Table-to-Text has been traditionally approached as a linear language to text problem. However, visually represented tables are rich in visual information and serve as a concise, effective form of representing data and its relationships. When using text-based approaches, after the linearization process, this information is either lost or represented in a space inefficient manner. This inefficiency has remained a constant challenge for text-based approaches making them struggle with large tables. In this paper, we demonstrate that image representation of tables are more space-efficient than the typical textual linearizations, and multi-modal approaches are competitive in Table-to-Text tasks. We present PixT3, a multimodal table-to-text model that outperforms the state-of-the-art (SotA) in the ToTTo benchmark in a pure Table-to-Text setting while remaining competitive in controlled Table-to-Text scenarios. It also generalizes better in unseen datasets, outperforming ToTTo SotA in all generation settings. Additionally, we introduce a new intermediate training curriculum to reinforce table structural awareness, leading to improved generation and overall faithfulness of the models.
Accurate and robust pose estimation plays a crucial role in many robotic systems. Popular algorithms for pose estimation typically rely on high-fidelity and high-frequency signals from various sensors. Inclusion of these sensors makes the system less affordable and much more complicated. In this work we introduce a novel approach for the robotic odometry which only requires a single camera and, importantly, can produce reliable estimates given even extremely low-frequency signal of around one frame per second. The approach is based on matching image features between the consecutive frames of the video stream using deep feature matching models. The resulting coarse estimate is then adjusted by a convolutional neural network, which is also responsible for estimating the scale of the transition, otherwise irretrievable using only the feature matching information. We evaluate the performance of the approach in the AISG-SLA Visual Localisation Challenge and find that while being computationally efficient and easy to implement our method shows competitive results with only around $3^{\circ}$ of orientation estimation error and $2m$ of translation estimation error taking the third place in the challenge.
We introduce an improved solution to the neural image-based rendering problem in computer vision. Given a set of images taken from a freely moving camera at train time, the proposed approach could synthesize a realistic image of the scene from a novel viewpoint at test time. The key ideas presented in this paper are (i) Recovering accurate camera parameters via a robust pipeline from unposed day-to-day images is equally crucial in neural novel view synthesis problem; (ii) It is rather more practical to model object's content at different resolutions since dramatic camera motion is highly likely in day-to-day unposed images. To incorporate the key ideas, we leverage the fundamentals of scene rigidity, multi-scale neural scene representation, and single-image depth prediction. Concretely, the proposed approach makes the camera parameters as learnable in a neural fields-based modeling framework. By assuming per view depth prediction is given up to scale, we constrain the relative pose between successive frames. From the relative poses, absolute camera pose estimation is modeled via a graph-neural network-based multiple motion averaging within the multi-scale neural-fields network, leading to a single loss function. Optimizing the introduced loss function provides camera intrinsic, extrinsic, and image rendering from unposed images. We demonstrate, with examples, that for a unified framework to accurately model multiscale neural scene representation from day-to-day acquired unposed multi-view images, it is equally essential to have precise camera-pose estimates within the scene representation framework. Without considering robustness measures in the camera pose estimation pipeline, modeling for multi-scale aliasing artifacts can be counterproductive. We present extensive experiments on several benchmark datasets to demonstrate the suitability of our approach.
Spiking neural networks (SNNs) have demonstrated the capability to achieve comparable performance to deep neural networks (DNNs) in both visual and linguistic domains while offering the advantages of improved energy efficiency and adherence to biological plausibility. However, the extension of such single-modality SNNs into the realm of multimodal scenarios remains an unexplored territory. Drawing inspiration from the concept of contrastive language-image pre-training (CLIP), we introduce a novel framework, named SpikeCLIP, to address the gap between two modalities within the context of spike-based computing through a two-step recipe involving ``Alignment Pre-training + Dual-Loss Fine-tuning". Extensive experiments demonstrate that SNNs achieve comparable results to their DNN counterparts while significantly reducing energy consumption across a variety of datasets commonly used for multimodal model evaluation. Furthermore, SpikeCLIP maintains robust performance in image classification tasks that involve class labels not predefined within specific categories.
Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts describing complex scenes with multiple objects. While excelling in generating images from short, single-object descriptions, these models often struggle to faithfully capture all the nuanced details within longer and more elaborate textual inputs. In response, we present a novel approach leveraging Large Language Models (LLMs) to extract critical components from text prompts, including bounding box coordinates for foreground objects, detailed textual descriptions for individual objects, and a succinct background context. These components form the foundation of our layout-to-image generation model, which operates in two phases. The initial Global Scene Generation utilizes object layouts and background context to create an initial scene but often falls short in faithfully representing object characteristics as specified in the prompts. To address this limitation, we introduce an Iterative Refinement Scheme that iteratively evaluates and refines box-level content to align them with their textual descriptions, recomposing objects as needed to ensure consistency. Our evaluation on complex prompts featuring multiple objects demonstrates a substantial improvement in recall compared to baseline diffusion models. This is further validated by a user study, underscoring the efficacy of our approach in generating coherent and detailed scenes from intricate textual inputs.
