Deep learning in general focuses on training a neural network from large labeled datasets. Yet, in many cases there is value in training a network just from the input at hand. This may involve training a network from scratch using a single input or adapting an already trained network to a provided input example at inference time. This survey paper aims at covering deep internal-learning techniques that have been proposed in the past few years for these two important directions. While our main focus will be on image processing problems, most of the approaches that we survey are derived for general signals (vectors with recurring patterns that can be distinguished from noise) and are therefore applicable to other modalities. We believe that the topic of internal-learning is very important in many signal and image processing problems where training data is scarce and diversity is large on the one hand, and on the other, there is a lot of structure in the data that can be exploited.
Machine reasoning has made great progress in recent years owing to large language models (LLMs). In the clinical domain, however, most NLP-driven projects mainly focus on clinical classification or reading comprehension, and under-explore clinical reasoning for disease diagnosis due to the expensive rationale annotation with clinicians. In this work, we present a ``reasoning-aware'' diagnosis framework that rationalizes the diagnostic process via prompt-based learning in a time- and labor-efficient manner, and learns to reason over the prompt-generated rationales. Specifically, we address the clinical reasoning for disease diagnosis, where the LLM generates diagnostic rationales providing its insight on presented patient data and the reasoning path towards the diagnosis, namely Clinical Chain-of-Thought (Clinical CoT). We empirically demonstrate LLMs/LMs' ability of clinical reasoning via extensive experiments and analyses on both rationale generation and disease diagnosis in various settings. We further propose a novel set of criteria for evaluating machine-generated rationales' potential for real-world clinical settings, facilitating and benefiting future research in this area.
We propose a method for accelerating large-scale pre-training with online data selection policies. For the first time, we demonstrate that model-based data selection can reduce the total computation needed to reach the performance of models trained with uniform sampling. The key insight which enables this "compute-positive" regime is that small models provide good proxies for the loss of much larger models, such that computation spent on scoring data can be drastically scaled down but still significantly accelerate training of the learner.. These data selection policies also strongly generalize across datasets and tasks, opening an avenue for further amortizing the overhead of data scoring by re-using off-the-shelf models and training sequences. Our methods, ClassAct and ActiveCLIP, require 46% and 51% fewer training updates and up to 25% less total computation when training visual classifiers on JFT and multimodal models on ALIGN, respectively. Finally, our paradigm seamlessly applies to the curation of large-scale image-text datasets, yielding a new state-of-the-art in several multimodal transfer tasks and pre-training regimes.
We propose a zero-shot approach for consistent Text-to-Animated-Characters synthesis based on pre-trained Text-to-Image (T2I) diffusion models. Existing Text-to-Video (T2V) methods are expensive to train and require large-scale video datasets to produce diverse characters and motions. At the same time, their zero-shot alternatives fail to produce temporally consistent videos. We strive to bridge this gap, and we introduce a zero-shot approach that produces temporally consistent videos of animated characters and requires no training or fine-tuning. We leverage existing text-based motion diffusion models to generate diverse motions that we utilize to guide a T2I model. To achieve temporal consistency, we introduce the Spatial Latent Alignment module that exploits cross-frame dense correspondences that we compute to align the latents of the video frames. Furthermore, we propose Pixel-Wise Guidance to steer the diffusion process in a direction that minimizes visual discrepancies. Our proposed approach generates temporally consistent videos with diverse motions and styles, outperforming existing zero-shot T2V approaches in terms of pixel-wise consistency and user preference.
Collaborative robots (cobots) are widely used in industrial applications, yet extensive research is still needed to enhance human-robot collaborations and operator experience. A potential approach to improve the collaboration experience involves adapting cobot behavior based on natural cues from the operator. Inspired by the literature on human-human interactions, we conducted a wizard-of-oz study to examine whether a gaze towards the cobot can serve as a trigger for initiating joint activities in collaborative sessions. In this study, 37 participants engaged in an assembly task while their gaze behavior was analyzed. We employ a gaze-based attention recognition model to identify when the participants look at the cobot. Our results indicate that in most cases (84.88\%), the joint activity is preceded by a gaze towards the cobot. Furthermore, during the entire assembly cycle, the participants tend to look at the cobot around the time of the joint activity. To the best of our knowledge, this is the first study to analyze the natural gaze behavior of participants working on a joint activity with a robot during a collaborative assembly task.
Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the retrieval unit in which the corpus is indexed, e.g. document, passage, or sentence. We discover that the retrieval unit choice significantly impacts the performance of both retrieval and downstream tasks. Distinct from the typical approach of using passages or sentences, we introduce a novel retrieval unit, proposition, for dense retrieval. Propositions are defined as atomic expressions within text, each encapsulating a distinct factoid and presented in a concise, self-contained natural language format. We conduct an empirical comparison of different retrieval granularity. Our results reveal that proposition-based retrieval significantly outperforms traditional passage or sentence-based methods in dense retrieval. Moreover, retrieval by proposition also enhances the performance of downstream QA tasks, since the retrieved texts are more condensed with question-relevant information, reducing the need for lengthy input tokens and minimizing the inclusion of extraneous, irrelevant information.
