Recent advances in deep learning have enabled complex real-world use cases comprised of multiple vision tasks and detection tasks are being shifted to the edge side as a pre-processing step of the entire workload. Since running a deep model on resource-constraint devices is challenging, techniques for efficient inference methods are demanded. In this paper, we present an objectness-aware object detection method to reduce computational cost by sparsifying activation values on background regions where target objects don't exist. Sparsified activation can be exploited to increase inference speed by software or hardware accelerated sparse convolution techniques. To accomplish this goal, we incorporate a light-weight objectness mask generation (OMG) network in front of an object detection (OD) network so that it can zero out unnecessary background areas of an input image before being fed into the OD network. In experiments, by switching background activation values to zero, the average number of zero values increases further from 36% to 68% on MobileNetV2-SSDLite even with ReLU activation while maintaining accuracy on MS-COCO. This result indicates that the total MAC including both OMG and OD networks can be reduced to 62% of the original OD model when only non-zero multiply-accumulate operations are considered. Moreover, we show a similar tendency in heavy networks (VGG and RetinaNet) and an additional dataset (PASCAL VOC).
Institute of Medical Technology, Peking University Health Science Center, Peking University（北京大学医学部医学技术研究院）；Department of Biomedical Engineering, Peking University（北京大学生物医学工程系）；Institute of Biomedical Engineering, Shenzhen Bay Laboratory（深圳湾实验室生物医学工程研究所）；Institute of Biomedical Engineering, Peking University Shenzhen Graduate School（北京大学深圳研究生院生物医学工程研究所）；ByteDance AI Lab, ByteDance（字节跳动人工智能实验室）；Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Peking University Cancer Hospital & Institute（北京大学肿瘤医院暨研究所，恶性肿瘤发生与转化研究教育部重点实验室）
Weakly supervised object localization (WSOL) relaxes the requirement of dense annotations for object localization by using image-level classification masks to supervise its learning process. However, current WSOL methods suffer from excessive activation of background locations and need post-processing to obtain the localization mask. This paper attributes these issues to the unawareness of background cues, and propose the background-aware classification activation map (B-CAM) to simultaneously learn localization scores of both object and background with only image-level labels. In our B-CAM, t…
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Weakly supervised object localization (WSOL) aims to localize objects using only image-level labels. Recently a new paradigm has emerged by generating a foreground prediction map (FPM) to achieve localization task. Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator. We argue for using activation value to achieve more efficient learning. It is based on the experimental observation that, for a trained network, CE converges to zero when the foreground mask covers only part of the object region. While activation value …
Shenzhen University（深圳大学）；Wenzhou-Kean University（温州肯恩大学）；Shenzhen Institute of Artificial Intelligence of Robotics of Society（深圳市人工智能与机器人研究院）
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions. In this paper, we propose Contrastive learning for Class-agnostic Activation Map (C$^2$AM) generation only using unlabeled image data, without the involvement of image-level supervision. The core idea comes from the observation that i) semantic information of foreground objects usually differs from their backgrounds; ii) foreground objects with similar a…
Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Korea Advanced Institute of Science Technology (KAIST)（韩国高等科学技术院（KAIST））
Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previous methods utilize the activation map corresponding to the highest activation source. Exploiting only one activation map of the highest probability class is often biased into limited regions or sometimes even highlights background regions. To resolve these limitations, we propose to use activation maps, named combinational class activation maps (CCAM), which are linear combinations of activation maps from the highest…
Weakly-supervised semantic segmentation (WSSS) has recently gained much attention for its promise to train segmentation models only with image-level labels. Existing WSSS methods commonly argue that the sparse coverage of CAM incurs the performance bottleneck of WSSS. This paper provides analytical and empirical evidence that the actual bottleneck may not be sparse coverage but a global thresholding scheme applied after CAM. Then, we show that this issue can be mitigated by satisfying two conditions; 1) reducing the imbalance in the foreground activation and 2) increasing the gap between the f…
