAIR can locate objects in a scene and simultaneously cluster them without supervision. Furthermore, we analyze the "what" latent variables and clustering process. Finally, we evaluate our model on MultiMNIST and Fruit2D datasets and show that GMAIR achieves competitive results on localization and clustering compared to state-of-the-art methods.
We study anomaly detection for the case when the normal class consists of more than one object category. This is an obvious generalization of the standard one-class anomaly detection problem. However, we show that jointly using multiple one-class anomaly detectors to solve this problem yields poorer results as compared to training a single one-class anomaly detector on all normal object categories together. We further develop a new anomaly detector called DeepMAD that learns compact distinguishing features by exploiting the multiple normal objects categories. This algorithm achieves higher AUC values for different datasets compared to two top performing one-class algorithms that either are trained on each normal object category or jointly trained on all normal object categories combined. In addition to theoretical results we present empirical results using the CIFAR-10, fMNIST, CIFAR-100, and a new dataset we developed called RECYCLE.
This work explores the YOLOv6 object detection model in depth, concentrating on its design framework, optimization techniques, and detection capabilities. YOLOv6's core elements consist of the EfficientRep Backbone for robust feature extraction and the Rep-PAN Neck for seamless feature aggregation, ensuring high-performance object detection. Evaluated on the COCO dataset, YOLOv6-N achieves 37.5\% AP at 1187 FPS on an NVIDIA Tesla T4 GPU. YOLOv6-S reaches 45.0\% AP at 484 FPS, outperforming models like PPYOLOE-S, YOLOv5-S, YOLOX-S, and YOLOv8-S in the same class. Moreover, YOLOv6-M and YOLOv6-L also show better accuracy (50.0\% and 52.8\%) while maintaining comparable inference speeds to other detectors. With an upgraded backbone and neck structure, YOLOv6-L6 delivers cutting-edge accuracy in real-time.
While 3D object detection and pose estimation has been studied for a long time, its evaluation is not yet completely satisfactory. Indeed, existing datasets typically consist in numerous acquisitions of only a few scenes because of the tediousness of pose annotation, and existing evaluation protocols cannot handle properly objects with symmetries. This work aims at addressing those two points. We first present automatic techniques to produce fully annotated RGBD data of many object instances in arbitrary poses, with which we produce a dataset of thousands of independent scenes of bulk parts composed of both real and synthetic images. We then propose a consistent evaluation methodology suitable for any rigid object, regardless of its symmetries. We illustrate it with two reference object detection and pose estimation methods on different objects, and show that incorporating symmetry considerations into pose estimation methods themselves can lead to significant performance gains. The proposed dataset is available at http://rbregier.github.io/dataset2017.
A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects. In this paper, we propose HyperDet3D to explore scene-conditioned prior knowledge for 3D object detection. Existing methods strive for better representation of local elements and their relations without scene-conditioned knowledge, which may cause ambiguity merely based on the understanding of individual points and object candidates. Instead, HyperDet3D simultaneously learns scene-agnostic embeddings and scene-specific knowledge through scene-conditioned hypernetworks. More specifically, our HyperDet3D not only explores the sharable abstracts from various 3D scenes, but also adapts the detector to the given scene at test time. We propose a discriminative Multi-head Scene-specific Attention (MSA) module to dynamically control the layer parameters of the detector conditioned on the fusion of scene-conditioned knowledge. Our HyperDet3D achieves state-of-the-art results on the 3D object detection benchmark of the ScanNet and SUN RGB-D datasets. Moreover, through cross-dataset evaluation, we show the acquired scene-conditioned prior knowledge still takes effect when facing 3D scenes with domain gap.
Object detection with Unmanned Aerial Vehicles (UAVs) has attracted much attention in the research field of computer vision. However, not easy to accurately detect objects with data obtained from UAVs, which capture images from very high altitudes, making the image dominated by small object sizes, that difficult to detect. Motivated by that challenge, we aim to improve the performance of the one-stage detector YOLOv3 by adding a Spatial Pyramid Pooling (SPP) layer on the end of the backbone darknet-53 to obtain more efficient feature extraction process in object detection tasks with UAVs. We also conducted an evaluation study on different versions of YOLOv3 methods. Includes YOLOv3 with SPP, YOLOv3, and YOLOv3-tiny, which we analyzed with the VisDrone2019-Det dataset. Here we show that YOLOv3 with SPP can get results mAP 0.6% higher than YOLOv3 and 26.6% than YOLOv3-Tiny at 640x640 input scale and is even able to maintain accuracy at different input image scales than other versions of the YOLOv3 method. Those results prove that the addition of SPP layers to YOLOv3 can be an efficient solution for improving the performance of the object detection method with data obtained from UAVs.
