Multi-object tracking (MOT) is a crucial component of situational awareness in military defense applications. With the growing use of unmanned aerial systems (UASs), MOT methods for aerial surveillance is in high demand. Application of MOT in UAS presents specific challenges such as moving sensor, changing zoom levels, dynamic background, illumination changes, obscurations and small objects. In this work, we present a robust object tracking architecture aimed to accommodate for the noise in real-time situations. We propose a kinematic prediction model, called Deep Extended Kalman Filter (DeepEKF), in which a sequence-to-sequence architecture is used to predict entity trajectories in latent space. DeepEKF utilizes a learned image embedding along with an attention mechanism trained to weight the importance of areas in an image to predict future states. For the visual scoring, we experiment with different similarity measures to calculate distance based on entity appearances, including a convolutional neural network (CNN) encoder, pre-trained using Siamese networks. In initial evaluation experiments, we show that our method, combining scoring structure of the kinematic and visual models within a MHT framework, has improved performance especially in edge cases where entity motion is unpredictable, or the data presents frames with significant gaps.
A plethora of attack methods have been proposed to generate adversarial examples, among which the iterative methods have been demonstrated the ability to find a strong attack. However, the computation of an adversarial perturbation for a new data point requires solving a time-consuming optimization problem from scratch. To generate a stronger attack, it normally requires updating a data point with more iterations. In this paper, we show the existence of a meta adversarial perturbation (MAP), a better initialization that causes natural images to be misclassified with high probability after being updated through only a one-step gradient ascent update, and propose an algorithm for computing such perturbations. We conduct extensive experiments, and the empirical results demonstrate that state-of-the-art deep neural networks are vulnerable to meta perturbations. We further show that these perturbations are not only image-agnostic, but also model-agnostic, as a single perturbation generalizes well across unseen data points and different neural network architectures.
This paper presents a Transformer architecture for volumetric medical image segmentation. Designing a computationally efficient Transformer architecture for volumetric segmentation is a challenging task. It requires keeping a complex balance in encoding local and global spatial cues, and preserving information along all axes of the volumetric data. The proposed volumetric Transformer has a U-shaped encoder-decoder design that processes the input voxels in their entirety. Our encoder has two consecutive self-attention layers to simultaneously encode local and global cues, and our decoder has novel parallel shifted window based self and cross attention blocks to capture fine details for boundary refinement by subsuming Fourier position encoding. Our proposed design choices result in a computationally efficient architecture, which demonstrates promising results on Brain Tumor Segmentation (BraTS) 2021, and Medical Segmentation Decathlon (Pancreas and Liver) datasets for tumor segmentation. We further show that the representations learned by our model transfer better across-datasets and are robust against data corruptions. \href{https://github.com/himashi92/VT-UNet}{Our code implementation is publicly available}.
Polyps represent an early sign of the development of Colorectal Cancer. The standard procedure for their detection consists of colonoscopic examination of the gastrointestinal tract. However, the wide range of polyp shapes and visual appearances, as well as the reduced quality of this image modality, turn their automatic identification and segmentation with computational tools into a challenging computer vision task. In this work, we present a new strategy for the delineation of gastrointestinal polyps from endoscopic images based on a direct extension of common encoder-decoder networks for semantic segmentation. In our approach, two pretrained encoder-decoder networks are sequentially stacked: the second network takes as input the concatenation of the original frame and the initial prediction generated by the first network, which acts as an attention mechanism enabling the second network to focus on interesting areas within the image, thereby improving the quality of its predictions. Quantitative evaluation carried out on several polyp segmentation databases shows that double encoder-decoder networks clearly outperform their single encoder-decoder counterparts in all cases. In addition, our best double encoder-decoder combination attains excellent segmentation accuracy and reaches state-of-the-art performance results in all the considered datasets, with a remarkable boost of accuracy on images extracted from datasets not used for training.
For a globally recognized planting breeding organization, manually-recorded field observation data is crucial for plant breeding decision making. However, certain phenotypic traits such as plant color, height, kernel counts, etc. can only be collected during a specific time-window of a crop's growth cycle. Due to labor-intensive requirements, only a small subset of possible field observations are recorded each season. To help mitigate this data collection bottleneck in wheat breeding, we propose a novel deep learning framework to accurately and efficiently count wheat heads to aid in the gathering of real-time data for decision making. We call our model WheatNet and show that our approach is robust and accurate for a wide range of environmental conditions of the wheat field. WheatNet uses a truncated MobileNetV2 as a lightweight backbone feature extractor which merges feature maps with different scales to counter image scale variations. Then, extracted multi-scale features go to two parallel sub-networks for simultaneous density-based counting and localization tasks. Our proposed method achieves an MAE and RMSE of 3.85 and 5.19 in our wheat head counting task, respectively, while having significantly fewer parameters when compared to other state-of-the-art methods. Our experiments and comparisons with other state-of-the-art methods demonstrate the superiority and effectiveness of our proposed method.