Medical imaging data is often siloed within hospitals, limiting the amount of data available for specialized model development. With limited in-domain data, one might hope to leverage larger datasets from related domains. In this paper, we analyze the benefit of transferring self-supervised contrastive representations from moment contrast (MoCo) pretraining on out-of-distribution data to settings with limited data. We consider two X-ray datasets which image different parts of the body, and compare transferring from each other to transferring from ImageNet. We find that depending on quantity of labeled and unlabeled data, contrastive pretraining on larger out-of-distribution datasets can perform nearly as well or better than MoCo pretraining in-domain, and pretraining on related domains leads to higher performance than if one were to use the ImageNet pretrained weights. Finally, we provide a preliminary way of quantifying similarity between datasets.
Human fingerprints serve as one unique and powerful characteristic for each person, from which policemen can recognize the identity. Similar to humans, many natural bodies and intrinsic mechanical qualities can also be uniquely identified from surface characteristics. To measure the elasto-plastic properties of one material, one formally sharp indenter is pushed into the measured body under constant force and retracted, leaving a unique residual imprint of the minute size from several micrometers to nanometers. However, one great challenge is how to map the optical image of this residual imprint into the real wanted mechanical properties, i.e., the tensile force curve. In this paper, we propose a novel method to use multi-fidelity neural networks (MFNN) to solve this inverse problem. We first actively train the NN model via pure simulation data, and then bridge the sim-to-real gap via transfer learning. The most innovative part is that we use NN to dig out the unknown physics and also implant the known physics into the transfer learning framework, thus highly improving the model stability and decreasing the data requirement. This work serves as one great example of applying machine learning into the real experimental research, especially under the constraints of data limitation and fidelity variance.
Analysis of the 3D Texture is indispensable for various tasks, such as retrieval, segmentation, classification, and inspection of sculptures, knitted fabrics, and biological tissues. A 3D texture is a locally repeated surface variation independent of the surface's overall shape and can be determined using the local neighborhood and its characteristics. Existing techniques typically employ computer vision techniques that analyze a 3D mesh globally, derive features, and then utilize the obtained features for retrieval or classification. Several traditional and learning-based methods exist in the literature, however, only a few are on 3D texture, and nothing yet, to the best of our knowledge, on the unsupervised schemes. This paper presents an original framework for the unsupervised segmentation of the 3D texture on the mesh manifold. We approach this problem as binary surface segmentation, partitioning the mesh surface into textured and non-textured regions without prior annotation. We devise a mutual transformer-based system comprising a label generator and a cleaner. The two models take geometric image representations of the surface mesh facets and label them as texture or non-texture across an iterative mutual learning scheme. Extensive experiments on three publicly available datasets with diverse texture patterns demonstrate that the proposed framework outperforms standard and SOTA unsupervised techniques and competes reasonably with supervised methods.
With the increasing use of deep learning on data collected by non-perfect sensors and in non-perfect environments, the robustness of deep learning systems has become an important issue. A common approach for obtaining robustness to noise has been to train deep learning systems with data augmented with Gaussian noise. In this work, we challenge the common choice of Gaussian noise and explore the possibility of stronger robustness for non-Gaussian impulsive noise, specifically alpha-stable noise. Justified by the Generalized Central Limit Theorem and evidenced by observations in various application areas, alpha-stable noise is widely present in nature. By comparing the testing accuracy of models trained with Gaussian noise and alpha-stable noise on data corrupted by different noise, we find that training with alpha-stable noise is more effective than Gaussian noise, especially when the dataset is corrupted by impulsive noise, thus improving the robustness of the model. The generality of this conclusion is validated through experiments conducted on various deep learning models with image and time series datasets, and other benchmark corrupted datasets. Consequently, we propose a novel data augmentation method that replaces Gaussian noise, which is typically added to the training data, with alpha-stable noise.
The rapid advancement of artificial intelligence (AI) has been marked by the large language models exhibiting human-like intelligence. However, these models also present unprecedented challenges to energy consumption and environmental sustainability. One promising solution is to revisit analogue computing, a technique that predates digital computing and exploits emerging analogue electronic devices, such as resistive memory, which features in-memory computing, high scalability, and nonvolatility. However, analogue computing still faces the same challenges as before: programming nonidealities and expensive programming due to the underlying devices physics. Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network. Software-wise, the topology of a randomly weighted neural network is optimized by pruning connections rather than precisely tuning resistive memory weights. Hardware-wise, we reveal the physical origin of the programming stochasticity using transmission electron microscopy, which is leveraged for large-scale and low-cost implementation of an overparameterized random neural network containing high-performance sub-networks. We implemented the co-design on a 40nm 256K resistive memory macro, observing 17.3% and 19.9% accuracy improvements in image and audio classification on FashionMNIST and Spoken digits datasets, as well as 9.8% (2%) improvement in PR (ROC) in image segmentation on DRIVE datasets, respectively. This is accompanied by 82.1%, 51.2%, and 99.8% improvement in energy efficiency thanks to analogue in-memory computing. By embracing the intrinsic stochasticity and in-memory computing, this work may solve the biggest obstacle of analogue computing systems and thus unleash their immense potential for next-generation AI hardware.