The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perceive the interval objects from the small and sparse discriminative attention map, yet ignoring the co-occurrence confounder (e.g., bird and sky), which makes the model inspection (e.g., CAM) hard to distinguish between the object and context. In this paper, we make an early attempt to tackle this challenge via causal intervention (CI). Our proposed method, dubbed CI-CAM, explores the causalities among images, contexts, and categories to eliminate the biased co-occurrence in the class activation maps thus improving the accuracy of object localization. Extensive experiments on several benchmarks demonstrate the effectiveness of CI-CAM in learning the clear object boundaries from confounding contexts. Particularly, in CUB-200-2011 which severely suffers from the co-occurrence confounder, CI-CAM significantly outperforms the traditional CAM-based baseline (58.39% vs 52.4% in top-1 localization accuracy). While in more general scenarios such as ImageNet, CI-CAM can also perform on par with the state of the arts.
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade. As methods have been proposed, a comprehensive survey of these topics is of great importance. In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets and standard evaluation metrics that are widely used in this field. We also discuss the key challenges in this field, development history of this field, advantages/disadvantages of the methods in each category, the relationships between methods in different categories, applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.
Although recent advances in deep learning accelerated an improvement in a weakly supervised object localization (WSOL) task, there are still challenges to identify the entire body of an object, rather than only discriminative parts. In this paper, we propose a novel residual fine-grained attention (RFGA) module that autonomously excites the less activated regions of an object by utilizing information distributed over channels and locations within feature maps in combination with a residual operation. To be specific, we devise a series of mechanisms of triple-view attention representation, attention expansion, and feature calibration. Unlike other attention-based WSOL methods that learn a coarse attention map, having the same values across elements in feature maps, our proposed RFGA learns fine-grained values in an attention map by assigning different attention values for each of the elements. We validated the superiority of our proposed RFGA module by comparing it with the recent methods in the literature over three datasets. Further, we analyzed the effect of each mechanism in our RFGA and visualized attention maps to get insights.
Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation. The BoxCaseg model is jointly trained using box-supervised images and salient images in a multi-task learning manner. The fine-annotated salient images provide class-agnostic and precise object localization guidance for box-supervised images. The object masks predicted by a pretrained BoxCaseg model are refined via a novel merged and dropped strategy as proxy ground truth to train a Mask R-CNN for weakly-supervised instance segmentation. Only using $7991$ salient images, the weakly-supervised Mask R-CNN is on par with fully-supervised Mask R-CNN on PASCAL VOC and significantly outperforms previous state-of-the-art box-supervised instance segmentation methods on COCO. The source code, pretrained models and datasets are available at \url{https://github.com/hustvl/BoxCaseg}.
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In contrast to the widely used image classification-based pre-training (e.g., on ImageNet), which does not include any location-related training tasks, we transform a classification dataset into a detection dataset through a weakly supervised object localization method based on Class Activation Maps to directly pre-train a detector, making the pre-trained model location-aware and capable of predicting bounding boxes. We show that DAP can outperform the traditional classification pre-training in terms of both sample efficiency and convergence speed in downstream detection tasks including VOC and COCO. In particular, DAP boosts the detection accuracy by a large margin when the number of examples in the downstream task is small.
Weakly supervised object localization (WSOL) is a challenging problem when given image category labels but requires to learn object localization models. Optimizing a convolutional neural network (CNN) for classification tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue. In this paper, we argue that partial activation is caused by the intrinsic characteristics of CNN, where the convolution operations produce local receptive fields and experience difficulty to capture long-range feature dependency among pixels. We introduce the token semantic coupled attention map (TS-CAM) to take full advantage of the self-attention mechanism in visual transformer for long-range dependency extraction. TS-CAM first splits an image into a sequence of patch tokens for spatial embedding, which produce attention maps of long-range visual dependency to avoid partial activation. TS-CAM then re-allocates category-related semantics for patch tokens, enabling each of them to be aware of object categories. TS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization. Experiments on the ILSVRC/CUB-200-2011 datasets show that TS-CAM outperforms its CNN-CAM counterparts by 7.1%/27.1% for WSOL, achieving state-of-the-art performance.
Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object categories which limits their applicability in real world scenarios such as field robotics. In this work, we propose a probabilistic multiple instance learning approach for few-shot Common Object Localization (COL) and few-shot Weakly Supervised Object Detection (WSOD). In these tasks, only image-level labels, which are much cheaper to acquire, are available. We find that operating on features extracted from the last layer of a pre-trained Faster-RCNN is more effective compared to previous episodic learning based few-shot COL methods. Our model simultaneously learns the distribution of the novel objects and localizes them via expectation-maximization steps. As a probabilistic model, we employ von Mises-Fisher (vMF) distribution which captures the semantic information better than Gaussian distribution when applied to the pre-trained embedding space. When the novel objects are localized, we utilize them to learn a linear appearance model to detect novel classes in new images. Our extensive experiments show that the proposed method, despite being simple, outperforms strong baselines in few-shot COL and WSOD, as well as large-scale WSOD tasks.
Object localization has a vital role in any object detector, and therefore, has been the focus of attention by many researchers. In this article, a special training approach is proposed for a light convolutional neural network (CNN) to determine the region of interest (ROI) in an image while effectively reducing the number of probable anchor boxes. Almost all CNN-based detectors utilize a fixed input size image, which may yield poor performance when dealing with various object sizes. In this paper, a different CNN structure is proposed taking three different input sizes, to enhance the performance. In order to demonstrate the effectiveness of the proposed method, two common data set are used for training while tracking by localization application is considered to demonstrate its final performance. The promising results indicate the applicability of the presented structure and the training method in practice.
Object localization in 3D space is a challenging aspect in monocular 3D object detection. Recent advances in 6DoF pose estimation have shown that predicting dense 2D-3D correspondence maps between image and object 3D model and then estimating object pose via Perspective-n-Point (PnP) algorithm can achieve remarkable localization accuracy. Yet these methods rely on training with ground truth of object geometry, which is difficult to acquire in real outdoor scenes. To address this issue, we propose MonoRUn, a novel detection framework that learns dense correspondences and geometry in a self-supervised manner, with simple 3D bounding box annotations. To regress the pixel-related 3D object coordinates, we employ a regional reconstruction network with uncertainty awareness. For self-supervised training, the predicted 3D coordinates are projected back to the image plane. A Robust KL loss is proposed to minimize the uncertainty-weighted reprojection error. During testing phase, we exploit the network uncertainty by propagating it through all downstream modules. More specifically, the uncertainty-driven PnP algorithm is leveraged to estimate object pose and its covariance. Extensive experiments demonstrate that our proposed approach outperforms current state-of-the-art methods on KITTI benchmark.
Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is constrained by several factors, such as (i) low-quality region proposals for novel classes and (ii) negligence of the inter-class correlation among different classes. Such limitations hinder the generalization of base-class knowledge for the detection of novel-class objects. In this work, we design Meta-DETR, a novel few-shot detection framework that incorporates correlational aggregation for meta-learning into DETR detection frameworks. Meta-DETR works entirely at image level without any region proposals, which circumvents the constraint of inaccurate proposals in prevalent few-shot detection frameworks. Besides, Meta-DETR can simultaneously attend to multiple support classes within a single feed-forward. This unique design allows capturing the inter-class correlation among different classes, which significantly reduces the misclassification of similar classes and enhances knowledge generalization to novel classes. Experiments over multiple few-shot object detection benchmarks show that the proposed Meta-DETR outperforms state-of-the-art methods by large margins. The implementation codes will be released at https://github.com/ZhangGongjie/Meta-DETR.
This paper reports a new solution of leveraging temporal classification to support weakly supervised object detection (WSOD). Specifically, we introduce raster scan-order techniques to serialize 2D images into 1D sequence data, and then leverage a combined LSTM (Long, Short-Term Memory) and CTC (Connectionist Temporal Classification) network to achieve object localization based on a total count (of interested objects). We term our proposed network LSTM-CCTC (Count-based CTC). This "learning from counting" strategy differs from existing WSOD methods in that our approach automatically identifies critical points on or near a target object. This strategy significantly reduces the need of generating a large number of candidate proposals for object localiza- tion. Experiments show that our method yields state-of-the-art performance based on an evaluation on PASCAL VOC datasets.
Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network. Although prior works struggled to localize objects through various spatial regularization strategies, we argue that how to extract object structural information from the trained classification network is neglected. In this paper, we propose a two-stage approach, termed structure-preserving activation (SPA), toward fully leveraging the structure information incorporated in convolutional features for WSOL. First, a restricted activation module (RAM) is designed to alleviate the structure-missing issue caused by the classification network on the basis of the observation that the unbounded classification map and global average pooling layer drive the network to focus only on object parts. Second, we designed a post-process approach, termed self-correlation map generating (SCG) module to obtain structure-preserving localization maps on the basis of the activation maps acquired from the first stage. Specifically, we utilize the high-order self-correlation (HSC) to extract the inherent structural information retained in the learned model and then aggregate HSC of multiple points for precise object localization. Extensive experiments on two publicly available benchmarks including CUB-200-2011 and ILSVRC show that the proposed SPA achieves substantial and consistent performance gains compared with baseline approaches.Code and models are available at https://github.com/Panxjia/SPA_CVPR2021
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding through the grounding-by-matching strategy. In practice, our model first predicts the target category from the language descriptions using a simple language classification model. Then, based on the category, our model sifts out a small number of instance candidates (usually less than 20) from the panoptic segmentation of point clouds. Thus, the non-trivial 3D visual grounding task has been effectively re-formulated as a simplified instance-matching problem, considering that instance-level candidates are more rational than the redundant 3D object proposals. Subsequently, for each candidate, we perform the multi-level contextual inference, i.e., referring from instance attribute perception, instance-to-instance relation perception, and instance-to-background global localization perception, respectively. Eventually, the most relevant candidate is selected and localized by ranking confidence scores, which are obtained by the cooperative holistic visual-language feature matching. Experiments confirm that our method outperforms previous state-of-the-arts on ScanRefer online benchmark and Nr3D/Sr3D datasets.
We demonstrate the use of an extensive deep neural network to localize instances of objects in images. The EDNN is naturally able to accurately perform multi-class counting using only ground truth count values as labels. Without providing any conceptual information, object annotations, or pixel segmentation information, the neural network is able to formulate its own conceptual representation of the items in the image. Using images labelled with only the counts of the objects present,the structure of the extensive deep neural network can be exploited to perform localization of the objects within the visual field. We demonstrate that a trained EDNN can be used to count objects in images much larger than those on which it was trained. In order to demonstrate our technique, we introduce seven new data sets: five progressively harder MNIST digit-counting data sets, and two datasets of 3d-rendered rubber ducks in various situations. On most of these datasets, the EDNN achieves greater than 99% test set accuracy in counting objects.
Deep learning (DL) has drawn tremendous attention in object localization and recognition for both natural and medical images. U-Net segmentation models have demonstrated superior performance compared to conventional handcrafted feature-based methods. Medical image modality-specific DL models are better at transferring domain knowledge to a relevant target task than those that are pretrained on stock photography images. This helps improve model adaptation, generalization, and class-specific region of interest (ROI) localization. In this study, we train chest X-ray (CXR) modality-specific U-Nets and other state-of-the-art U-Net models for semantic segmentation of tuberculosis (TB)-consistent findings. Automated segmentation of such manifestations could help radiologists reduce errors and supplement decision-making while improving patient care and productivity. Our approach uses the publicly available TBX11K CXR dataset with weak TB annotations, typically provided as bounding boxes, to train a set of U-Net models. Next, we improve the results by augmenting the training data with weak localizations, post-processed into an ROI mask, from a DL classifier that is trained to classify CXRs as showing normal lungs or suspected TB manifestations. Test data are individually derived from the TBX11K CXR training distribution and other cross-institutional collections including the Shenzhen TB and Montgomery TB CXR datasets. We observe that our augmented training strategy helped the CXR modality-specific U-Net models achieve superior performance with test data derived from the TBX11K CXR training distribution as well as from cross-institutional collections (p < 0.05).
Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of the gradient-based terms in Grad-CAM. We conduct a thorough analysis to demonstrate the improvement achieved by our method in measuring the importance of the extracted representations for the CNN's predictions, which yields to our method's administration in object localization and model interpretation.
