KPConvX: Modernizing Kernel Point Convolution with Kernel Attention

In the field of deep point cloud understanding, KPConv is a unique architecture that uses kernel points to locate convolutional weights in space, instead of relying on Multi-Layer Perceptron (MLP) encodings. While it initially achieved success, it has since been surpassed by recent MLP networks that employ updated designs and training strategies. Building upon the kernel point principle, we present two novel designs: KPConvD (depthwise KPConv), a lighter design that enables the use of deeper architectures, and KPConvX, an innovative design that scales the depthwise convolutional weights of KPConvD with kernel attention values. Using KPConvX with a modern architecture and training strategy, we are able to outperform current state-of-the-art approaches on the ScanObjectNN, Scannetv2, and S3DIS datasets. We validate our design choices through ablation studies and release our code and models.

Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning

Step-by-step decision planning with large language models (LLMs) is gaining attention in AI agent development. This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models. Existing approaches are either white-box or computationally demanding, limiting use of black-box proprietary LLMs within budgets. The paper's first contribution is a non-parametric uncertainty quantification method for LLMs, efficiently estimating point-wise dependencies between input-decision on the fly with a single inference, without access to token logits. This estimator informs the statistical interpretation of decision trustworthiness. The second contribution outlines a systematic design for a decision-making agent, generating actions like ``turn on the bathroom light'' based on user prompts such as ``take a bath''. Users will be asked to provide preferences when more than one action has high estimated point-wise dependencies. In conclusion, our uncertainty estimation and decision-making agent design offer a cost-efficient approach for AI agent development.

An Empirical Study of Simplicial Representation Learning with Wasserstein Distance

In this paper, we delve into the problem of simplicial representation learning utilizing the 1-Wasserstein distance on a tree structure (a.k.a., Tree-Wasserstein distance (TWD)), where TWD is defined as the L1 distance between two tree-embedded vectors. Specifically, we consider a framework for simplicial representation estimation employing a self-supervised learning approach based on SimCLR with a negative TWD as a similarity measure. In SimCLR, the cosine similarity with real-vector embeddings is often utilized; however, it has not been well studied utilizing L1-based measures with simplicial embeddings. A key challenge is that training the L1 distance is numerically challenging and often yields unsatisfactory outcomes, and there are numerous choices for probability models. Thus, this study empirically investigates a strategy for optimizing self-supervised learning with TWD and find a stable training procedure. More specifically, we evaluate the combination of two types of TWD (total variation and ClusterTree) and several simplicial models including the softmax function, the ArcFace probability model, and simplicial embedding. Moreover, we propose a simple yet effective Jeffrey divergence-based regularization method to stabilize the optimization. Through empirical experiments on STL10, CIFAR10, CIFAR100, and SVHN, we first found that the simple combination of softmax function and TWD can obtain significantly lower results than the standard SimCLR (non-simplicial model and cosine similarity). We found that the model performance depends on the combination of TWD and the simplicial model, and the Jeffrey divergence regularization usually helps model training. Finally, we inferred that the appropriate choice of combination of TWD and simplicial models outperformed cosine similarity based representation learning.

Multimodal Large Language Model for Visual Navigation

Recent efforts to enable visual navigation using large language models have mainly focused on developing complex prompt systems. These systems incorporate instructions, observations, and history into massive text prompts, which are then combined with pre-trained large language models to facilitate visual navigation. In contrast, our approach aims to fine-tune large language models for visual navigation without extensive prompt engineering. Our design involves a simple text prompt, current observations, and a history collector model that gathers information from previous observations as input. For output, our design provides a probability distribution of possible actions that the agent can take during navigation. We train our model using human demonstrations and collision signals from the Habitat-Matterport 3D Dataset (HM3D). Experimental results demonstrate that our method outperforms state-of-the-art behavior cloning methods and effectively reduces collision rates.

Human Following in Mobile Platforms with Person Re-Identification

Human following is a crucial feature of human-robot interaction, yet it poses numerous challenges to mobile agents in real-world scenarios. Some major hurdles are that the target person may be in a crowd, obstructed by others, or facing away from the agent. To tackle these challenges, we present a novel person re-identification module composed of three parts: a 360-degree visual registration, a neural-based person re-identification using human faces and torsos, and a motion tracker that records and predicts the target person's future position. Our human-following system also addresses other challenges, including identifying fast-moving targets with low latency, searching for targets that move out of the camera's sight, collision avoidance, and adaptively choosing different following mechanisms based on the distance between the target person and the mobile agent. Extensive experiments show that our proposed person re-identification module significantly enhances the human-following feature compared to other baseline variants.

