A variety of recent works have looked into defenses for deep neural networks against adversarial attacks particularly within the image processing domain. Speech processing applications such as automatic speech recognition (ASR) are increasingly relying on deep learning models, and so are also prone to adversarial attacks. However, many of the defenses explored for ASR simply adapt the image-domain defenses, which may not provide optimal robustness. This paper explores speech specific defenses using the mel spectral domain, and introduces a novel defense method called 'mel domain noise flooding' (MDNF). MDNF applies additive noise to the mel spectrogram of a speech utterance prior to re-synthesising the audio signal. We test the defenses against strong white-box adversarial attacks such as projected gradient descent (PGD) and Carlini-Wagner (CW) attacks, and show better robustness compared to a randomized smoothing baseline across strong threat models.
We present a method for estimating dense continuous-time optical flow. Traditional dense optical flow methods compute the pixel displacement between two images. Due to missing information, these approaches cannot recover the pixel trajectories in the blind time between two images. In this work, we show that it is possible to compute per-pixel, continuous-time optical flow by additionally using events from an event camera. Events provide temporally fine-grained information about movement in image space due to their asynchronous nature and microsecond response time. We leverage these benefits to predict pixel trajectories densely in continuous-time via parameterized B\'ezier curves. To achieve this, we introduce multiple innovations to build a neural network with strong inductive biases for this task: First, we build multiple sequential correlation volumes in time using event data. Second, we use B\'ezier curves to index these correlation volumes at multiple timestamps along the trajectory. Third, we use the retrieved correlation to update the B\'ezier curve representations iteratively. Our method can optionally include image pairs to boost performance further. The proposed approach outperforms existing image-based and event-based methods by 11.5 % lower EPE on DSEC-Flow. Finally, we introduce a novel synthetic dataset MultiFlow for pixel trajectory regression on which our method is currently the only successful approach.
In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images. Using a Vision Transformer (ViT) pretrained with a label-free self-supervised method, we successfully train a coarse image segmentation model for the Duckietown environment using 70 training images. Our model performs coarse image segmentation at the 8x8 patch level, and the inference resolution can be adjusted to balance prediction granularity and real-time perception constraints. We study how best to adapt a ViT to our task and environment, and find that some lightweight architectures can yield good single-image segmentations at a usable frame rate, even on CPU. The resulting perception model is used as the backbone for a simple yet robust visual servoing agent, which we deploy on a differential drive mobile robot to perform two tasks: lane following and obstacle avoidance.
Scientists at the Berkeley SETI Research Center are Searching for Extraterrestrial Intelligence (SETI) by a new signal detection method that converts radio signals into spectrograms through Fourier transforms and classifies signals represented by two-dimensional time-frequency spectrums, which successfully converts a signal classification problem into an image classification task. In view of the negative impact of background noises on the accuracy of spectrograms classification, a new method is introduced in this paper. After Gaussian convolution smoothing the signals, edge detection functions are applied to detect the edge of the signals and enhance the outline of the signals, then the processed spectrograms are used to train the deep neural network to compare the classification accuracy of various image classification networks. The results show that the proposed method can effectively improve the classification accuracy of SETI spectrums.
Image-to-image translation has recently achieved remarkable results. But despite current success, it suffers from inferior performance when translations between classes require large shape changes. We attribute this to the high-resolution bottlenecks which are used by current state-of-the-art image-to-image methods. Therefore, in this work, we propose a novel deep hierarchical Image-to-Image Translation method, called DeepI2I. We learn a model by leveraging hierarchical features: (a) structural information contained in the shallow layers and (b) semantic information extracted from the deep layers. To enable the training of deep I2I models on small datasets, we propose a novel transfer learning method, that transfers knowledge from pre-trained GANs. Specifically, we leverage the discriminator of a pre-trained GANs (i.e. BigGAN or StyleGAN) to initialize both the encoder and the discriminator and the pre-trained generator to initialize the generator of our model. Applying knowledge transfer leads to an alignment problem between the encoder and generator. We introduce an adaptor network to address this. On many-class image-to-image translation on three datasets (Animal faces, Birds, and Foods) we decrease mFID by at least 35% when compared to the state-of-the-art. Furthermore, we qualitatively and quantitatively demonstrate that transfer learning significantly improves the performance of I2I systems, especially for small datasets. Finally, we are the first to perform I2I translations for domains with over 100 classes.
Training a fully convolutional network for semantic segmentation typically requires a large, labeled dataset with little label noise if good generalization is to be guaranteed. For many segmentation problems, however, data with pixel- or voxel-level labeling accuracy are scarce due to the cost of manual labeling. This problem is exacerbated in domains where manual annotation is difficult, resulting in large amounts of variability in the labeling even across domain experts. Therefore, training segmentation networks to generalize better by learning from both labeled and unlabeled images (called semi-supervised learning) is problem of both practical and theoretical interest. However, traditional semi-supervised learning methods for segmentation often necessitate hand-crafting a differentiable regularizer specific to a given segmentation problem, which can be extremely time-consuming. In this work, we propose "supervision by denoising" (SUD), a framework that enables us to supervise segmentation models using their denoised output as targets. SUD unifies temporal ensembling and spatial denoising techniques under a spatio-temporal denoising framework and alternates denoising and network weight update in an optimization framework for semi-supervision. We validate SUD on three tasks-kidney and tumor (3D), and brain (3D) segmentation, and cortical parcellation (2D)-demonstrating a significant improvement in the Dice overlap and the Hausdorff distance of segmentations over supervised-only and temporal ensemble baselines.
