Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in the community. Most existing approaches employ the Faster R-CNN as basic detection framework, yet, due to the lack of tailored considerations for data-scarce scenario, their performance is often not satisfactory. In this paper, we look closely into the conventional Faster R-CNN and analyze its contradictions from two orthogonal perspectives, namely multi-stage (RPN vs. RCNN) and multi-task (classification vs. localization). To resolve these issues, we propose a simple yet effective architecture, named Decoupled Faster R-CNN (DeFRCN). To be concrete, we extend Faster R-CNN by introducing Gradient Decoupled Layer for multi-stage decoupling and Prototypical Calibration Block for multi-task decoupling. The former is a novel deep layer with redefining the feature-forward operation and gradient-backward operation for decoupling its subsequent layer and preceding layer, and the latter is an offline prototype-based classification model with taking the proposals from detector as input and boosting the original classification scores with additional pairwise scores for calibration. Extensive experiments on multiple benchmarks show our framework is remarkably superior to other existing approaches and establishes a new state-of-the-art in few-shot literature.
论文检索
输入标题、作者或关键词，从 8,216 篇学术成果中精准定位
Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering
PDF ↗We introduce an evaluation methodology for visual question answering (VQA) to better diagnose cases of shortcut learning. These cases happen when a model exploits spurious statistical regularities to produce correct answers but does not actually deploy the desired behavior. There is a need to identify possible shortcuts in a dataset and assess their use before deploying a model in the real world. The research community in VQA has focused exclusively on question-based shortcuts, where a model might, for example, answer "What is the color of the sky" with "blue" by relying mostly on the question-conditional training prior and give little weight to visual evidence. We go a step further and consider multimodal shortcuts that involve both questions and images. We first identify potential shortcuts in the popular VQA v2 training set by mining trivial predictive rules such as co-occurrences of words and visual elements. We then introduce VQA-CounterExamples (VQA-CE), an evaluation protocol based on our subset of CounterExamples i.e. image-question-answer triplets where our rules lead to incorrect answers. We use this new evaluation in a large-scale study of existing approaches for VQA. We demonstrate that even state-of-the-art models perform poorly and that existing techniques to reduce biases are largely ineffective in this context. Our findings suggest that past work on question-based biases in VQA has only addressed one facet of a complex issue. The code for our method is available at \url https://github.com/cdancette/detect-shortcuts
The deep learning methods in addressing semantic segmentation typically demand vast amount of pixel-wise annotated training samples. In this work, we present zero-shot semantic segmentation, which aims to identify not only the seen classes contained in training but also the novel classes that have never been seen. We adopt a stringent inductive setting in which only the instances of seen classes are accessible during training. We propose an open-aware prototypical matching approach to accomplish the segmentation. The prototypical way extracts the visual representations by a set of prototypes, making it convenient and flexible to add new unseen classes. A prototype projection is trained to map the semantic representations towards prototypes based on seen instances, and will generate prototypes for unseen classes. Moreover, an open-set rejection is utilized to detect the objects that do not belong to any seen classes, which greatly reduces the misclassifications of unseen objects as seen classes caused by the lack of unseen training instances. We apply the framework on two segmentation datasets, Pascal VOC 2012 and Pascal Context, and achieve impressively state-of-the-art performance.
Estimating camera wearer's body pose from an egocentric view (egopose) is a vital task in augmented and virtual reality. Existing approaches either use a narrow field of view front facing camera that barely captures the wearer, or an extended head-mounted top-down camera for maximal wearer visibility. In this paper, we tackle the egopose estimation from a more natural human vision span, where camera wearer can be seen in the peripheral view and depending on the head pose the wearer may become invisible or has a limited partial view. This is a realistic visual field for user-centric wearable devices like glasses which have front facing wide angle cameras. Existing solutions are not appropriate for this setting, and so, we propose a novel deep learning system taking advantage of both the dynamic features from camera SLAM and the body shape imagery. We compute 3D head pose, 3D body pose, the figure/ground separation, all at the same time while explicitly enforcing a certain geometric consistency across pose attributes. We further show that this system can be trained robustly with lots of existing mocap data so we do not have to collect and annotate large new datasets. Lastly, our system estimates egopose in real time and on the fly while maintaining high accuracy.
We present a novel approach to robustly detect and perceive vehicles in different camera views as part of a cooperative vehicle-infrastructure system (CVIS). Our formulation is designed for arbitrary camera views and makes no assumptions about intrinsic or extrinsic parameters. First, to deal with multi-view data scarcity, we propose a part-assisted novel view synthesis algorithm for data augmentation. We train a part-based texture inpainting network in a self-supervised manner. Then we render the textured model into the background image with the target 6-DoF pose. Second, to handle various camera parameters, we present a new method that produces dense mappings between image pixels and 3D points to perform robust 2D/3D vehicle parsing. Third, we build the first CVIS dataset for benchmarking, which annotates more than 1540 images (14017 instances) from real-world traffic scenarios. We combine these novel algorithms and datasets to develop a robust approach for 2D/3D vehicle parsing for CVIS. In practice, our approach outperforms SOTA methods on 2D detection, instance segmentation, and 6-DoF pose estimation by 3.8%, 4.3%, and 2.9%, respectively.
Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation
PDF ↗Current self-supervised depth estimation algorithms mainly focus on either stereo or monocular only, neglecting the reciprocal relations between them. In this paper, we propose a simple yet effective framework to improve both stereo and monocular depth estimation by leveraging the underlying complementary knowledge of the two tasks. Our approach consists of three stages. In the first stage, the proposed stereo matching network termed StereoNet is trained on image pairs in a self-supervised manner. Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet. At last, we design an occlusion-aware fusion module (OA Fusion), which generates more reliable depths by fusing estimated depths from StereoNet and SingleNet given the occlusion map. Furthermore, we also take the fused depths as pseudo labels to supervise StereoNet in turn, which brings StereoNet's performance to a new height. Extensive experiments on KITTI dataset demonstrate the effectiveness of our proposed framework. We achieve new SOTA performance on both stereo and monocular depth estimation tasks.
Adversarial data examples have drawn significant attention from the machine learning and security communities. A line of work on tackling adversarial examples is certified robustness via randomized smoothing that can provide a theoretical robustness guarantee. However, such a mechanism usually uses floating-point arithmetic for calculations in inference and requires large memory footprints and daunting computational costs. These defensive models cannot run efficiently on edge devices nor be deployed on integer-only logical units such as Turing Tensor Cores or integer-only ARM processors. To overcome these challenges, we propose an integer randomized smoothing approach with quantization to convert any classifier into a new smoothed classifier, which uses integer-only arithmetic for certified robustness against adversarial perturbations. We prove a tight robustness guarantee under L2-norm for the proposed approach. We show our approach can obtain a comparable accuracy and 4x 5x speedup over floating-point arithmetic certified robust methods on general-purpose CPUs and mobile devices on two distinct datasets (CIFAR-10 and Caltech-101).
With the recent progress in Generative Adversarial Networks (GANs), it is imperative for media and visual forensics to develop detectors which can identify and attribute images to the model generating them. Existing works have shown to attribute images to their corresponding GAN sources with high accuracy. However, these works are limited to a closed set scenario, failing to generalize to GANs unseen during train time and are therefore, not scalable with a steady influx of new GANs. We present an iterative algorithm for discovering images generated from previously unseen GANs by exploiting the fact that all GANs leave distinct fingerprints on their generated images. Our algorithm consists of multiple components including network training, out-of-distribution detection, clustering, merge and refine steps. Through extensive experiments, we show that our algorithm discovers unseen GANs with high accuracy and also generalizes to GANs trained on unseen real datasets. We additionally apply our algorithm to attribution and discovery of GANs in an online fashion as well as to the more standard task of real/fake detection. Our experiments demonstrate the effectiveness of our approach to discover new GANs and can be used in an open-world setup.
Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy are broken. To address this problem, we present an unsupervised learning approach that fuses gyroscope into optical flow learning. Specifically, we first convert gyroscope readings into motion fields named gyro field. Second, we design a self-guided fusion module to fuse the background motion extracted from the gyro field with the optical flow and guide the network to focus on motion details. To the best of our knowledge, this is the first deep learning-based framework that fuses gyroscope data and image content for optical flow learning. To validate our method, we propose a new dataset that covers regular and challenging scenes. Experiments show that our method outperforms the state-of-art methods in both regular and challenging scenes. Code and dataset are available at https://github.com/megvii-research/GyroFlow.
Our objective in this work is video-text retrieval - in particular a joint embedding that enables efficient text-to-video retrieval. The challenges in this area include the design of the visual architecture and the nature of the training data, in that the available large scale video-text training datasets, such as HowTo100M, are noisy and hence competitive performance is achieved only at scale through large amounts of compute. We address both these challenges in this paper. We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captioning datasets. Our model is an adaptation and extension of the recent ViT and Timesformer architectures, and consists of attention in both space and time. The model is flexible and can be trained on both image and video text datasets, either independently or in conjunction. It is trained with a curriculum learning schedule that begins by treating images as 'frozen' snapshots of video, and then gradually learns to attend to increasing temporal context when trained on video datasets. We also provide a new video-text pretraining dataset WebVid-2M, comprised of over two million videos with weak captions scraped from the internet. Despite training on datasets that are an order of magnitude smaller, we show that this approach yields state-of-the-art results on standard downstream video-retrieval benchmarks including MSR-VTT, DiDeMo and MSVD.