In this paper, we consider the problem of leveraging existing fully labeled categories to improve the weakly supervised detection (WSD) of new object categories, which we refer to as mixed supervised detection (MSD). Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD. In our framework, we first learn domain-invariant objectness knowledge from the existing fully labeled categories. The knowledge is modeled based on invariant features that are robust to the distribution discrepancy between the existing categories and new categories; therefore the resulting knowledge would generalize well to new categories and could assist detection models to reject distractors (e.g., object parts) in weakly labeled images of new categories. Under the guidance of learned objectness knowledge, we utilize multiple instance learning (MIL) to model the concepts of both objects and distractors and to further improve the ability of rejecting distractors in weakly labeled images. Our robust objectness transfer approach outperforms the existing MSD methods, and achieves state-of-the-art results on the challenging ILSVRC2013 detection dataset and the PASCAL VOC datasets.
In many object recognition applications, the set of possible categories is an open set, and the deployed recognition system will encounter novel objects belonging to categories unseen during training. Detecting such "novel category" objects is usually formulated as an anomaly detection problem. Anomaly detection algorithms for feature-vector data identify anomalies as outliers, but outlier detection has not worked well in deep learning. Instead, methods based on the computed logits of visual object classifiers give state-of-the-art performance. This paper proposes the Familiarity Hypothesis that these methods succeed because they are detecting the absence of familiar learned features rather than the presence of novelty. This distinction is important, because familiarity-based detection will fail in many situations where novelty is present. For example when an image contains both a novel object and a familiar one, the familiarity score will be high, so the novel object will not be noticed. The paper reviews evidence from the literature and presents additional evidence from our own experiments that provide strong support for this hypothesis. The paper concludes with a discussion of whether familiarity-based detection is an inevitable consequence of representation learning.
Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach, named DetCo, which fully explores the contrasts between global image and local image patches to learn discriminative representations for object detection. DetCo has several appealing benefits. (1) It is carefully designed by investigating the weaknesses of current self-supervised methods, which discard important representations for object detection. (2) DetCo builds hierarchical intermediate contrastive losses between global image and local patches to improve object detection, while maintaining global representations for image recognition. Theoretical analysis shows that the local patches actually remove the contextual information of an image, improving the lower bound of mutual information for better contrastive learning. (3) Extensive experiments on PASCAL VOC, COCO and Cityscapes demonstrate that DetCo not only outperforms state-of-the-art methods on object detection, but also on segmentation, pose estimation, and 3D shape prediction, while it is still competitive on image classification. For example, on PASCAL VOC, DetCo-100ep achieves 57.4 mAP, which is on par with the result of MoCov2-800ep. Moreover, DetCo consistently outperforms supervised method by 1.6/1.2/1.0 AP on Mask RCNN-C4/FPN/RetinaNet with 1x schedule. Code will be released at \href{https://github.com/xieenze/DetCo}{\color{blue}{\tt github.com/xieenze/DetCo}}.
Transformer-based methods have demonstrated superior performance for monocular 3D object detection recently, which aims at predicting 3D attributes from a single 2D image. Most existing transformer-based methods leverage both visual and depth representations to explore valuable query points on objects, and the quality of the learned query points has a great impact on detection accuracy. Unfortunately, existing unsupervised attention mechanisms in transformers are prone to generate low-quality query features due to inaccurate receptive fields, especially on hard objects. To tackle this problem, this paper proposes a novel "Supervised Scale-aware Deformable Attention" (SSDA) for monocular 3D object detection. Specifically, SSDA presets several masks with different scales and utilizes depth and visual features to adaptively learn a scale-aware filter for object query augmentation. Imposing the scale awareness, SSDA could well predict the accurate receptive field of an object query to support robust query feature generation. Aside from this, SSDA is assigned with a Weighted Scale Matching (WSM) loss to supervise scale prediction, which presents more confident results as compared to the unsupervised attention mechanisms. Extensive experiments on the KITTI and Waymo Open datasets demonstrate that SSDA significantly improves the detection accuracy, especially on moderate and hard objects, yielding state-of-the-art performance as compared to the existing approaches. Our code will be made publicly available at https://github.com/mikasa3lili/SSD-MonoDETR.
