2022-07-14 更新
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
Authors:Tyler LaBonte, Yale Song, Xin Wang, Vibhav Vineet, Neel Joshi
Weakly supervised object detection (WSOD) enables object detectors to be trained using image-level class labels. However, the practical application of current WSOD models is limited, as they operate at small scales and require extensive training and refinement. We propose the Weakly Supervised Detection Transformer, which enables efficient knowledge transfer from a large-scale pretraining dataset to WSOD finetuning on hundreds of novel objects. We leverage pretrained knowledge to improve the multiple instance learning framework used in WSOD, and experiments show our approach outperforms the state-of-the-art on datasets with twice the novel classes than previously shown.
PDF CVPR 2022 Workshop on Attention and Transformers in Vision
点此查看论文截图
Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network
Authors:Bo Ju, Zhikang Zou, Xiaoqing Ye, Minyue Jiang, Xiao Tan, Errui Ding, Jingdong Wang
3D object detection task from lidar or camera sensors is essential for autonomous driving. Pioneer attempts at multi-modality fusion complement the sparse lidar point clouds with rich semantic texture information from images at the cost of extra network designs and overhead. In this work, we propose a novel semantic passing framework, named SPNet, to boost the performance of existing lidar-based 3D detection models with the guidance of rich context painting, with no extra computation cost during inference. Our key design is to first exploit the potential instructive semantic knowledge within the ground-truth labels by training a semantic-painted teacher model and then guide the pure-lidar network to learn the semantic-painted representation via knowledge passing modules at different granularities: class-wise passing, pixel-wise passing and instance-wise passing. Experimental results show that the proposed SPNet can seamlessly cooperate with most existing 3D detection frameworks with 1~5% AP gain and even achieve new state-of-the-art 3D detection performance on the KITTI test benchmark. Code is available at: https://github.com/jb892/SPNet.
PDF Accepted by ACMMM2022
点此查看论文截图
Dynamic Proposals for Efficient Object Detection
Authors:Yiming Cui, Linjie Yang, Ding Liu
Object detection is a basic computer vision task to loccalize and categorize objects in a given image. Most state-of-the-art detection methods utilize a fixed number of proposals as an intermediate representation of object candidates, which is unable to adapt to different computational constraints during inference. In this paper, we propose a simple yet effective method which is adaptive to different computational resources by generating dynamic proposals for object detection. We first design a module to make a single query-based model to be able to inference with different numbers of proposals. Further, we extend it to a dynamic model to choose the number of proposals according to the input image, greatly reducing computational costs. Our method achieves significant speed-up across a wide range of detection models including two-stage and query-based models while obtaining similar or even better accuracy.
PDF
点此查看论文截图
Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection
Authors:Xubin Zhong, Changxing Ding, Zijian Li, Shaoli Huang
Human-Object Interaction (HOI) detection is a core task for high-level image understanding. Recently, Detection Transformer (DETR)-based HOI detectors have become popular due to their superior performance and efficient structure. However, these approaches typically adopt fixed HOI queries for all testing images, which is vulnerable to the location change of objects in one specific image. Accordingly, in this paper, we propose to enhance DETR’s robustness by mining hard-positive queries, which are forced to make correct predictions using partial visual cues. First, we explicitly compose hard-positive queries according to the ground-truth (GT) position of labeled human-object pairs for each training image. Specifically, we shift the GT bounding boxes of each labeled human-object pair so that the shifted boxes cover only a certain portion of the GT ones. We encode the coordinates of the shifted boxes for each labeled human-object pair into an HOI query. Second, we implicitly construct another set of hard-positive queries by masking the top scores in cross-attention maps of the decoder layers. The masked attention maps then only cover partial important cues for HOI predictions. Finally, an alternate strategy is proposed that efficiently combines both types of hard queries. In each iteration, both DETR’s learnable queries and one selected type of hard-positive queries are adopted for loss computation. Experimental results show that our proposed approach can be widely applied to existing DETR-based HOI detectors. Moreover, we consistently achieve state-of-the-art performance on three benchmarks: HICO-DET, V-COCO, and HOI-A. Code is available at https://github.com/MuchHair/HQM.
PDF Accepted by ECCV2022
点此查看论文截图
Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection
Authors:Fatih Cagatay Akyon, Sinan Onur Altinuc, Alptekin Temizel
Detection of small objects and objects far away in the scene is a major challenge in surveillance applications. Such objects are represented by small number of pixels in the image and lack sufficient details, making them difficult to detect using conventional detectors. In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection. The proposed technique is generic in the sense that it can be applied on top of any available object detector without any fine-tuning. Experimental evaluations, using object detection baselines on the Visdrone and xView aerial object detection datasets show that the proposed inference method can increase object detection AP by 6.8%, 5.1% and 5.3% for FCOS, VFNet and TOOD detectors, respectively. Moreover, the detection accuracy can be further increased with a slicing aided fine-tuning, resulting in a cumulative increase of 12.7%, 13.4% and 14.5% AP in the same order. Proposed technique has been integrated with Detectron2, MMDetection and YOLOv5 models and it is publicly available at https://github.com/obss/sahi.git .
