Unlike other data modalities such as text and vision, speech does not lend itself to easy interpretation. While lay people can understand how to describe an image or sentence via perception, non-expert descriptions of speech often end at high-level demographic information, such as gender or age. In this paper, we propose a possible interpretable representation of speaker identity based on perceptual voice qualities (PQs). By adding gendered PQs to the pathology-focused Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) protocol, our PQ-based approach provides a perceptual latent space of the character of adult voices that is an intermediary of abstraction between high-level demographics and low-level acoustic, physical, or learned representations. Contrary to prior belief, we demonstrate that these PQs are hearable by ensembles of non-experts, and further demonstrate that the information encoded in a PQ-based representation is predictable by various speech representations.
Cephalometric landmark detection on lateral skull X-ray images plays a crucial role in the diagnosis of certain dental diseases. Accurate and effective identification of these landmarks presents a significant challenge. Based on extensive data observations and quantitative analyses, we discovered that visual features from different receptive fields affect the detection accuracy of various landmarks differently. As a result, we employed an image pyramid structure, integrating multiple resolutions as input to train a series of models with different receptive fields, aiming to achieve the optimal feature combination for each landmark. Moreover, we applied several data augmentation techniques during training to enhance the model's robustness across various devices and measurement alternatives. We implemented this method in the Cephalometric Landmark Detection in Lateral X-ray Images 2023 Challenge and achieved a Mean Radial Error (MRE) of 1.62 mm and a Success Detection Rate (SDR) 2.0mm of 74.18% in the final testing phase.
Federated Averaging, and many federated learning algorithm variants which build upon it, have a limitation: all clients must share the same model architecture. This results in unused modeling capacity on many clients, which limits model performance. To address this issue, we propose a method that involves training a small model on the entire pool and a larger model on a subset of clients with higher capacity. The models exchange information bidirectionally via knowledge distillation, utilizing an unlabeled dataset on a server without sharing parameters. We present two variants of our method, which improve upon federated averaging on image classification and language modeling tasks. We show this technique can be useful even if only out-of-domain or limited in-domain distillation data is available. Additionally, the bi-directional knowledge distillation allows for domain transfer between the models when different pool populations introduce domain shift.
Text-to-Image generation (TTI) technologies are advancing rapidly, especially in the English language communities. However, English-native TTI models inherently carry biases from English world centric training data, which creates a dilemma for development of other language-native TTI models. One common choice is fine-tuning the English-native TTI model with translated samples from non-English communities. It falls short of fully addressing the model bias problem. Alternatively, training non-English language native models from scratch can effectively resolve the English world bias, but diverges from the English TTI communities, thus not able to utilize the strides continuously gaining in the English TTI communities any more. To build non-English language native TTI model meanwhile keep compatability with the English TTI communities, we propose a novel model structure referred as "Bridge Diffusion Model" (BDM). The proposed BDM employs a backbone-branch network structure to learn the non-English language semantics while keep the latent space compatible with the English-native TTI backbone, in an end-to-end manner. The unique advantages of the proposed BDM are that it's not only adept at generating images that precisely depict non-English language semantics, but also compatible with various English-native TTI plugins, such as different checkpoints, LoRA, ControlNet, Dreambooth, and Textual Inversion, etc. Moreover, BDM can concurrently generate content seamlessly combining both non-English native and English-native semantics within a single image, fostering cultural interaction. We verify our method by applying BDM to build a Chinese-native TTI model, whereas the method is generic and applicable to any other language.
Prior methods that tackle the problem of generalizable object pose estimation highly rely on having dense views of the unseen object. By contrast, we address the scenario where only a single reference view of the object is available. Our goal then is to estimate the relative object pose between this reference view and a query image that depicts the object in a different pose. In this scenario, robust generalization is imperative due to the presence of unseen objects during testing and the large-scale object pose variation between the reference and the query. To this end, we present a new hypothesis-and-verification framework, in which we generate and evaluate multiple pose hypotheses, ultimately selecting the most reliable one as the relative object pose. To measure reliability, we introduce a 3D-aware verification that explicitly applies 3D transformations to the 3D object representations learned from the two input images. Our comprehensive experiments on the Objaverse, LINEMOD, and CO3D datasets evidence the superior accuracy of our approach in relative pose estimation and its robustness in large-scale pose variations, when dealing with unseen objects.
In this paper, we propose a framework of building knowledgeable robot control in the scope of smart human-robot interaction, by empowering a basic uncalibrated visual servoing controller with contextual knowledge through the joint usage of event knowledge graphs (EKGs) and large-scale pretrained vision-language models (VLMs). The framework is expanded in twofold: first, we interpret low-level image geometry as high-level concepts, allowing us to prompt VLMs and to select geometric features of points and lines for motor control skills; then, we create an event knowledge graph (EKG) to conceptualize a robot manipulation task of interest, where the main body of the EKG is characterized by an executable behavior tree, and the leaves by semantic concepts relevant to the manipulation context. We demonstrate, in an uncalibrated environment with real robot trials, that our method lowers the reliance of human annotation during task interfacing, allows the robot to perform activities of daily living more easily by treating low-level geometric-based motor control skills as high-level concepts, and is beneficial in building cognitive thinking for smart robot applications.