Novel object captioning aims at describing objects absent from training data, with the key ingredient being the provision of object vocabulary to the model. Although existing methods heavily rely on an object detection model, we view the detection step as vocabulary retrieval from an external knowledge in the form of embeddings for any object's definition from Wiktionary, where we use in the retrieval image region features learned from a transformers model. We propose an end-to-end Novel Object Captioning with Retrieved vocabulary from External Knowledge method (NOC-REK), which simultaneously learns vocabulary retrieval and caption generation, successfully describing novel objects outside of the training dataset. Furthermore, our model eliminates the requirement for model retraining by simply updating the external knowledge whenever a novel object appears. Our comprehensive experiments on held-out COCO and Nocaps datasets show that our NOC-REK is considerably effective against SOTAs.
Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly, in surveillance applications sufficiently representative training data may be lacking due to privacy regulations. In this paper, we address the domain adaptation problem from the perspective of robust learning and show that the problem may be formulated as training with noisy labels. We propose a robust object detection framework that is resilient to noise in bounding box class labels, locations and size annotations. To adapt to the domain shift, the model is trained on the target domain using a set of noisy object bounding boxes that are obtained by a detection model trained only in the source domain. We evaluate the accuracy of our approach in various source/target domain pairs and demonstrate that the model significantly improves the state-of-the-art on multiple domain adaptation scenarios on the SIM10K, Cityscapes and KITTI datasets.
Obtaining gold standard annotated data for object detection is often costly, involving human-level effort. Semi-supervised object detection algorithms solve the problem with a small amount of gold-standard labels and a large unlabelled dataset used to generate silver-standard labels. But training on the silver standard labels does not produce good results, because they are machine-generated annotations. In this work, we design a modified loss function to train on large silver standard annotated sets generated by a weak annotator. We include a confidence metric associated with the annotation as an additional term in the loss function, signifying the quality of the annotation. We test the effectiveness of our approach on various test sets and use numerous variations to compare the results with some of the current approaches to object detection. In comparison with the baseline where no confidence metric is used, we achieved a 4% gain in mAP with 25% labeled data and 10% gain in mAP with 50% labeled data by using the proposed confidence metric.
Few-shot object detection, which focuses on detecting novel objects with few labels, is an emerging challenge in the community. Recent studies show that adapting a pre-trained model or modified loss function can improve performance. In this paper, we explore leveraging the power of Contrastive Language-Image Pre-training (CLIP) and hard negative classification loss in low data setting. Specifically, we propose Re-scoring using Image-language Similarity for Few-shot object detection (RISF) which extends Faster R-CNN by introducing Calibration Module using CLIP (CM-CLIP) and Background Negative Re-scale Loss (BNRL). The former adapts CLIP, which performs zero-shot classification, to re-score the classification scores of a detector using image-class similarities, the latter is modified classification loss considering the punishment for fake backgrounds as well as confusing categories on a generalized few-shot object detection dataset. Extensive experiments on MS-COCO and PASCAL VOC show that the proposed RISF substantially outperforms the state-of-the-art approaches. The code will be available.
Object detection, a crucial aspect of computer vision, has seen significant advancements in accuracy and robustness. Despite these advancements, practical applications still face notable challenges, primarily the inaccurate detection or missed detection of small objects. In this paper, we propose YOLO-TLA, an advanced object detection model building on YOLOv5. We first introduce an additional detection layer for small objects in the neck network pyramid architecture, thereby producing a feature map of a larger scale to discern finer features of small objects. Further, we integrate the C3CrossCovn module into the backbone network. This module uses sliding window feature extraction, which effectively minimizes both computational demand and the number of parameters, rendering the model more compact. Additionally, we have incorporated a global attention mechanism into the backbone network. This mechanism combines the channel information with global information to create a weighted feature map. This feature map is tailored to highlight the attributes of the object of interest, while effectively ignoring irrelevant details. In comparison to the baseline YOLOv5s model, our newly developed YOLO-TLA model has shown considerable improvements on the MS COCO validation dataset, with increases of 4.6% in [email omitted] and 4% in [email omitted]:0.95, all while keeping the model size compact at 9.49M parameters. Further extending these improvements to the YOLOv5m model, the enhanced version exhibited a 1.7% and 1.9% increase in [email omitted] and [email omitted]:0.95, respectively, with a total of 27.53M parameters. These results validate the YOLO-TLA model's efficient and effective performance in small object detection, achieving high accuracy with fewer parameters and computational demands.