Object Goal Navigation with End-to-End Self-Supervision

A household robot should be able to navigate to target locations without requiring users to first annotate everything in their home. Current approaches to this object navigation challenge do not test on real robots and rely on expensive semantically labeled 3D meshes. In this work, our aim is an agent that builds self-supervised models of the world via exploration, the same as a child might. We propose an end-to-end self-supervised embodied agent that leverages exploration to train a semantic segmentation model of 3D objects, and uses those representations to learn an object navigation policy purely from self-labeled 3D meshes. The key insight is that embodied agents can leverage location consistency as a supervision signal - collecting images from different views/angles and applying contrastive learning to fine-tune a semantic segmentation model. In our experiments, we observe that our framework performs better than other self-supervised baselines and competitively with supervised baselines, in both simulation and when deployed in real houses.

Greedy Modality Selection via Approximate Submodular Maximization

Multimodal learning considers learning from multi-modality data, aiming to fuse heterogeneous sources of information. However, it is not always feasible to leverage all available modalities due to memory constraints. Further, training on all the modalities may be inefficient when redundant information exists within data, such as different subsets of modalities providing similar performance. In light of these challenges, we study modality selection, intending to efficiently select the most informative and complementary modalities under certain computational constraints. We formulate a theoretical framework for optimizing modality selection in multimodal learning and introduce a utility measure to quantify the benefit of selecting a modality. For this optimization problem, we present efficient algorithms when the utility measure exhibits monotonicity and approximate submodularity. We also connect the utility measure with existing Shapley-value-based feature importance scores. Last, we demonstrate the efficacy of our algorithm on synthetic (Patch-MNIST) and two real-world (PEMS-SF, CMU-MOSI) datasets.

Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents

The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc. Nonetheless, this direction has not been well-explored in comparison with models for outdoor environments (e.g., the autonomous driving system that includes pedestrian prediction, car detection, traffic sign recognition, etc.). In this paper, we first discuss the main challenge: insufficient, or even no, labeled data for real-world indoor environments, and other challenges such as fusion between heterogeneous sources of information (e.g., RGB images and Lidar point clouds), modeling relationships between a diverse set of outputs (e.g., 3D object locations, depth estimation, and human poses), and computational efficiency. Then, we describe MMISM (Multi-modality input Multi-task output Indoor Scene understanding Model) to tackle the above challenges. MMISM considers RGB images as well as sparse Lidar points as inputs and 3D object detection, depth completion, human pose estimation, and semantic segmentation as output tasks. We show that MMISM performs on par or even better than single-task models; e.g., we improve the baseline 3D object detection results by 11.7% on the benchmark ARKitScenes dataset.

Paraphrasing Is All You Need for Novel Object Captioning

Novel object captioning (NOC) aims to describe images containing objects without observing their ground truth captions during training. Due to the absence of caption annotation, captioning models cannot be directly optimized via sequence-to-sequence training or CIDEr optimization. As a result, we present Paraphrasing-to-Captioning (P2C), a two-stage learning framework for NOC, which would heuristically optimize the output captions via paraphrasing. With P2C, the captioning model first learns paraphrasing from a language model pre-trained on text-only corpus, allowing expansion of the word bank for improving linguistic fluency. To further enforce the output caption sufficiently describing the visual content of the input image, we perform self-paraphrasing for the captioning model with fidelity and adequacy objectives introduced. Since no ground truth captions are available for novel object images during training, our P2C leverages cross-modality (image-text) association modules to ensure the above caption characteristics can be properly preserved. In the experiments, we not only show that our P2C achieves state-of-the-art performances on nocaps and COCO Caption datasets, we also verify the effectiveness and flexibility of our learning framework by replacing language and cross-modality association models for NOC. Implementation details and code are available in the supplementary materials.

Scale dependant layer for self-supervised nuclei encoding

Recent developments in self-supervised learning give us the possibility to further reduce human intervention in multi-step pipelines where the focus evolves around particular objects of interest. In the present paper, the focus lays in the nuclei in histopathology images. In particular we aim at extracting cellular information in an unsupervised manner for a downstream task. As nuclei present themselves in a variety of sizes, we propose a new Scale-dependant convolutional layer to bypass scaling issues when resizing nuclei. On three nuclei datasets, we benchmark the following methods: handcrafted, pre-trained ResNet, supervised ResNet and self-supervised features. We show that the proposed convolution layer boosts performance and that this layer combined with Barlows-Twins allows for better nuclei encoding compared to the supervised paradigm in the low sample setting and outperforms all other proposed unsupervised methods. In addition, we extend the existing TNBC dataset to incorporate nuclei class annotation in order to enrich and publicly release a small sample setting dataset for nuclei segmentation and classification.