Learning to Localize in Unseen Scenes with Relative Pose Regressors

Relative pose regressors (RPRs) localize a camera by estimating its relative translation and rotation to a pose-labelled reference. Unlike scene coordinate regression and absolute pose regression methods, which learn absolute scene parameters, RPRs can (theoretically) localize in unseen environments, since they only learn the residual pose between camera pairs. In practice, however, the performance of RPRs is significantly degraded in unseen scenes. In this work, we propose to aggregate paired feature maps into latent codes, instead of operating on global image descriptors, in order to improve the generalization of RPRs. We implement aggregation with concatenation, projection, and attention operations (Transformer Encoders) and learn to regress the relative pose parameters from the resulting latent codes. We further make use of a recently proposed continuous representation of rotation matrices, which alleviates the limitations of the commonly used quaternions. Compared to state-of-the-art RPRs, our model is shown to localize significantly better in unseen environments, across both indoor and outdoor benchmarks, while maintaining competitive performance in seen scenes. We validate our findings and architecture design through multiple ablations. Our code and pretrained models is publicly available.

Continuous-Time Gaussian Process Motion-Compensation for Event-vision Pattern Tracking with Distance Fields

This work addresses the issue of motion compensation and pattern tracking in event camera data. An event camera generates asynchronous streams of events triggered independently by each of the pixels upon changes in the observed intensity. Providing great advantages in low-light and rapid-motion scenarios, such unconventional data present significant research challenges as traditional vision algorithms are not directly applicable to this sensing modality. The proposed method decomposes the tracking problem into a local SE(2) motion-compensation step followed by a homography registration of small motion-compensated event batches. The first component relies on Gaussian Process (GP) theory to model the continuous occupancy field of the events in the image plane and embed the camera trajectory in the covariance kernel function. In doing so, estimating the trajectory is done similarly to GP hyperparameter learning by maximising the log marginal likelihood of the data. The continuous occupancy fields are turned into distance fields and used as templates for homography-based registration. By benchmarking the proposed method against other state-of-the-art techniques, we show that our open-source implementation performs high-accuracy motion compensation and produces high-quality tracks in real-world scenarios.

TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets

Diffusion models have achieved great success in a range of tasks, such as image synthesis and molecule design. As such successes hinge on large-scale training data collected from diverse sources, the trustworthiness of these collected data is hard to control or audit. In this work, we aim to explore the vulnerabilities of diffusion models under potential training data manipulations and try to answer: How hard is it to perform Trojan attacks on well-trained diffusion models? What are the adversarial targets that such Trojan attacks can achieve? To answer these questions, we propose an effective Trojan attack against diffusion models, TrojDiff, which optimizes the Trojan diffusion and generative processes during training. In particular, we design novel transitions during the Trojan diffusion process to diffuse adversarial targets into a biased Gaussian distribution and propose a new parameterization of the Trojan generative process that leads to an effective training objective for the attack. In addition, we consider three types of adversarial targets: the Trojaned diffusion models will always output instances belonging to a certain class from the in-domain distribution (In-D2D attack), out-of-domain distribution (Out-D2D-attack), and one specific instance (D2I attack). We evaluate TrojDiff on CIFAR-10 and CelebA datasets against both DDPM and DDIM diffusion models. We show that TrojDiff always achieves high attack performance under different adversarial targets using different types of triggers, while the performance in benign environments is preserved. The code is available at https://github.com/chenweixin107/TrojDiff.

Deep-MDS Framework for Recovering the 3D Shape of 2D Landmarks from a Single Image

In this paper, a low parameter deep learning framework utilizing the Non-metric Multi-Dimensional scaling (NMDS) method, is proposed to recover the 3D shape of 2D landmarks on a human face, in a single input image. Hence, NMDS approach is used for the first time to establish a mapping from a 2D landmark space to the corresponding 3D shape space. A deep neural network learns the pairwise dissimilarity among 2D landmarks, used by NMDS approach, whose objective is to learn the pairwise 3D Euclidean distance of the corresponding 2D landmarks on the input image. This scheme results in a symmetric dissimilarity matrix, with the rank larger than 2, leading the NMDS approach toward appropriately recovering the 3D shape of corresponding 2D landmarks. In the case of posed images and complex image formation processes like perspective projection which causes occlusion in the input image, we consider an autoencoder component in the proposed framework, as an occlusion removal part, which turns different input views of the human face into a profile view. The results of a performance evaluation using different synthetic and real-world human face datasets, including Besel Face Model (BFM), CelebA, CoMA - FLAME, and CASIA-3D, indicates the comparable performance of the proposed framework, despite its small number of training parameters, with the related state-of-the-art and powerful 3D reconstruction methods from the literature, in terms of efficiency and accuracy.