Recent mainstream weakly supervised semantic segmentation (WSSS) approaches are mainly based on Class Activation Map (CAM) generated by a CNN (Convolutional Neural Network) based image classifier. In this paper, we propose a novel transformer-based framework, named Semantic Guided Activation Transformer (SemFormer), for WSSS. We design a transformer-based Class-Aware AutoEncoder (CAAE) to extract the class embeddings for the input image and learn class semantics for all classes of the dataset. The class embeddings and learned class semantics are then used to guide the generation of activation …
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；imec-IDLab
One of the most common problems of weakly supervised object localization is that of inaccurate object coverage. In the context of state-of-the-art methods based on Class Activation Mapping, this is caused either by localization maps which focus, exclusively, on the most discriminative region of the objects of interest or by activations occurring in background regions. To address these two problems, we propose two representation regularization mechanisms: Full Region Regularizationwhich tries to maximize the coverage of the localization map inside the object region, and Common Region Regulariza…
School of Computer Science & Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University（深圳大学广东省智能信息处理重点实验室）
We present a two-stage learning framework for weakly supervised object localization (WSOL). While most previous efforts rely on high-level feature based CAMs (Class Activation Maps), this paper proposes to localize objects using the low-level feature based activation maps. In the first stage, an activation map generator produces activation maps based on the low-level feature maps in the classifier, such that rich contextual object information is included in an online manner. In the second stage, we employ an evaluator to evaluate the activation maps predicted by the activation map generator. B…
Fudan University（复旦大学）；Shanghai University of Finance and Economics（上海财经大学）；Deakin University（迪肯大学）
Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus on the most discriminative parts of an object (i.e., incomplete localization problem). In this paper, we empirically prove that this problem is associated with the mixup of the activation values between less discriminative foreground regions and the background. To address it, we propose Class RE-Activation Mapping (CREAM), a novel clustering-based approach to…
When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization
VCIP, College of Computer Science, Nankai University（南开大学计算机科学学院VCIP）；School of Computer Science and Engineering, Tianjin University of Technology（天津工业大学计算机科学与工程学院）；Institute for Infocomm Research, A*STAR（A*STAR信息与通信研究所）；Academy for Advanced Interdisciplinary Studies, Nankai University（南开大学先进跨学科研究院）；Nankai International Advanced Research Institute, Shenzhen Futian（南开国际先进研究院，深圳福田）
Extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS). The CAM of convolution neural networks fails to capture long-range feature dependency on the image and result in the coverage on only foreground object parts, i.e., a lot of false negatives. An intuitive solution is ``coupling'' the CAM with the long-range attention matrix of visual transformers (ViT) We find that the direct ``coupling'', e.g., pixel-wise multiplication of attention and activation, achieves a more global coverage (on the foreground), but unfortunately goes with a great incr…
Shanghai Jiao Tong University（上海交通大学）；Eastern Institute for Advanced Study（东方理工高等研究院）；Northwestern Polytechnical University（西北工业大学）
Few-shot semantic segmentation task aims at performing segmentation in query images with a few annotated support samples. Currently, few-shot segmentation methods mainly focus on leveraging foreground information without fully utilizing the rich background information, which could result in wrong activation of foreground-like background regions with the inadaptability to dramatic scene changes of support-query image pairs. Meanwhile, the lack of detail mining mechanism could cause coarse parsing results without some semantic components or edge areas since prototypes have limited ability to cop…
Shenzhen University（深圳大学）；Shenzhen Institute of Artificial Intelligence of Robotics of Society（深圳人工智能与机器人社会研究院）
It has been widely known that CAM (Class Activation Map) usually only activates discriminative object regions and falsely includes lots of object-related backgrounds. As only a fixed set of image-level object labels are available to the WSSS (weakly supervised semantic segmentation) model, it could be very difficult to suppress those diverse background regions consisting of open set objects. In this paper, we propose a novel Cross Language Image Matching (CLIMS) framework, based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our fram…