While predicting robot grasps with parallel jaw grippers have been well studied and widely applied in robot manipulation tasks, the study on natural human grasp generation with a multi-finger hand remains a very challenging problem. In this paper, we propose to generate human grasps given a 3D object in the world. Our key observation is that it is crucial to model the consistency between the hand contact points and object contact regions. That is, we encourage the prior hand contact points to be close to the object surface and the object common contact regions to be touched by the hand at the same time. Based on the hand-object contact consistency, we design novel objectives in training the human grasp generation model and also a new self-supervised task which allows the grasp generation network to be adjusted even during test time. Our experiments show significant improvement in human grasp generation over state-of-the-art approaches by a large margin. More interestingly, by optimizing the model during test time with the self-supervised task, it helps achieve larger gain on unseen and out-of-domain objects. Project page: https://hwjiang1510.github.io/GraspTTA/.
Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferability on other models with the same learning task but having different architectures. Recently, various methods are proposed to boost the adversarial transferability, among which the input transformation is one of the most effective approaches. We investigate in this direction and observe that existing transformations are all applied on a single image, which might limit the adversarial transferability. To this end, we propose a new input transformation based attack method called Admix that considers the input image and a set of images randomly sampled from other categories. Instead of directly calculating the gradient on the original input, Admix calculates the gradient on the input image admixed with a small portion of each add-in image while using the original label of the input to craft more transferable adversaries.
Neuromorphic vision sensor is a new bio-inspired imaging paradigm that emerged in recent years, which continuously sensing luminance intensity and firing asynchronous spikes (events) with high temporal resolution. Typically, there are two types of neuromorphic vision sensors, namely dynamic vision sensor (DVS) and spike camera. From the perspective of bio-inspired sampling, DVS only perceives movement by imitating the retinal periphery, while the spike camera was developed to perceive fine textures by simulating the fovea. It is meaningful to explore how to combine two types of neuromorphic cameras to reconstruct high quality image like human vision. In this paper, we propose a NeuSpike-Net to learn both the high dynamic range and high motion sensitivity of DVS and the full texture sampling of spike camera to achieve high-speed and high dynamic image reconstruction. We propose a novel representation to effectively extract the temporal information of spike and event data. By introducing the feature fusion module, the two types of neuromorphic data achieve complementary to each other. The experimental results on the simulated and real datasets demonstrate that the proposed approach is effective to reconstruct high-speed and high dynamic range images via the combination of spike and event data.
End-to-end discriminative trackers improve the state of the art significantly, yet the improvement in robustness and efficiency is restricted by the conventional discriminative model, i.e., least-squares based regression. In this paper, we present DTT, a novel single-object discriminative tracker, based on an encoder-decoder Transformer architecture. By self- and encoder-decoder attention mechanisms, our approach is able to exploit the rich scene information in an end-to-end manner, effectively removing the need for hand-designed discriminative models. In online tracking, given a new test frame, dense prediction is performed at all spatial positions. Not only location, but also bounding box of the target object is obtained in a robust fashion, streamlining the discriminative tracking pipeline. DTT is conceptually simple and easy to implement. It yields state-of-the-art performance on four popular benchmarks including GOT-10k, LaSOT, NfS, and TrackingNet while running at over 50 FPS, confirming its effectiveness and efficiency. We hope DTT may provide a new perspective for single-object visual tracking.
In this paper, we present InSeGAN an unsupervised 3D generative adversarial network (GAN) for segmenting (nearly) identical instances of rigid objects in depth images. Using an analysis-by-synthesis approach, we design a novel GAN architecture to synthesize a multiple-instance depth image with independent control over each instance. InSeGAN takes in a set of code vectors (e.g., random noise vectors), each encoding the 3D pose of an object that is represented by a learned implicit object template. The generator has two distinct modules. The first module, the instance feature generator, uses each encoded pose to transform the implicit template into a feature map representation of each object instance. The second module, the depth image renderer, aggregates all of the single-instance feature maps output by the first module and generates a multiple-instance depth image. A discriminator distinguishes the generated multiple-instance depth images from the distribution of true depth images. To use our model for instance segmentation, we propose an instance pose encoder that learns to take in a generated depth image and reproduce the pose code vectors for all of the object instances. To evaluate our approach, we introduce a new synthetic dataset, "Insta-10," consisting of 100,000 depth images each with 5 instances of an object from one of 10 classes. Our experiments on Insta-10, as well as on real-world noisy depth images, show that InSeGAN achieves state-of-the-art performance, often outperforming prior methods by large margins.
