Developing a new Salient Object Detection (SOD) model involves selecting an ImageNet pre-trained backbone and creating novel feature refinement modules to use backbone features. However, adding new components to a pre-trained backbone needs retraining the whole network on the ImageNet dataset, which requires significant time. Hence, we explore developing a neural network from scratch directly trained on SOD without ImageNet pre-training. Such a formulation offers full autonomy to design task-specific components. To that end, we propose SODAWideNet, an encoder-decoder-style network for Salient Object Detection. We deviate from the commonly practiced paradigm of narrow and deep convolutional models to a wide and shallow architecture, resulting in a parameter-efficient deep neural network. To achieve a shallower network, we increase the receptive field from the beginning of the network using a combination of dilated convolutions and self-attention. Therefore, we propose Multi Receptive Field Feature Aggregation Module (MRFFAM) that efficiently obtains discriminative features from farther regions at higher resolutions using dilated convolutions. Next, we propose Multi-Scale Attention (MSA), which creates a feature pyramid and efficiently computes attention across multiple resolutions to extract global features from larger feature maps. Finally, we propose two variants, SODAWideNet-S (3.03M) and SODAWideNet (9.03M), that achieve competitive performance against state-of-the-art models on five datasets.
In this paper, we aim to develop an efficient and compact deep network for RGB-D salient object detection, where the depth image provides complementary information to boost performance in complex scenarios. Starting from a coarse initial prediction by a multi-scale residual block, we propose a progressively guided alternate refinement network to refine it. Instead of using ImageNet pre-trained backbone network, we first construct a lightweight depth stream by learning from scratch, which can extract complementary features more efficiently with less redundancy. Then, different from the existing…
Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches between image-level annotations and salient objects are still inadequate. In this work, 1) we propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions, liberating the saliency network from error-prone propagation caused by pseudo labels. 2) we prove that even a much…
Recent Salient Object Detection (SOD) systems are mostly based on Convolutional Neural Networks (CNNs). Specifically, Deeply Supervised Saliency (DSS) system has shown it is very useful to add short connections to the network and supervising on the side output. In this work, we propose a new SOD system which aims at designing a more efficient and effective way to pass back global information. Richer and Deeper Supervision (RDS) is applied to better combine features from each side output without demanding much extra computational space. Meanwhile, the backbone network used for SOD is normally p…
Dalian University of Technology（大连理工大学）；Peng Cheng Laboratory（鹏城实验室）；The Hong Kong Polytechnic University（香港理工大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Existing RGB-D salient object detection (SOD) approaches concentrate on the cross-modal fusion between the RGB stream and the depth stream. They do not deeply explore the effect of the depth map itself. In this work, we design a single stream network to directly use the depth map to guide early fusion and middle fusion between RGB and depth, which saves the feature encoder of the depth stream and achieves a lightweight and real-time model. We tactfully utilize depth information from two perspectives: (1) Overcoming the incompatibility problem caused by the great difference between modalities, …
Beihang University（北京航空航天大学）；Harbin Institute of Technology（哈尔滨工业大学）；China University of Petroleum (East China)（中国石油大学（华东））；Peng Cheng Laboratory（鹏城实验室）；Western University（韦仕敦大学）
Although deep salient object detection (SOD) has achieved remarkable progress, deep SOD models are extremely data-hungry, requiring large-scale pixel-wise annotations to deliver such promising results. In this paper, we propose a novel yet effective method for SOD, coined SODGAN, which can generate infinite high-quality image-mask pairs requiring only a few labeled data, and these synthesized pairs can replace the human-labeled DUTS-TR to train any off-the-shelf SOD model. Its contribution is three-fold. 1) Our proposed diffusion embedding network can address the manifold mismatch and is tract…
School of Control and Computer Engineering, North China Electric Power University（华北电力大学控制与计算机工程学院）；China Mobile (Hangzhou) Information Technology Co., Ltd.（中国移动（杭州）信息技术有限公司）
As the scale of object detection dataset is smaller than that of image recognition dataset ImageNet, transfer learning has become a basic training method for deep learning object detection models, which will pretrain the backbone network of object detection model on ImageNet dataset to extract features for classification and localization subtasks. However, the classification task focuses on the salient region features of object, while the location task focuses on the edge features of object, so there is certain deviation between the features extracted by pretrained backbone network and the fea…
Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a…
