Precise manipulation that is generalizable across scenes and objects remains a persistent challenge in robotics. Current approaches for this task heavily depend on having a significant number of training instances to handle objects with pronounced visual and/or geometric part ambiguities. Our work explores the grounding of fine-grained part descriptors for precise manipulation in a zero-shot setting by utilizing web-trained text-to-image diffusion-based generative models. We tackle the problem by framing it as a dense semantic part correspondence task. Our model returns a gripper pose for manipulating a specific part, using as reference a user-defined click from a source image of a visually different instance of the same object. We require no manual grasping demonstrations as we leverage the intrinsic object geometry and features. Practical experiments in a real-world tabletop scenario validate the efficacy of our approach, demonstrating its potential for advancing semantic-aware robotics manipulation. Web page: https://tsagkas.github.io/click2grasp
Recent progress in self-supervised representation learning has resulted in models that are capable of extracting image features that are not only effective at encoding image level, but also pixel-level, semantics. These features have been shown to be effective for dense visual semantic correspondence estimation, even outperforming fully-supervised methods. Nevertheless, current self-supervised approaches still fail in the presence of challenging image characteristics such as symmetries and repeated parts. To address these limitations, we propose a new approach for semantic correspondence estimation that supplements discriminative self-supervised features with 3D understanding via a weak geometric spherical prior. Compared to more involved 3D pipelines, our model only requires weak viewpoint information, and the simplicity of our spherical representation enables us to inject informative geometric priors into the model during training. We propose a new evaluation metric that better accounts for repeated part and symmetry-induced mistakes. We present results on the challenging SPair-71k dataset, where we show that our approach demonstrates is capable of distinguishing between symmetric views and repeated parts across many object categories, and also demonstrate that we can generalize to unseen classes on the AwA dataset.
We propose a new active learning approach for efficiently estimating the geographic range of a species from a limited number of on the ground observations. We model the range of an unmapped species of interest as the weighted combination of estimated ranges obtained from a set of different species. We show that it is possible to generate this candidate set of ranges by using models that have been trained on large weakly supervised community collected observation data. From this, we develop a new active querying approach that sequentially selects geographic locations to visit that best reduce our uncertainty over an unmapped species' range. We conduct a detailed evaluation of our approach and compare it to existing active learning methods using an evaluation dataset containing expert-derived ranges for one thousand species. Our results demonstrate that our method outperforms alternative active learning methods and approaches the performance of end-to-end trained models, even when only using a fraction of the data. This highlights the utility of active learning via transfer learned spatial representations for species range estimation. It also emphasizes the value of leveraging emerging large-scale crowdsourced datasets, not only for modeling a species' range, but also for actively discovering them.
1. Automated analysis of bioacoustic recordings using machine learning (ML) methods has the potential to greatly scale biodiversity monitoring efforts. The use of ML for high-stakes applications, such as conservation research, demands a data-centric approach with a focus on utilizing carefully annotated and curated evaluation and training data that is relevant and representative. Creating annotated datasets of sound recordings presents a number of challenges, such as managing large collections of recordings with associated metadata, developing flexible annotation tools that can accommodate the diverse range of vocalization profiles of different organisms, and addressing the scarcity of expert annotators. 2. We present Whombat a user-friendly, browser-based interface for managing audio recordings and annotation projects, with several visualization, exploration, and annotation tools. It enables users to quickly annotate, review, and share annotations, as well as visualize and evaluate a set of machine learning predictions on a dataset. The tool facilitates an iterative workflow where user annotations and machine learning predictions feedback to enhance model performance and annotation quality. 3. We demonstrate the flexibility of Whombat by showcasing two distinct use cases: an project aimed at enhancing automated UK bat call identification at the Bat Conservation Trust (BCT), and a collaborative effort among the USDA Forest Service and Oregon State University researchers exploring bioacoustic applications and extending automated avian classification models in the Pacific Northwest, USA. 4. Whombat is a flexible tool that can effectively address the challenges of annotation for bioacoustic research. It can be used for individual and collaborative work, hosted on a shared server or accessed remotely, or run on a personal computer without the need for coding skills.