Camera Distortion-Aware 3D Human Pose Estimation in Video With Optimization-Based Meta-Learning
PDF ↗Existing 3D human pose estimation algorithms trained on distortion-free datasets suffer performance drop when applied to new scenarios with a specific camera distortion. In this paper, we propose a simple yet effective model for 3D human pose estimation in video that can quickly adapt to any distortion environment by utilizing MAML, a representative optimization-based meta-learning algorithm. We consider a sequence of 2D keypoints in a particular distortion as a single task of MAML. However, due to the absence of a large-scale dataset in a distorted environment, we propose an efficient method to generate synthetic distorted data from undistorted 2D keypoints. For the evaluation, we assume two practical testing situations depending on whether a motion capture sensor is available or not. In particular, we propose Inference Stage Optimization using bone-length symmetry and consistency. Extensive evaluation shows that our proposed method successfully adapts to various degrees of distortion in the testing phase and outperforms the existing state-of-the-art approaches. The proposed method is useful in practice because it does not require camera calibration and additional computations in a testing set-up.
While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific `targeted' class remains a challenging feat. In this paper, we propose a new generative approach for highly transferable targeted perturbations (\ours). We note that the existing methods are less suitable for this task due to their reliance on class-boundary information that changes from one model to another, thus reducing transferability. In contrast, our approach matches perturbed image `distribution' with that of the target class, leading to high targeted transferability rates. To this end, we propose a new objective function that not only aligns the global distributions of source and target images, but also matches the local neighbourhood structure between the two domains. Based on the proposed objective, we train a generator function that can adaptively synthesize perturbations specific to a given input. Our generative approach is independent of the source or target domain labels, while consistently performs well against state-of-the-art methods on a wide range of attack settings. As an example, we achieve 32.63% target transferability from (an adversarially weak) VGG19_ BN to (a strong) WideResNet on ImageNet val. set, which is 4xhigher than the previous best generative attack and 16xbetter than instance-specific iterative attack.
Salient object detection identifies objects in an image that grab visual attention. Although contextual features are considered in recent literature, they often fail in real-world complex scenarios. We observe that this is mainly due to two issues: First, most existing datasets consist of simple foregrounds and backgrounds that hardly represent real-life scenarios. Second, current methods only learn contextual features of salient objects, which are insufficient to model high-level semantics for saliency reasoning in complex scenes. To address these problems, we first construct a new large-scale dataset with complex scenes in this paper. We then propose a context-aware learning approach to explicitly exploit the semantic scene contexts. Specifically, two modules are proposed to achieve the goal: 1) a Semantic Scene Context Refinement module to enhance contextual features learned from salient objects with scene context, and 2) a Contextual Instance Transformer to learn contextual relations between objects and scene context. To our knowledge, such high-level semantic contextual information of image scenes is under-explored for saliency detection in the literature. Extensive experiments demonstrate that the proposed approach outperforms state-of-the-art techniques in complex scenarios for saliency detection, and transfers well to other existing datasets. The code and dataset are available at https://github.com/SirisAvishek/Scene_Context_Aware_Saliency.
Egocentric 3D human pose estimation using a single fisheye camera has become popular recently as it allows capturing a wide range of daily activities in unconstrained environments, which is difficult for traditional outside-in motion capture with external cameras. However, existing methods have several limitations. A prominent problem is that the estimated poses lie in the local coordinate system of the fisheye camera, rather than in the world coordinate system, which is restrictive for many applications. Furthermore, these methods suffer from limited accuracy and temporal instability due to ambiguities caused by the monocular setup and the severe occlusion in a strongly distorted egocentric perspective. To tackle these limitations, we present a new method for egocentric global 3D body pose estimation using a single head-mounted fisheye camera. To achieve accurate and temporally stable global poses, a spatio-temporal optimization is performed over a sequence of frames by minimizing heatmap reprojection errors and enforcing local and global body motion priors learned from a mocap dataset. Experimental results show that our approach outperforms state-of-the-art methods both quantitatively and qualitatively.
T-AutoML: Automated Machine Learning for Lesion Segmentation Using Transformers in 3D Medical Imaging
PDF ↗Lesion segmentation in medical imaging has been an important topic in clinical research. Researchers have proposed various detection and segmentation algorithms to address this task. Recently, deep learning-based approaches have significantly improved the performance over conventional methods. However, most state-of-the-art deep learning methods require the manual design of multiple network components and training strategies. In this paper, we propose a new automated machine learning algorithm, T-AutoML, which not only searches for the best neural architecture, but also finds the best combination of hyper-parameters and data augmentation strategies simultaneously. The proposed method utilizes the modern transformer model, which is introduced to adapt to the dynamic length of the search space embedding and can significantly improve the ability of the search. We validate T-AutoML on several large-scale public lesion segmentation data-sets and achieve state-of-the-art performance.