Robotic manipulators are essential for future autonomous systems, yet limited trust in their autonomy has confined them to rigid, task-specific systems. The intricate configuration space of manipulators, coupled with the challenges of obstacle avoidance and constraint satisfaction, often makes motion planning the bottleneck for achieving reliable and adaptable autonomy. Recently, a class of constant-time motion planners (CTMP) was introduced. These planners employ a preprocessing phase to compute data structures that enable online planning provably guarantee the ability to generate motion plans, potentially sub-optimal, within a user defined time bound. This framework has been demonstrated to be effective in a number of time-critical tasks. However, robotic systems often have more time allotted for planning than the online portion of CTMP requires, time that can be used to improve the solution. To this end, we propose an anytime refinement approach that works in combination with CTMP algorithms. Our proposed framework, as it operates as a constant time algorithm, rapidly generates an initial solution within a user-defined time threshold. Furthermore, functioning as an anytime algorithm, it iteratively refines the solution's quality within the allocated time budget. This enables our approach to strike a balance between guaranteed fast plan generation and the pursuit of optimization over time. We support our approach by elucidating its analytical properties, showing the convergence of the anytime component towards optimal solutions. Additionally, we provide empirical validation through simulation and real-world demonstrations on a 6 degree-of-freedom robot manipulator, applied to an assembly domain.
Conventional approaches to dietary assessment are primarily grounded in self-reporting methods or structured interviews conducted under the supervision of dietitians. These methods, however, are often subjective, potentially inaccurate, and time-intensive. Although artificial intelligence (AI)-based solutions have been devised to automate the dietary assessment process, these prior AI methodologies encounter challenges in their ability to generalize across a diverse range of food types, dietary behaviors, and cultural contexts. This results in AI applications in the dietary field that possess a narrow specialization and limited accuracy. Recently, the emergence of multimodal foundation models such as GPT-4V powering the latest ChatGPT has exhibited transformative potential across a wide range of tasks (e.g., Scene understanding and image captioning) in numerous research domains. These models have demonstrated remarkable generalist intelligence and accuracy, capable of processing various data modalities. In this study, we explore the application of multimodal ChatGPT within the realm of dietary assessment. Our findings reveal that GPT-4V excels in food detection under challenging conditions with accuracy up to 87.5% without any fine-tuning or adaptation using food-specific datasets. By guiding the model with specific language prompts (e.g., African cuisine), it shifts from recognizing common staples like rice and bread to accurately identifying regional dishes like banku and ugali. Another GPT-4V's standout feature is its contextual awareness. GPT-4V can leverage surrounding objects as scale references to deduce the portion sizes of food items, further enhancing its accuracy in translating food weight into nutritional content. This alignment with the USDA National Nutrient Database underscores GPT-4V's potential to advance nutritional science and dietary assessment techniques.
Urban water-surface robust perception serves as the foundation for intelligent monitoring of aquatic environments and the autonomous navigation and operation of unmanned vessels, especially in the context of waterway safety. It is worth noting that current multi-sensor fusion and multi-task learning models consume substantial power and heavily rely on high-power GPUs for inference. This contributes to increased carbon emissions, a concern that runs counter to the prevailing emphasis on environmental preservation and the pursuit of sustainable, low-carbon urban environments. In light of these concerns, this paper concentrates on low-power, lightweight, multi-task panoptic perception through the fusion of visual and 4D radar data, which is seen as a promising low-cost perception method. We propose a framework named Achelous++ that facilitates the development and comprehensive evaluation of multi-task water-surface panoptic perception models. Achelous++ can simultaneously execute five perception tasks with high speed and low power consumption, including object detection, object semantic segmentation, drivable-area segmentation, waterline segmentation, and radar point cloud semantic segmentation. Furthermore, to meet the demand for developers to customize models for real-time inference on low-performance devices, a novel multi-modal pruning strategy known as Heterogeneous-Aware SynFlow (HA-SynFlow) is proposed. Besides, Achelous++ also supports random pruning at initialization with different layer-wise sparsity, such as Uniform and Erdos-Renyi-Kernel (ERK). Overall, our Achelous++ framework achieves state-of-the-art performance on the WaterScenes benchmark, excelling in both accuracy and power efficiency compared to other single-task and multi-task models. We release and maintain the code at https://github.com/GuanRunwei/Achelous.
This work concerns control-oriented and structure-preserving learning of low-dimensional approximations of high-dimensional physical systems, with a focus on mechanical systems. We investigate the integration of neural autoencoders in model order reduction, while at the same time preserving Hamiltonian or Lagrangian structures. We focus on extensively evaluating the considered methodology by performing simulation and control experiments on large mass-spring-damper networks, with hundreds of states. The empirical findings reveal that compressed latent dynamics with less than 5 degrees of freedom can accurately reconstruct the original systems' transient and steady-state behavior with a relative total error of around 4\%, while simultaneously accurately reconstructing the total energy. Leveraging this system compression technique, we introduce a model-based controller that exploits the mathematical structure of the compressed model to regulate the configuration of heavily underactuated mechanical systems.