One of the inherent limitations of current AI systems, stemming from the passive learning mechanisms (e.g., supervised learning), is that they perform well on labeled datasets but cannot deduce knowledge on their own. To tackle this problem, we derive inspiration from a highly intentional learning system via action: the toddler. Inspired by the toddler's learning procedure, we design an interactive agent that can learn and store task-agnostic visual representation while exploring and interacting with objects in the virtual environment. Experimental results show that such obtained representation was expandable to various vision tasks such as image classification, object localization, and distance estimation tasks. In specific, the proposed model achieved 100%, 75.1% accuracy and 1.62% relative error, respectively, which is noticeably better than autoencoder-based model (99.7%, 66.1%, 1.95%), and also comparable with those of supervised models (100%, 87.3%, 0.71%).
As a natural way for human-computer interaction, fixation provides a promising solution for interactive image segmentation. In this paper, we focus on Personal Fixations-based Object Segmentation (PFOS) to address issues in previous studies, such as the lack of appropriate dataset and the ambiguity in fixations-based interaction. In particular, we first construct a new PFOS dataset by carefully collecting pixel-level binary annotation data over an existing fixation prediction dataset, such dataset is expected to greatly facilitate the study along the line. Then, considering characteristics of personal fixations, we propose a novel network based on Object Localization and Boundary Preservation (OLBP) to segment the gazed objects. Specifically, the OLBP network utilizes an Object Localization Module (OLM) to analyze personal fixations and locates the gazed objects based on the interpretation. Then, a Boundary Preservation Module (BPM) is designed to introduce additional boundary information to guard the completeness of the gazed objects. Moreover, OLBP is organized in the mixed bottom-up and top-down manner with multiple types of deep supervision. Extensive experiments on the constructed PFOS dataset show the superiority of the proposed OLBP network over 17 state-of-the-art methods, and demonstrate the effectiveness of the proposed OLM and BPM components. The constructed PFOS dataset and the proposed OLBP network are available at https://github.com/MathLee/OLBPNet4PFOS.
In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. However, we find that most previous loss functions for BBR have two main drawbacks: (i) Both $\ell_n$-norm and IOU-based loss functions are inefficient to depict the objective of BBR, which leads to slow convergence and inaccurate regression results. (ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR. To mitigate the adverse effects caused thereby, we perform thorough studies to exploit the potential of BBR losses in this paper. Firstly, an Efficient Intersection over Union (EIOU) loss is proposed, which explicitly measures the discrepancies of three geometric factors in BBR, i.e., the overlap area, the central point and the side length. After that, we state the Effective Example Mining (EEM) problem and propose a regression version of focal loss to make the regression process focus on high-quality anchor boxes. Finally, the above two parts are combined to obtain a new loss function, namely Focal-EIOU loss. Extensive experiments on both synthetic and real datasets are performed. Notable superiorities on both the convergence speed and the localization accuracy can be achieved over other BBR losses.
Humans are able to form a complex mental model of the environment they move in. This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e.g., objects, rooms, buildings), includes static and dynamic entities and their relations (e.g., a person is in a room at a given time). In contrast, current robots' internal representations still provide a partial and fragmented understanding of the environment, either in the form of a sparse or dense set of geometric primitives (e.g., points, lines, planes, voxels) or as a collection of objects. This paper attempts to reduce the gap between robot and human perception by introducing a novel representation, a 3D Dynamic Scene Graph(DSG), that seamlessly captures metric and semantic aspects of a dynamic environment. A DSG is a layered graph where nodes represent spatial concepts at different levels of abstraction, and edges represent spatio-temporal relations among nodes. Our second contribution is Kimera, the first fully automatic method to build a DSG from visual-inertial data. Kimera includes state-of-the-art techniques for visual-inertial SLAM, metric-semantic 3D reconstruction, object localization, human pose and shape estimation, and scene parsing. Our third contribution is a comprehensive evaluation of Kimera in real-life datasets and photo-realistic simulations, including a newly released dataset, uHumans2, which simulates a collection of crowded indoor and outdoor scenes. Our evaluation shows that Kimera achieves state-of-the-art performance in visual-inertial SLAM, estimates an accurate 3D metric-semantic mesh model in real-time, and builds a DSG of a complex indoor environment with tens of objects and humans in minutes. Our final contribution shows how to use a DSG for real-time hierarchical semantic path-planning. The core modules in Kimera are open-source.