Estimating the geographical range of a species from sparse observations is a challenging and important geospatial prediction problem. Given a set of locations where a species has been observed, the goal is to build a model to predict whether the species is present or absent at any location. This problem has a long history in ecology, but traditional methods struggle to take advantage of emerging large-scale crowdsourced datasets which can include tens of millions of records for hundreds of thousands of species. In this work, we use Spatial Implicit Neural Representations (SINRs) to jointly estimate the geographical range of 47k species simultaneously. We find that our approach scales gracefully, making increasingly better predictions as we increase the number of species and the amount of data per species when training. To make this problem accessible to machine learning researchers, we provide four new benchmarks that measure different aspects of species range estimation and spatial representation learning. Using these benchmarks, we demonstrate that noisy and biased crowdsourced data can be combined with implicit neural representations to approximate expert-developed range maps for many species.
We present Visual-Language Fields (VL-Fields), a neural implicit spatial representation that enables open-vocabulary semantic queries. Our model encodes and fuses the geometry of a scene with vision-language trained latent features by distilling information from a language-driven segmentation model. VL-Fields is trained without requiring any prior knowledge of the scene object classes, which makes it a promising representation for the field of robotics. Our model outperformed the similar CLIP-Fields model in the task of semantic segmentation by almost 10%.
For augmented reality (AR), it is important that virtual assets appear to `sit among' real world objects. The virtual element should variously occlude and be occluded by real matter, based on a plausible depth ordering. This occlusion should be consistent over time as the viewer's camera moves. Unfortunately, small mistakes in the estimated scene depth can ruin the downstream occlusion mask, and thereby the AR illusion. Especially in real-time settings, depths inferred near boundaries or across time can be inconsistent. In this paper, we challenge the need for depth-regression as an intermediate step. We instead propose an implicit model for depth and use that to predict the occlusion mask directly. The inputs to our network are one or more color images, plus the known depths of any virtual geometry. We show how our occlusion predictions are more accurate and more temporally stable than predictions derived from traditional depth-estimation models. We obtain state-of-the-art occlusion results on the challenging ScanNetv2 dataset and superior qualitative results on real scenes.
We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a challenging category incremental learning setting where the goal is to develop models that can correctly categorize images from previously seen categories, in addition to discovering novel ones. Learning is performed over a series of time steps where the model obtains new labeled and unlabeled data, and discards old data, at each iteration. The difficulty of the problem is compounded in our generalized setting as the unlabeled data can contain images from categories that may or may not have been observed before. We present a new method for IGCD which combines non-parametric categorization with efficient image sampling to mitigate catastrophic forgetting. To quantify performance, we propose a new benchmark dataset named iNatIGCD that is motivated by a real-world fine-grained visual categorization task. In our experiments we outperform existing related methods
Multimodal learning, which aims to understand and analyze information from multiple modalities, has achieved substantial progress in the supervised regime in recent years. However, the heavy dependence on data paired with expensive human annotations impedes scaling up models. Meanwhile, given the availability of large-scale unannotated data in the wild, self-supervised learning has become an attractive strategy to alleviate the annotation bottleneck. Building on these two directions, self-supervised multimodal learning (SSML) provides ways to leverage supervision from raw multimodal data. In this survey, we provide a comprehensive review of the state-of-the-art in SSML, which we categorize along three orthogonal axes: objective functions, data alignment, and model architectures. These axes correspond to the inherent characteristics of self-supervised learning methods and multimodal data. Specifically, we classify training objectives into instance discrimination, clustering, and masked prediction categories. We also discuss multimodal input data pairing and alignment strategies during training. Finally, we review model architectures including the design of encoders, fusion modules, and decoders, which are essential components of SSML methods. We review downstream multimodal application tasks, reporting the concrete performance of the state-of-the-art image-text models and multimodal video models, and also review real-world applications of SSML algorithms in diverse fields such as healthcare, remote sensing, and machine translation. Finally, we discuss challenges and future directions for SSML. A collection of related resources can be found at: https://github.com/ys-zong/awesome-self-supervised-multimodal-learning.