PDF Accepted at ICIP 2022, 5 pages, 4 figures, 2 tables
点此查看论文截图
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
Authors:Mingfei Gao, Chen Xing, Juan Carlos Niebles, Junnan Li, Ran Xu, Wenhao Liu, Caiming Xiong
Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent open vocabulary and zero-shot detection methods attempt to detect novel object categories beyond those seen during training. They achieve this goal by training on a pre-defined base categories to induce generalization to novel objects. However, their potential is still constrained by the small set of base categories available for training. To enlarge the set of base classes, we propose a method to automatically generate pseudo bounding-box annotations of diverse objects from large-scale image-caption pairs. Our method leverages the localization ability of pre-trained vision-language models to generate pseudo bounding-box labels and then directly uses them for training object detectors. Experimental results show that our method outperforms the state-of-the-art open vocabulary detector by 8% AP on COCO novel categories, by 6.3% AP on PASCAL VOC, by 2.3% AP on Objects365 and by 2.8% AP on LVIS. Code is available at https://github.com/salesforce/PB-OVD.
PDF ECCV 2022
点此查看论文截图
Weakly-Supervised Salient Object Detection Using Point Supervision
Authors:Shuyong Gao, Wei Zhang, Yan Wang, Qianyu Guo, Chenglong Zhang, Yangji He, Wenqiang Zhang
Current state-of-the-art saliency detection models rely heavily on large datasets of accurate pixel-wise annotations, but manually labeling pixels is time-consuming and labor-intensive. There are some weakly supervised methods developed for alleviating the problem, such as image label, bounding box label, and scribble label, while point label still has not been explored in this field. In this paper, we propose a novel weakly-supervised salient object detection method using point supervision. To infer the saliency map, we first design an adaptive masked flood filling algorithm to generate pseudo labels. Then we develop a transformer-based point-supervised saliency detection model to produce the first round of saliency maps. However, due to the sparseness of the label, the weakly supervised model tends to degenerate into a general foreground detection model. To address this issue, we propose a Non-Salient Suppression (NSS) method to optimize the erroneous saliency maps generated in the first round and leverage them for the second round of training. Moreover, we build a new point-supervised dataset (P-DUTS) by relabeling the DUTS dataset. In P-DUTS, there is only one labeled point for each salient object. Comprehensive experiments on five largest benchmark datasets demonstrate our method outperforms the previous state-of-the-art methods trained with the stronger supervision and even surpass several fully supervised state-of-the-art models. The code is available at: https://github.com/shuyonggao/PSOD.
PDF accepted by AAAI2022
点此查看论文截图
Appearance-guided Attentive Self-Paced Learning for Unsupervised Salient Object Detection
Authors:Huajun Zhou, Bo Qiao, Lingxiao Yang, Jianhuang Lai, Xiaohua Xie
Existing Deep-Learning-based (DL-based) Unsupervised Salient Object Detection (USOD) methods learn saliency information in images based on the prior knowledge of traditional saliency methods and pretrained deep networks. However, these methods employ a simple learning strategy to train deep networks and therefore cannot properly incorporate the “hidden” information of the training samples into the learning process. Moreover, appearance information, which is crucial for segmenting objects, is only used as post-process after the network training process. To address these two issues, we propose a novel appearance-guided attentive self-paced learning framework for unsupervised salient object detection. The proposed framework integrates both self-paced learning (SPL) and appearance guidance into a unified learning framework. Specifically, for the first issue, we propose an Attentive Self-Paced Learning (ASPL) paradigm that organizes the training samples in a meaningful order to excavate gradually more detailed saliency information. Our ASPL facilitates our framework capable of automatically producing soft attention weights that measure the learning difficulty of training samples in a purely self-learning way. For the second issue, we propose an Appearance Guidance Module (AGM), which formulates the local appearance contrast of each pixel as the probability of saliency boundary and finds the potential boundary of the target objects by maximizing the probability. Furthermore, we further extend our framework to other multi-modality SOD tasks by aggregating the appearance vectors of other modality data, such as depth map, thermal image or optical flow. Extensive experiments on RGB, RGB-D, RGB-T and video SOD benchmarks prove that our framework achieves state-of-the-art performance against existing USOD methods and is comparable to the latest supervised SOD methods.
PDF 14 pages
点此查看论文截图