Hyperspectral unmixing allows representing mixed pixels as a set of pure materials weighted by their abundances. Spectral features alone are often insufficient, so it is common to rely on other features of the scene. Matrix models become insufficient when the hyperspectral image (HSI) is represented as a high-order tensor with additional features in a multimodal, multifeature framework. Tensor models such as canonical polyadic decomposition allow for this kind of unmixing but lack a general framework and interpretability of the results. In this article, we propose an interpretable methodological framework for low-rank multifeature hyperspectral unmixing based on tensor decomposition (MultiHU-TD) that incorporates the abundance sum-to-one constraint in the alternating optimization alternating direction method of multipliers (ADMM) algorithm and provide in-depth mathematical, physical, and graphical interpretation and connections with the extended linear mixing model. As additional features, we propose to incorporate mathematical morphology and reframe a previous work on neighborhood patches within MultiHU-TD. Experiments on real HSIs showcase the interpretability of the model and the analysis of the results. Python and MATLAB implementations are made available on GitHub.
Mitotic figure detection in histology images is a hard-to-define, yet clinically significant task, where labels are generated with pathologist interpretations and where there is no ``gold-standard'' independent ground-truth. However, it is well-established that these interpretation based labels are often unreliable, in part, due to differences in expertise levels and human subjectivity. In this paper, our goal is to shed light on the inherent uncertainty of mitosis labels and characterize the mitotic figure classification task in a human interpretable manner. We train a probabilistic diffusion model to synthesize patches of cell nuclei for a given mitosis label condition. Using this model, we can then generate a sequence of synthetic images that correspond to the same nucleus transitioning into the mitotic state. This allows us to identify different image features associated with mitosis, such as cytoplasm granularity, nuclear density, nuclear irregularity and high contrast between the nucleus and the cell body. Our approach offers a new tool for pathologists to interpret and communicate the features driving the decision to recognize a mitotic figure.
Facade parsing stands as a pivotal computer vision task with far-reaching applications in areas like architecture, urban planning, and energy efficiency. Despite the recent success of deep learning-based methods in yielding impressive results on certain open-source datasets, their viability for real-world applications remains uncertain. Real-world scenarios are considerably more intricate, demanding greater computational efficiency. Existing datasets often fall short in representing these settings, and previous methods frequently rely on extra models to enhance accuracy, which requires much computation cost. In this paper, we introduce Comprehensive Facade Parsing (CFP), a dataset meticulously designed to encompass the intricacies of real-world facade parsing tasks. Comprising a total of 602 high-resolution street-view images, this dataset captures a diverse array of challenging scenarios, including sloping angles and densely clustered buildings, with painstakingly curated annotations for each image. We introduce a new pipeline known as Revision-based Transformer Facade Parsing (RTFP). This marks the pioneering utilization of Vision Transformers (ViT) in facade parsing, and our experimental results definitively substantiate its merit. We also design Line Acquisition, Filtering, and Revision (LAFR), an efficient yet accurate revision algorithm that can improve the segment result solely from simple line detection using prior knowledge of the facade. In ECP 2011, RueMonge 2014, and our CFP, we evaluate the superiority of our method.
Recent popularity of Large Language Models (LLMs) has opened countless possibilities in automating numerous AI tasks by connecting LLMs to various domain-specific models or APIs, where LLMs serve as dispatchers while domain-specific models or APIs are action executors. Despite the vast numbers of domain-specific models/APIs, they still struggle to comprehensively cover super diverse automation demands in the interaction between human and User Interfaces (UIs). In this work, we build a multimodal model to ground natural language instructions in given UI screenshots as a generic UI task automation executor. This metadata-free grounding model, consisting of a visual encoder and a language decoder, is first pretrained on well studied document understanding tasks and then learns to decode spatial information from UI screenshots in a promptable way. To facilitate the exploitation of image-to-text pretrained knowledge, we follow the pixel-to-sequence paradigm to predict geometric coordinates in a sequence of tokens using a language decoder. We further propose an innovative Reinforcement Learning (RL) based algorithm to supervise the tokens in such sequence jointly with visually semantic metrics, which effectively strengthens the spatial decoding capability of the pixel-to-sequence paradigm. Extensive experiments demonstrate our proposed reinforced UI instruction grounding model outperforms the state-of-the-art methods by a clear margin and shows the potential as a generic UI task automation API.