Image-level weakly supervised semantic segmentation (WSSS) relies on class activation maps (CAMs) for pseudo labels generation. As CAMs only highlight the most discriminative regions of objects, the generated pseudo labels are usually unsatisfactory to serve directly as supervision. To solve this, most existing approaches follow a multi-training pipeline to refine CAMs for better pseudo-labels, which includes: 1) re-training the classification model to generate CAMs; 2) post-processing CAMs to obtain pseudo labels; and 3) training a semantic segmentation model with the obtained pseudo labels. …
Self-supervised vision transformers can generate accurate localization maps of the objects in an image. However, since they decompose the scene into multiple maps containing various objects, and they do not rely on any explicit supervisory signal, they cannot distinguish between the object of interest from other objects, as required in weakly-supervised object localization (WSOL). To address this issue, we propose leveraging the multiple maps generated by the different transformer heads to acquire pseudo-labels for training a WSOL model. In particular, a new discriminative proposals sampling m…
Extracting class activation maps (CAM) from a classification model often results in poor coverage on foreground objects, i.e., only the discriminative region (e.g., the "head" of "sheep") is recognized and the rest (e.g., the "leg" of "sheep") mistakenly as background. The crux behind is that the weight of the classifier (used to compute CAM) captures only the discriminative features of objects. We tackle this by introducing a new computation method for CAM that explicitly captures non-discriminative features as well, thereby expanding CAM to cover whole objects. Specifically, we omit the last…
Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation
School of Computer and Information Science, Hefei University of Technology（合肥工业大学计算机与信息科学学院）；Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education, School of Artificial Intelligence, Xidian University（教育部智能感知与图像理解重点实验室，西安电子科技大学人工智能学院）；Brain and Artificial Intelligence Laboratory, School of Automation, Northwestern Polytechnical University（脑与人工智能实验室，西北工业大学自动化学院）
Commonwealth Science and Industrial Research Organization (CSIRO)（澳大利亚联邦科学与工业研究组织）；EPFL（瑞士洛桑联邦理工学院）；The Australian National University (ANU)（澳大利亚国立大学）
Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require training pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we p…
Nanyang Technological University（南洋理工大学）；Ant Group（蚂蚁集团）；Delta Research Center（台达研究中心）
Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the classification objective and lack the ability to generalize. To improve the generality of the objective activation maps, we propose a region prototypical network RPNet to explore the cross-image object diversity of the training set. Similar object parts across images are identified via region feature comparison. Object confidence is propagated between regions…
Institute of Microelectronics of Chinese Academy of Sciences（中国科学院微电子研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Deep learning achieves excellent performance in many domains, so we not only apply it to the navel orange semantic segmentation task to solve the two problems of distinguishing defect categories and identifying the stem end and blossom end, but also propose a fastidious attention mechanism to further improve model performance. This lightweight attention mechanism includes two learnable parameters, activations and thresholds, to capture long-range dependence. Specifically, the threshold picks out part of the spatial feature map and the activation excite this area. Based on activations and thres…
University of Malta（马耳他大学）；Department of Computer Science（计算机科学系）
Visual Relationship Detection is defined as, given an image composed of a subject and an object, the correct relation is predicted. To improve the visual part of this difficult problem, ten preprocessing methods were tested to determine whether the widely used Union method yields the optimal results. Therefore, focusing solely on predicate prediction, no object detection and linguistic knowledge were used to prevent them from affecting the comparison results. Once fine-tuned, the Visual Geometry Group models were evaluated using Recall@1, per-predicate recall, activation maximisations, class a…
Weakly supervised object localization (WSOL) aims to localize the target object using only the image-level supervision. Recent methods encourage the model to activate feature maps over the entire object by dropping the most discriminative parts. However, they are likely to induce excessive extension to the backgrounds which leads to over-estimated localization. In this paper, we consider the background as an important cue that guides the feature activation to cover the sophisticated object region and propose contrastive attention loss. The loss promotes similarity between foreground and its dr…
Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories. Existing deep network approaches are mainly based on class activation map, which focuses on highlighting discriminative local region while ignoring the full object. In addition, the emerging transformer-based techniques constantly put a lot of emphasis on the backdrop that impedes the ability to identify complete objects. To address these issues, we present a re-attention mechanism termed token refinement transformer (TRT) that captures the object-level s…
Imperial College London（帝国理工学院）；University of Birmingham（伯明翰大学）；University of Oxford（牛津大学）；HeartFlow, Inc.（HeartFlow公司）
Background samples provide key contextual information for segmenting regions of interest (ROIs). However, they always cover a diverse set of structures, causing difficulties for the segmentation model to learn good decision boundaries with high sensitivity and precision. The issue concerns the highly heterogeneous nature of the background class, resulting in multi-modal distributions. Empirically, we find that neural networks trained with heterogeneous background struggle to map the corresponding contextual samples to compact clusters in feature space. As a result, the distribution over backgr…
University of Tehran（德黑兰大学）；Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM））
Visual attention brings significant progress for Convolution Neural Networks (CNNs) in various applications. In this paper, object-based attention in human visual cortex inspires us to introduce a mechanism for modification of activations in feature maps of CNNs. In this mechanism, the activations of object locations are excited in feature maps. This mechanism is specifically inspired by attention-based gain modulation in object-based attention in brain. It facilitates figure-ground segregation in the visual cortex. Similar to brain, we use the idea to address two challenges in salient object …
Inception Institute of Artificial Intelligence（启元人工智能研究院）；Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Monash University（莫纳什大学）；Linköping University（林雪平大学）；University of California Merced（加州大学默塞德分校）；Google Research（谷歌研究院）；Yonsei University（延世大学）
This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main contribution is the introduction of a novel loss formulation, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision. The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization. The discriminative term incorporates a class…
College of Engineering and Computer Science, Australian National University（澳大利亚国立大学工程与计算机科学学院）；Data61-CSIRO（澳大利亚联邦科学与工业研究组织 Data61）；CVLab, EPFL（洛桑联邦理工学院计算机视觉实验室）
Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we propose a …
SAMSOD: Rethinking SAM Optimization for RGB-T Salient Object Detection
Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Computer Science and Technology, Anhui University（教育部智能计算与信号处理重点实验室，计算机科学与技术学院，安徽大学）
Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activation maps (CAMs) to locate the object regions for pseudo label generation. However, CAMs can only discover the most discriminative parts of objects, thus leading to inferior pixel-level pseudo labels. To address this issue, we propose a saliency guided Inter- and Intra-Class Relation Constrained (I$^2$CRC) framework to assist the expansion of the activated object regions in CAMs. Specifically, we propose a saliency gu…
Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Ewha Womans University（梨花女子大学）；Zhejiang University（浙江大学）；Zhejiang Lab（之江实验室）；University of Michigan（密歇根大学）
Czestochowa University of Technology（琴斯托霍瓦理工大学）；Southeast University（东南大学）；University of Social Sciences（社会科学大学）
In this paper, we consider the problem of descriptors construction for the task of content-based image retrieval using deep neural networks. The idea of neural codes, based on fully connected layers activations, is extended by incorporating the information contained in convolutional layers. It is known that the total number of neurons in the convolutional part of the network is large and the majority of them have little influence on the final classification decision. Therefore, in the paper we propose a novel algorithm that allows us to extract the most significant neuron activations and utili…
Feature extraction has always been a critical component of the computer vision field. More recently, state-of-the-art computer visions algorithms have incorporated Deep Neural Networks (DNN) in feature extracting roles, creating Deep Convolutional Activation Features (DeCAF). The transferability of DNN knowledge domains has enabled the wide use of pretrained DNN feature extraction for applications with novel object classes, especially those with limited training data. This study analyzes the general discriminability of novel object visual appearances encoded into the DeCAF space of six of the …