High-resolution images are widely adopted for high-performance object detection in videos. However, processing high-resolution inputs comes with high computation costs, and naive down-sampling of the input to reduce the computation costs quickly degrades the detection performance. In this paper, we propose SALISA, a novel non-uniform SALiency-based Input SAmpling technique for video object detection that allows for heavy down-sampling of unimportant background regions while preserving the fine-grained details of a high-resolution image. The resulting image is spatially smaller, leading to redu…
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Arizona State University（亚利桑那州立大学）
Deep neural networks have achieved remarkable success in computer vision tasks. Existing neural networks mainly operate in the spatial domain with fixed input sizes. For practical applications, images are usually large and have to be downsampled to the predetermined input size of neural networks. Even though the downsampling operations reduce computation and the required communication bandwidth, it removes both redundant and salient information obliviously, which results in accuracy degradation. Inspired by digital signal processing theories, we analyze the spectral bias from the frequency per…
Deep neural networks can be unreliable in the real world especially when they heavily use spurious features for their predictions. Recently, Singla & Feizi (2022) introduced the Salient Imagenet dataset by annotating and localizing core and spurious features of ~52k samples from 232 classes of Imagenet. While this dataset is useful for evaluating the reliance of pretrained models on spurious features, its small size limits its usefulness for training models. In this work, we first introduce the Salient Imagenet-1M dataset with more than 1 million soft masks localizing core and spurious feature…
Deep neural networks can be unreliable in the real world especially when they heavily use {\it spurious} features for their predictions. Focusing on image classifications, we define {\it core features} as the set of visual features that are always a part of the object definition while {\it spurious features} are the ones that are likely to {\it co-occur} with the object but not a part of it (e.g., attribute "fingers" for class "band aid"). Traditional methods for discovering spurious features either require extensive human annotations (thus, not scalable), or are useful on specific models. In …
University of Oxford（牛津大学）；Shanghai Jiao Tong University（上海交通大学）；University of Cambridge（剑桥大学）
The goal of this work is to segment and name regions of images without access to pixel-level labels during training. To tackle this task, we construct segmenters by distilling the complementary strengths of two foundation models. The first, CLIP (Radford et al. 2021), exhibits the ability to assign names to image content but lacks an accessible representation of object structure. The second, DINO (Caron et al. 2021), captures the spatial extent of objects but has no knowledge of object names. Our method, termed NamedMask, begins by using CLIP to construct category-specific archives of images. …
Dalian University of Technology（大连理工大学）；Peng Cheng Laboratory（鹏城实验室）；Tiwaki Co.,Ltd.（Tiwaki株式会社）
Existing CNNs-Based RGB-D salient object detection (SOD) networks are all required to be pretrained on the ImageNet to learn the hierarchy features which helps provide a good initialization. However, the collection and annotation of large-scale datasets are time-consuming and expensive. In this paper, we utilize self-supervised representation learning (SSL) to design two pretext tasks: the cross-modal auto-encoder and the depth-contour estimation. Our pretext tasks require only a few and unlabeled RGB-D datasets to perform pretraining, which makes the network capture rich semantic contexts and…
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工学院）；Tencent AI Lab（腾讯人工智能实验室）；LIGM（加斯帕尔·蒙日信息学实验室）；Ecole des Ponts（巴黎桥路学院）；Samsung AI Center, Cambridge（三星剑桥人工智能中心）；MIT（麻省理工学院）
Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the self-supervised transformer features to discover an object from an image. Visual tokens are viewed as nodes in a weighted graph with edges representing a connectivity score based on the similarity of tokens. Foreground objects can then be segmented using a normalized graph-cut to group self-similar regions. We solve the graph-cut problem using spectral cluste…
Guangzhou University（广州大学）；Harbin Institute of Technology（哈尔滨工业大学）
Deep neural networks are facing severe threats from adversarial attacks. Most existing black-box attacks fool target model by generating either global perturbations or local patches. However, both global perturbations and local patches easily cause annoying visual artifacts in adversarial example. Compared with some smooth regions of an image, the object region generally has more edges and a more complex texture. Thus small perturbations on it will be more imperceptible. On the other hand, the object region is undoubtfully the decisive part of an image to classification tasks. Motivated by the…
Instagram has become a great venue for amateur and professional photographers alike to showcase their work. It has, in other words, democratized photography. Generally, photographers take thousands of photos in a session, from which they pick a few to showcase their work on Instagram. Photographers trying to build a reputation on Instagram have to strike a balance between maximizing their followers' engagement with their photos, while also maintaining their artistic style. We used transfer learning to adapt Xception, which is a model for object recognition trained on the ImageNet dataset, to t…
Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast to convolutional neural networks, Vision Transformer lacks inherent inductive biases. Therefore, successful training of such models is mainly attributed to pre-training on large-scale datasets such as ImageNet with 1.2M or JFT with 300M images. This hinders the direct adaption of Vision Transformer for small-scale datasets. In this work, we show that self-sup…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Amazon Web Services（亚马逊云科技）
Image classifiers are typically scored on their test set accuracy, but high accuracy can mask a subtle type of model failure. We find that high scoring convolutional neural networks (CNNs) on popular benchmarks exhibit troubling pathologies that allow them to display high accuracy even in the absence of semantically salient features. When a model provides a high-confidence decision without salient supporting input features, we say the classifier has overinterpreted its input, finding too much class-evidence in patterns that appear nonsensical to humans. Here, we demonstrate that neural network…
Zhejiang University of Technology（浙江工业大学）；Zhejiang University（浙江大学）；Hangzhou Dianzi University（杭州电子科技大学）；Zhejiang Police College（浙江警察学院）
Recent years have witnessed unprecedented success achieved by deep learning models in the field of computer vision. However, their vulnerability towards carefully crafted adversarial examples has also attracted the increasing attention of researchers. Motivated by the observation that adversarial examples are due to the non-robust feature learned from the original dataset by models, we propose the concepts of salient feature(SF) and trivial feature(TF). The former represents the class-related feature, while the latter is usually adopted to mislead the model. We extract these two features with …
Meta AI Research（Meta人工智能研究院）；Inria（法国国家信息与自动化研究所）
Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric features that perform on par with supervised features on most object-centric downstream tasks. In this work, we question if using this ability, we can learn any salient and more representative information present in diverse unbounded set of images from across the globe. To do so, we train models on billions of random images without any data pre-processing or …
Shenzhen Institutes of Advanced Technology（深圳先进技术研究院）；University of Cambridge（剑桥大学）
Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we reduce this cost by exploiting the fact that the importance of features computed by convolutional layers is highly input-dependent, and propose feature boosting and suppression (FBS), a new method to predictively amplify salient convolutional channels and skip unimportant ones at run-time. FBS introduces small auxiliary connections to existing convolutional layers. In contrast to channel pruning methods which permanently remove channels, it pres…
Several existing works study either adversarial or natural distributional robustness of deep neural networks separately. In practice, however, models need to enjoy both types of robustness to ensure reliability. In this work, we bridge this gap and show that in fact, explicit tradeoffs exist between adversarial and natural distributional robustness. We first consider a simple linear regression setting on Gaussian data with disjoint sets of core and spurious features. In this setting, through theoretical and empirical analysis, we show that (i) adversarial training with $\ell_1$ and $\ell_2$ no…
Xiamen University（厦门大学）；Peng Cheng Laboratory（鹏城实验室）；Pinterest（品趣志）；Beihang University（北京航空航天大学）；Peking University（北京大学）；Inception Institute of Artificial Intelligence（人工智能创想研究院）
Neural network pruning offers a promising prospect to facilitate deploying deep neural networks on resource-limited devices. However, existing methods are still challenged by the training inefficiency and labor cost in pruning designs, due to missing theoretical guidance of non-salient network components. In this paper, we propose a novel filter pruning method by exploring the High Rank of feature maps (HRank). Our HRank is inspired by the discovery that the average rank of multiple feature maps generated by a single filter is always the same, regardless of the number of image batches CNNs rec…
Institute for Bioinformatics and Medical Informatics, University Tübingen（蒂宾根大学生物信息学与医学信息学研究所）；Columbia University, Department of Psychiatry（哥伦比亚大学精神病学系）；International Max Planck Research School for Intelligent Systems（国际马克斯·普朗克智能系统研究学院）；Institute for Computer Science, University of Göttingen（哥廷根大学计算机科学研究所）；Department for Neuroscience, Baylor College of Medicine（贝勒医学院神经科学系）；Center for Neuroscience and Artificial Intelligence, Baylor College of Medicine（贝勒医学院神经科学与人工智能中心）
Deep neural networks set the state-of-the-art across many tasks in computer vision, but their generalization ability to image distortions is surprisingly fragile. In contrast, the mammalian visual system is robust to a wide range of perturbations. Recent work suggests that this generalization ability can be explained by useful inductive biases encoded in the representations of visual stimuli throughout the visual cortex. Here, we successfully leveraged these inductive biases with a multi-task learning approach: we jointly trained a deep network to perform image classification and to predict ne…