The importance of hierarchical image organization has been witnessed by a wide spectrum of applications in computer vision and graphics. Different from image segmentation with the spatial whole-part consideration, this work designs a modern framework for disassembling an image into a family of derived signals from a scale-space perspective. Specifically, we first offer a formal definition of image disassembly. Then, by concerning desired properties, such as peeling hierarchy and structure preservation, we convert the original complex problem into a series of two-component separation sub-problems, significantly reducing the complexity. The proposed framework is flexible to both supervised and unsupervised settings. A compact recurrent network, namely hierarchical image peeling net, is customized to efficiently and effectively fulfill the task, which is about 3.5Mb in size, and can handle 1080p images in more than 60 fps per recurrence on a GTX 2080Ti GPU, making it attractive for practical use. Both theoretical findings and experimental results are provided to demonstrate the efficacy of the proposed framework, reveal its superiority over other state-of-the-art alternatives, and show its potential to various applicable scenarios. Our code is available at \url{https://github.com/ForawardStar/HIPe}.
For image inpainting, the convolutional neural networks (CNN) in previous methods often adopt standard convolutional operator, which treats valid pixels and holes indistinguishably. As a result, they are limited in handling irregular holes and tend to produce color-discrepant and blurry inpainting result. Partial convolution (PConv) copes with this issue by conducting masked convolution and feature re-normalization conditioned only on valid pixels, but the mask-updating is handcrafted and independent with image structural information. In this paper, we present an edge-guided learnable bidirectional attention map (Edge-LBAM) for improving image inpainting of irregular holes with several distinct merits. Instead of using a hard 0-1 mask, a learnable attention map module is introduced for learning feature re-normalization and mask-updating in an end-to-end manner. Learnable reverse attention maps are further proposed in the decoder for emphasizing on filling in unknown pixels instead of reconstructing all pixels. Motivated by that the filling-in order is crucial to inpainting results and largely depends on image structures in exemplar-based methods, we further suggest a multi-scale edge completion network to predict coherent edges. Our Edge-LBAM method contains dual procedures,including structure-aware mask-updating guided by predict edges and attention maps generated by masks for feature re-normalization.Extensive experiments show that our Edge-LBAM is effective in generating coherent image structures and preventing color discrepancy and blurriness, and performs favorably against the state-of-the-art methods in terms of qualitative metrics and visual quality.
Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to the domain (sensitive attribute) for which labels are provided, while being informative over all other image attributes, which are unlabeled. We present a new approach, proposing a new domain-wise contrastive objective for ensuring invariant representations. This objective crucially restricts negative image pairs to be drawn from the same domain, which enforces domain invariance whereas the standard contrastive objective does not. This domain-wise objective is insufficient on its own as it suffers from shortcut solutions resulting in feature suppression. We overcome this issue by a combination of a reconstruction constraint, image augmentations and initialization with pre-trained weights. Our analysis shows that the choice of augmentations is important, and that a misguided choice of augmentations can harm the invariance and informativeness objectives. In an extensive evaluation, our method convincingly outperforms the state-of-the-art in terms of representation invariance, representation informativeness, and training speed. Furthermore, we find that in some cases our method can achieve excellent results even without the reconstruction constraint, leading to a much faster and resource efficient training.
Autonomous scene exposure and exploration, especially in localization or communication-denied areas, useful for finding targets in unknown scenes, remains a challenging problem in computer navigation. In this work, we present a novel method for real-time environment exploration, whose only requirements are a visually similar dataset for pre-training, enough lighting in the scene, and an on-board forward-looking RGB camera for environmental sensing. As opposed to existing methods, our method requires only one look (image) to make a good tactical decision, and therefore works at a non-growing, constant time. Two direction predictions, characterized by pixels dubbed the Goto and Lookat pixels, comprise the core of our method. These pixels encode the recommended flight instructions in the following way: the Goto pixel defines the direction in which the agent should move by one distance unit, and the Lookat pixel defines the direction in which the camera should be pointing at in the next step. These flying-instruction pixels are optimized to expose the largest amount of currently unexplored areas. Our method presents a novel deep learning-based navigation approach that is able to solve this problem and demonstrate its ability in an even more complicated setup, i.e., when computational power is limited. In addition, we propose a way to generate a navigation-oriented dataset, enabling efficient training of our method using RGB and depth images. Tests conducted in a simulator evaluating both the sparse pixels' coordinations inferring process, and 2D and 3D test flights aimed to unveil areas and decrease distances to targets achieve promising results. Comparison against a state-of-the-art algorithm shows our method is able to overperform it, that while measuring the new voxels per camera pose, minimum distance to target, percentage of surface voxels seen, and compute time metrics.