Many existing neural architecture search (NAS) solutions rely on downstream training for architecture evaluation, which takes enormous computations. Considering that these computations bring a large carbon footprint, this paper aims to explore a green (namely environmental-friendly) NAS solution that evaluates architectures without training. Intuitively, gradients, induced by the architecture itself, directly decide the convergence and generalization results. It motivates us to propose the gradient kernel hypothesis: Gradients can be used as a coarse-grained proxy of downstream training to evaluate random-initialized networks. To support the hypothesis, we conduct a theoretical analysis and find a practical gradient kernel that has good correlations with training loss and validation performance. According to this hypothesis, we propose a new kernel based architecture search approach KNAS. Experiments show that KNAS achieves competitive results with orders of magnitude faster than "train-then-test" paradigms on image classification tasks. Furthermore, the extremely low search cost enables its wide applications. The searched network also outperforms strong baseline RoBERTA-large on two text classification tasks. Codes are available at \url{https://github.com/Jingjing-NLP/KNAS} .
Deep learning based methods hold state-of-the-art results in low-level image processing tasks, but remain difficult to interpret due to their black-box construction. Unrolled optimization networks present an interpretable alternative to constructing deep neural networks by deriving their architecture from classical iterative optimization methods without use of tricks from the standard deep learning tool-box. So far, such methods have demonstrated performance close to that of state-of-the-art models while using their interpretable construction to achieve a comparably low learned parameter count. In this work, we propose an unrolled convolutional dictionary learning network (CDLNet) and demonstrate its competitive denoising and joint denoising and demosaicing (JDD) performance both in low and high parameter count regimes. Specifically, we show that the proposed model outperforms state-of-the-art fully convolutional denoising and JDD models when scaled to a similar parameter count. In addition, we leverage the model's interpretable construction to propose a noise-adaptive parameterization of thresholds in the network that enables state-of-the-art blind denoising performance, and near perfect generalization on noise-levels unseen during training. Furthermore, we show that such performance extends to the JDD task and unsupervised learning.
Fairness in decision-making has been a long-standing issue in our society. Despite the increasing number of research activities on unfairness mitigation in machine learning models, there is little research focusing on mitigating unfairness in human decisions. Fairness in human decisions is as important as, if not more important than, fairness in machine learning models since there are processes where humans make the final decisions and machine learning models can inherit bias from the human decisions they were trained on. As a result, this work aims to detect unfairness in human decisions, the very first step of solving the unfair human decision problem. This paper proposes to utilize the existing machine learning fairness detection mechanisms to detect unfairness in human decisions. The rationale behind this is, while it is difficult to directly test whether a human makes unfair decisions, with current research on machine learning fairness, it is now easy to test, on a large scale at a low cost, whether a machine learning model is unfair. By synthesizing unfair labels on four general machine learning fairness datasets and one image processing dataset, this paper shows that the proposed approach is able to detect (1) whether or not unfair labels exist in the training data and (2) the degree and direction of the unfairness. We believe that this work demonstrates the potential of utilizing machine learning fairness to detect human decision fairness. Following this work, research can be conducted on (1) preventing future unfair decisions, (2) fixing prior unfair decisions, and (3) training a fairer machine learning model.
Recent studies have shown that convolutional neural networks (CNNs) are not the only feasible solution for image classification. Furthermore, weight sharing and backpropagation used in CNNs do not correspond to the mechanisms present in the primate visual system. To propose a more biologically plausible solution, we designed a locally connected spiking neural network (SNN) trained using spike-timing-dependent plasticity (STDP) and its reward-modulated variant (R-STDP) learning rules. The use of spiking neurons and local connections along with reinforcement learning (RL) led us to the nomenclature BioLCNet for our proposed architecture. Our network consists of a rate-coded input layer followed by a locally connected hidden layer and a decoding output layer. A spike population-based voting scheme is adopted for decoding in the output layer. We used the MNIST dataset to obtain image classification accuracy and to assess the robustness of our rewarding system to varying target responses.
Rain removal plays an important role in the restoration of degraded images. Recently, data-driven methods have achieved remarkable success. However, these approaches neglect that the appearance of rain is often accompanied by low light conditions, which will further degrade the image quality. Therefore, it is very indispensable to jointly remove the rain and enhance the light for real-world rain image restoration. In this paper, we aim to address this problem from two aspects. First, we proposed a novel entangled network, namely EMNet, which can remove the rain and enhance illumination in one go. Specifically, two encoder-decoder networks interact complementary information through entanglement structure, and parallel rain removal and illumination enhancement. Considering that the encoder-decoder structure is unreliable in preserving spatial details, we employ a detail recovery network to restore the desired fine texture. Second, we present a new synthetic dataset, namely DarkRain, to boost the development of rain image restoration algorithms in practical scenarios. DarkRain not only contains different degrees of rain, but also considers different lighting conditions, and more realistically simulates the rainfall in the real world. EMNet is extensively evaluated on the proposed benchmark and achieves state-of-the-art results. In addition, after a simple transformation, our method outshines existing methods in both rain removal and low-light image enhancement. The source code and dataset will be made publicly available later.