Tongji University（同济大学）；Technical University of Munich（慕尼黑工业大学）；University of Science and Technology of China（中国科学技术大学）
Weakly-supervised temporal action localization aims to localize action instances temporal boundary and identify the corresponding action category with only video-level labels. Traditional methods mainly focus on foreground and background frames separation with only a single attention branch and class activation sequence. However, we argue that apart from the distinctive foreground and background frames there are plenty of semantically ambiguous action context frames. It does not make sense to group those context frames to the same background class since they are semantically related to a speci…
Yonsei University（延世大学）；Clova AI Research, NAVER Corp.（NAVER公司Clova人工智能研究院）
Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately. In this paper, we design Background Suppression Network (BaS-Net) wh…
Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that networks often learn background textures which are not relevant to the object of interest. In turn this makes the networks susceptible to variations and changes in the background which negatively affect their performance. We propose a new two-step training procedure called split training to reduce this bias in CNNs on both Infrared imagery and RGB data. Our spl…
École de technologie supérieure（高等技术学院）；Ericsson（爱立信）；McGill University（麦吉尔大学）
Class Activation Mapping (CAM) methods have recently gained much attention for weakly-supervised object localization (WSOL) tasks. They allow for CNN visualization and interpretation without training on fully annotated image datasets. CAM methods are typically integrated within off-the-shelf CNN backbones, such as ResNet50. Due to convolution and pooling operations, these backbones yield low resolution CAMs with a down-scaling factor of up to 32, contributing to inaccurate localizations. Interpolation is required to restore full size CAMs, yet it does not consider the statistical properties of…
Weakly Supervised Object Localization (WSOL) methodsusually rely on fully convolutional networks in order to ob-tain class activation maps(CAMs) of targeted labels. How-ever, these networks always highlight the most discriminativeparts to perform the task, the located areas are much smallerthan entire targeted objects. In this work, we propose a novelend-to-end model to enlarge CAMs generated from classifi-cation models, which can localize targeted objects more pre-cisely. In detail, we add an additional module in traditionalclassification networks to extract foreground object propos-als from …
Large-scale trademark retrieval is an important content-based image retrieval task. A recent study shows that off-the-shelf deep features aggregated with Regional-Maximum Activation of Convolutions (R-MAC) achieve state-of-the-art results. However, R-MAC suffers in the presence of background clutter/trivial regions and scale variance, and discards important spatial information. We introduce three simple but effective modifications to R-MAC to overcome these drawbacks. First, we propose the use of both sum and max pooling to minimise the loss of spatial information. We also employ domain-specif…
Vrije Universiteit Brussel（布鲁塞尔自由大学）；imec（欧洲微电子研究中心）；Weizmann Institute of Science（魏茨曼科学研究所）
Deep unfolded neural networks are designed by unrolling the iterations of optimization algorithms. They can be shown to achieve faster convergence and higher accuracy than their optimization counterparts. This paper proposes a new deep-unfolding-based network design for the problem of Robust Principal Component Analysis (RPCA) with application to video foreground-background separation. Unlike existing designs, our approach focuses on modeling the temporal correlation between the sparse representations of consecutive video frames. To this end, we perform the unfolding of an iterative algorithm …
It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of the magnitude of attention to each pixel is called a saliency-map. Saliency-maps are used to check the validity of the classification decision basis, e.g., it is not a valid basis for classification if a DNN pays more attention to the background rather than the subject of an image. Semantic perturbations can significantly change the saliency-map. In this work, we propose the first verification method for attention robustness, i.e., the lo…
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often contextually biased to the spurious scene correlations of different objects or object and background, which may harm their generalization on the downstream tasks. To tackle the issue, we develop a novel object-aware contrastive learning framework that first (a) localizes objects in a self-supervised manner and then (b) debias scene correlations via appropriate data …