Benchmarking performance of object detection under image distortions in an uncontrolled environment

The robustness of object detection algorithms plays a prominent role in real-world applications, especially in uncontrolled environments due to distortions during image acquisition. It has been proven that the performance of object detection methods suffers from in-capture distortions. In this study, we present a performance evaluation framework for the state-of-the-art object detection methods using a dedicated dataset containing images with various distortions at different levels of severity. Furthermore, we propose an original strategy of image distortion generation applied to the MS-COCO dataset that combines some local and global distortions to reach much better performances. We have shown that training using the proposed dataset improves the robustness of object detection by 31.5\%. Finally, we provide a custom dataset including natural images distorted from MS-COCO to perform a more reliable evaluation of the robustness against common distortions. The database and the generation source codes of the different distortions are made publicly available

SF2Former: Amyotrophic Lateral Sclerosis Identification From Multi-center MRI Data Using Spatial and Frequency Fusion Transformer

Amyotrophic Lateral Sclerosis (ALS) is a complex neurodegenerative disorder involving motor neuron degeneration. Significant research has begun to establish brain magnetic resonance imaging (MRI) as a potential biomarker to diagnose and monitor the state of the disease. Deep learning has turned into a prominent class of machine learning programs in computer vision and has been successfully employed to solve diverse medical image analysis tasks. However, deep learning-based methods applied to neuroimaging have not achieved superior performance in ALS patients classification from healthy controls due to having insignificant structural changes correlated with pathological features. Therefore, the critical challenge in deep models is to determine useful discriminative features with limited training data. By exploiting the long-range relationship of image features, this study introduces a framework named SF2Former that leverages vision transformer architecture's power to distinguish the ALS subjects from the control group. To further improve the network's performance, spatial and frequency domain information are combined because MRI scans are captured in the frequency domain before being converted to the spatial domain. The proposed framework is trained with a set of consecutive coronal 2D slices, which uses the pre-trained weights on ImageNet by leveraging transfer learning. Finally, a majority voting scheme has been employed to those coronal slices of a particular subject to produce the final classification decision. Our proposed architecture has been thoroughly assessed with multi-modal neuroimaging data using two well-organized versions of the Canadian ALS Neuroimaging Consortium (CALSNIC) multi-center datasets. The experimental results demonstrate the superiority of our proposed strategy in terms of classification accuracy compared with several popular deep learning-based techniques.

Criminal Investigation Tracker with Suspect Prediction using Machine Learning

An automated approach to identifying offenders in Sri Lanka would be better than the current system. Obtaining information from eyewitnesses is one of the less reliable approaches and procedures still in use today. Automated criminal identification has the ability to save lives, notwithstanding Sri Lankan culture's lack of awareness of the issue. Using cutting-edge technology like biometrics to finish this task would be the most accurate strategy. The most notable outcomes will be obtained by applying fingerprint and face recognition as biometric techniques. The main responsibilities will be image optimization and criminality. CCTV footage may be used to identify a person's fingerprint, identify a person's face, and identify crimes involving weapons. Additionally, we unveil a notification system and condense the police report to Additionally, to make it simpler for police officers to understand the essential points of the crime, we develop a notification system and condense the police report. Additionally, if an incident involving a weapon is detected, an automated notice of the crime with all the relevant facts is sent to the closest police station. The summarization of the police report is what makes this the most original. In order to improve the efficacy of the overall image, the system will quickly and precisely identify the full crime scene, identify, and recognize the suspects using their faces and fingerprints, and detect firearms. This study provides a novel approach for crime prediction based on real-world data, and criminality incorporation. A crime or occurrence should be reported to the appropriate agencies, and the suggested web application should be improved further to offer a workable channel of communication.

Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting

This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting. Many approaches achieve alpha mattes with complex encoders to extract robust semantics, then resort to the U-net-like decoder to concatenate or fuse encoder features. However, image matting is essentially a pixel-wise regression, and the ideal situation is to perceive the maximum opacity correspondence from the input image. In this paper, we argue that the high-resolution feature representation, perception and communication are more crucial for matting accuracy. Therefore, we propose an Intensive Integration and Global Foreground Perception network (I2GFP) to integrate wider and higher feature streams. Wider means we combine intensive features in each decoder stage, while higher suggests we retain high-resolution intermediate features and perceive large-scale foreground appearance. Our motivation sacrifices model depth for a significant performance promotion. We perform extensive experiments to prove the proposed I2GFP model, and state-of-the-art results can be achieved on different public datasets.

ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval

Diffusion models show promising generation capability for a variety of data. Despite their high generation quality, the inference for diffusion models is still time-consuming due to the numerous sampling iterations required. To accelerate the inference, we propose ReDi, a simple yet learning-free Retrieval-based Diffusion sampling framework. From a precomputed knowledge base, ReDi retrieves a trajectory similar to the partially generated trajectory at an early stage of generation, skips a large portion of intermediate steps, and continues sampling from a later step in the retrieved trajectory. We theoretically prove that the generation performance of ReDi is guaranteed. Our experiments demonstrate that ReDi improves the model inference efficiency by 2x speedup. Furthermore, ReDi is able to generalize well in zero-shot cross-domain image generation such as image stylization.

MetaDIP: Accelerating Deep Image Prior with Meta Learning

Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network. Unlike pretrained feedforward neural networks, the same DIP can generalize to arbitrary inverse problems, from denoising to phase retrieval, while offering competitive performance at each task. The central disadvantage of DIP is that, while feedforward neural networks can reconstruct an image in a single pass, DIP must gradually update its weights over hundreds to thousands of iterations, at a significant computational cost. In this work we use meta-learning to massively accelerate DIP-based reconstructions. By learning a proper initialization for the DIP weights, we demonstrate a 10x improvement in runtimes across a range of inverse imaging tasks. Moreover, we demonstrate that a network trained to quickly reconstruct faces also generalizes to reconstructing natural image patches.