InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions

Ambiguity is ubiquitous in human communication. Previous approaches in Human-Robot Interaction (HRI) have often relied on predefined interaction templates, leading to reduced performance in realistic and open-ended scenarios. To address these issues, we present a large-scale dataset, \invig, for interactive visual grounding under language ambiguity. Our dataset comprises over 520K images accompanied by open-ended goal-oriented disambiguation dialogues, encompassing millions of object instances and corresponding question-answer pairs. Leveraging the \invig dataset, we conduct extensive studies and propose a set of baseline solutions for end-to-end interactive visual disambiguation and grounding, achieving a 45.6\% success rate during validation. To the best of our knowledge, the \invig dataset is the first large-scale dataset for resolving open-ended interactive visual grounding, presenting a practical yet highly challenging benchmark for ambiguity-aware HRI. Codes and datasets are available at: \href{https://openivg.github.io}{https://openivg.github.io}.

Combo of Thinking and Observing for Outside-Knowledge VQA

Outside-knowledge visual question answering is a challenging task that requires both the acquisition and the use of open-ended real-world knowledge. Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features. In this paper, we are inspired to constrain the cross-modality space into the same space of natural-language space which makes the visual features preserved directly, and the model still benefits from the vast knowledge in natural-language space. To this end, we propose a novel framework consisting of a multimodal encoder, a textual encoder and an answer decoder. Such structure allows us to introduce more types of knowledge including explicit and implicit multimodal and textual knowledge. Extensive experiments validate the superiority of the proposed method which outperforms the state-of-the-art by 6.17% accuracy. We also conduct comprehensive ablations of each component, and systematically study the roles of varying types of knowledge. Codes and knowledge data can be found at https://github.com/PhoebusSi/Thinking-while-Observing.

Rethinking Generative Coverage: A Pointwise Guaranteed Approach

All generative models have to combat missing modes. The conventional wisdom is by reducing a statistical distance (such as f-divergence) between the generated distribution and the provided data distribution through training. We defy this wisdom. We show that even a small statistical distance does not imply a plausible mode coverage, because this distance measures a global similarity between two distributions, but not their similarity in local regions--which is needed to ensure a complete mode coverage. From a starkly different perspective, we view the battle against missing modes as a two-player game, between a player choosing a data point and an adversary choosing a generator aiming to cover that data point. Enlightened by von Neumann's minimax theorem, we see that if a generative model can approximate a data distribution moderately well under a global statistical distance measure, then we should be able to find a mixture of generators which collectively covers every data point and thus every mode with a lower-bounded probability density. A constructive realization of this minimax duality--that is, our proposed algorithm of finding the mixture of generators--is connected to a multiplicative weights update rule. We prove the pointwise coverage guarantee of our algorithm, and our experiments on real and synthetic data confirm better mode coverage over recent approaches that also use a mixture of generators but focus on global statistical distances.

Active Clothing Material Perception using Tactile Sensing and Deep Learning

Humans represent and discriminate the objects in the same category using their properties, and an intelligent robot should be able to do the same. In this paper, we build a robot system that can autonomously perceive the object properties through touch. We work on the common object category of clothing. The robot moves under the guidance of an external Kinect sensor, and squeezes the clothes with a GelSight tactile sensor, then it recognizes the 11 properties of the clothing according to the tactile data. Those properties include the physical properties, like thickness, fuzziness, softness and durability, and semantic properties, like wearing season and preferred washing methods. We collect a dataset of 153 varied pieces of clothes, and conduct 6616 robot exploring iterations on them. To extract the useful information from the high-dimensional sensory output, we applied Convolutional Neural Networks (CNN) on the tactile data for recognizing the clothing properties, and on the Kinect depth images for selecting exploration locations. Experiments show that using the trained neural networks, the robot can autonomously explore the unknown clothes and learn their properties. This work proposes a new framework for active tactile perception system with vision-touch system, and has potential to enable robots to help humans with varied clothing related housework.