David Lowe

Rui Xu, Mengya Hu, Deren Lei et al.

The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages advanced neural network architectures and training strategies to embed imperceptible yet highly robust watermarks. InvisMark achieves state-of-the-art performance in imperceptibility (PSNR$\sim$51, SSIM $\sim$ 0.998) while maintaining over 97\% bit accuracy across various image manipulations. Notably, we demonstrate the successful encoding of 256-bit watermarks, significantly expanding payload capacity while preserving image quality. This enables the embedding of UUIDs with error correction codes, achieving near-perfect decoding success rates even under challenging image distortions. We also address potential vulnerabilities against advanced attacks and propose mitigation strategies. By combining high imperceptibility, extended payload capacity, and resilience to manipulations, InvisMark provides a robust foundation for ensuring media provenance in an era of increasingly sophisticated AI-generated content. Source code of this paper is available at: https://github.com/microsoft/InvisMark.

Gabriele Pergola, Yulan He, David Lowe

Making sense of words often requires to simultaneously examine the surrounding context of a term as well as the global themes characterizing the overall corpus. Several topic models have already exploited word embeddings to recognize local context, however, it has been weakly combined with the global context during the topic inference. This paper proposes to extract topical phrases corroborating the word embedding information with the global context detected by Latent Semantic Analysis, and then combine them by means of the Pólya urn model. To highlight the effectiveness of this combined approach the model was assessed analyzing clinical reports, a challenging scenario characterized by technical jargon and a limited word statistics available. Results show it outperforms the state-of-the-art approaches in terms of both topic coherence and computational cost.

Hang Qi, Matthew Brown, David G. Lowe

Human vision is able to immediately recognize novel visual categories after seeing just one or a few training examples. We describe how to add a similar capability to ConvNet classifiers by directly setting the final layer weights from novel training examples during low-shot learning. We call this process weight imprinting as it directly sets weights for a new category based on an appropriately scaled copy of the embedding layer activations for that training example. The imprinting process provides a valuable complement to training with stochastic gradient descent, as it provides immediate good classification performance and an initialization for any further fine-tuning in the future. We show how this imprinting process is related to proxy-based embeddings. However, it differs in that only a single imprinted weight vector is learned for each novel category, rather than relying on a nearest-neighbor distance to training instances as typically used with embedding methods. Our experiments show that using averaging of imprinted weights provides better generalization than using nearest-neighbor instance embeddings.

Tinghui Zhou, Matthew Brown, Noah Snavely et al.

We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. We achieve this by simultaneously training depth and camera pose estimation networks using the task of view synthesis as the supervisory signal. The networks are thus coupled via the view synthesis objective during training, but can be applied independently at test time. Empirical evaluation on the KITTI dataset demonstrates the effectiveness of our approach: 1) monocular depth performing comparably with supervised methods that use either ground-truth pose or depth for training, and 2) pose estimation performing favorably with established SLAM systems under comparable input settings.

Iain Rice, Roger Benton, Les Hart et al.

This paper considers the problem of low-dimensional visualisation of very high dimensional information sources for the purpose of situation awareness in the maritime environment. In response to the requirement for human decision support aids to reduce information overload (and specifically, data amenable to inter-point relative similarity measures) appropriate to the below-water maritime domain, we are investigating a preliminary prototype topographic visualisation model. The focus of the current paper is on the mathematical problem of exploiting a relative dissimilarity representation of signals in a visual informatics mapping model, driven by real-world sonar systems. An independent source model is used to analyse the sonar beams from which a simple probabilistic input model to represent uncertainty is mapped to a latent visualisation space where data uncertainty can be accommodated. The use of euclidean and non-euclidean measures are used and the motivation for future use of non-euclidean measures is made. Concepts are illustrated using a simulated 64 beam weak SNR dataset with realistic sonar targets.

Kenji Okuma, David G. Lowe, James J. Little

This paper introduces a novel self-learning framework that automates the label acquisition process for improving models for detecting players in broadcast footage of sports games. Unlike most previous self-learning approaches for improving appearance-based object detectors from videos, we allow an unknown, unconstrained number of target objects in a more generalized video sequence with non-static camera views. Our self-learning approach uses a latent SVM learning algorithm and deformable part models to represent the shape and colour information of players, constraining their motions, and learns the colour of the playing field by a gentle Adaboost algorithm. We combine those image cues and discover additional labels automatically from unlabelled data. In our experiments, our approach exploits both labelled and unlabelled data in sparsely labelled videos of sports games, providing a mean performance improvement of over 20% in the average precision for detecting sports players and improved tracking, when videos contain very few labelled images.