We present a determinantal point process (DPP) inspired alternative to non-maximum suppression (NMS) which has become an integral step in all state-of-the-art object detection frameworks. DPPs have been shown to encourage diversity in subset selection problems. We pose NMS as a subset selection problem and posit that directly incorporating DPP like framework can improve the overall performance of the object detection system. We propose an optimization problem which takes the same inputs as NMS, but introduces a novel sub-modularity based diverse subset selection functional. Our results strongly indicate that the modifications proposed in this paper can provide consistent improvements to state-of-the-art object detection pipelines.
Moving object detection is important in computer vision. Event-based cameras are bio-inspired cameras that work by mimicking the working of the human eye. These cameras have multiple advantages over conventional frame-based cameras, like reduced latency, HDR, reduced motion blur during high motion, low power consumption, etc. In spite of these advantages, event-based cameras are noise-sensitive and have low resolution. Moreover, the task of moving object detection in these cameras is difficult, as event-based sensors lack useful visual features like texture and color. In this paper, we investigate the application of the k-means clustering technique in detecting moving objects in event-based data.
The paper focuses on the problem of vision-based obstacle detection and tracking for unmanned aerial vehicle navigation. A real-time object localization and tracking strategy from monocular image sequences is developed by effectively integrating the object detection and tracking into a dynamic Kalman model. At the detection stage, the object of interest is automatically detected and localized from a saliency map computed via the image background connectivity cue at each frame; at the tracking stage, a Kalman filter is employed to provide a coarse prediction of the object state, which is further refined via a local detector incorporating the saliency map and the temporal information between two consecutive frames. Compared to existing methods, the proposed approach does not require any manual initialization for tracking, runs much faster than the state-of-the-art trackers of its kind, and achieves competitive tracking performance on a large number of image sequences. Extensive experiments demonstrate the effectiveness and superior performance of the proposed approach.
We propose a 3D object detection method for autonomous driving by fully exploiting the sparse and dense, semantic and geometry information in stereo imagery. Our method, called Stereo R-CNN, extends Faster R-CNN for stereo inputs to simultaneously detect and associate object in left and right images. We add extra branches after stereo Region Proposal Network (RPN) to predict sparse keypoints, viewpoints, and object dimensions, which are combined with 2D left-right boxes to calculate a coarse 3D object bounding box. We then recover the accurate 3D bounding box by a region-based photometric alignment using left and right RoIs. Our method does not require depth input and 3D position supervision, however, outperforms all existing fully supervised image-based methods. Experiments on the challenging KITTI dataset show that our method outperforms the state-of-the-art stereo-based method by around 30% AP on both 3D detection and 3D localization tasks. Code has been released at https://github.com/HKUST-Aerial-Robotics/Stereo-RCNN.
This paper tackles the task of hand-object contact transition detection in egocentric video, which aims to localize the two temporal boundaries of a contact episode: the moment a hand first establishes contact with an object (touch) and the moment contact is released (release). We propose a unified framework that jointly models the interacting hand and object to accurately localize both transition types. The proposed framework augments hand-centric spatiotemporal representations with object-aware features learned directly from the video and introduces a transition-aware event spotting formulation tailored to contact transitions, without relying on external object or hand-object interaction detectors during inference. To support this task, we present ContactTransition, a dataset comprising 4,021 egocentric videos with 8,498 touch and 8,077 release annotations, together with object-of-interest supervision. Experiments demonstrate that the proposed method consistently outperforms strong two-stage and end-to-end event-spotting baselines on both transition types. Finally, we show that detected contact transitions provide effective temporal anchors for downstream egocentric hand-object reasoning.