Abstract:In this study, we consider the problem of predicting task success for open-vocabulary manipulation by a manipulator, based on instruction sentences and egocentric images before and after manipulation. Conventional approaches, including multimodal large language models (MLLMs), often fail to appropriately understand detailed characteristics of objects and/or subtle changes in the position of objects. We propose Contrastive $\lambda$-Repformer, which predicts task success for table-top manipulation tasks by aligning images with instruction sentences. Our method integrates the following three key types of features into a multi-level aligned representation: features that preserve local image information; features aligned with natural language; and features structured through natural language. This allows the model to focus on important changes by looking at the differences in the representation between two images. We evaluate Contrastive $\lambda$-Repformer on a dataset based on a large-scale standard dataset, the RT-1 dataset, and on a physical robot platform. The results show that our approach outperformed existing approaches including MLLMs. Our best model achieved an improvement of 8.66 points in accuracy compared to the representative MLLM-based model.
Abstract:In this work, we address the challenge of developing automatic evaluation metrics for image captioning, with a particular focus on robustness against hallucinations. Existing metrics are often inadequate for handling hallucinations, primarily due to their limited ability to compare candidate captions with multifaceted reference captions. To address this shortcoming, we propose DENEB, a novel supervised automatic evaluation metric specifically robust against hallucinations. DENEB incorporates the Sim-Vec Transformer, a mechanism that processes multiple references simultaneously, thereby efficiently capturing the similarity between an image, a candidate caption, and reference captions. To train DENEB, we construct the diverse and balanced Nebula dataset comprising 32,978 images, paired with human judgments provided by 805 annotators. We demonstrated that DENEB achieves state-of-the-art performance among existing LLM-free metrics on the FOIL, Composite, Flickr8K-Expert, Flickr8K-CF, Nebula, and PASCAL-50S datasets, validating its effectiveness and robustness against hallucinations.
Abstract:In this study, we aim to develop a domestic service robot (DSR) that, guided by open-vocabulary instructions, can carry everyday objects to the specified pieces of furniture. Few existing methods handle mobile manipulation tasks with open-vocabulary instructions in the image retrieval setting, and most do not identify both the target objects and the receptacles. We propose the Dual-Mode Multimodal Ranking model (DM2RM), which enables images of both the target objects and receptacles to be retrieved using a single model based on multimodal foundation models. We introduce a switching mechanism that leverages a mode token and phrase identification via a large language model to switch the embedding space based on the prediction target. To evaluate the DM2RM, we construct a novel dataset including real-world images collected from hundreds of building-scale environments and crowd-sourced instructions with referring expressions. The evaluation results show that the proposed DM2RM outperforms previous approaches in terms of standard metrics in image retrieval settings. Furthermore, we demonstrate the application of the DM2RM on a standardized real-world DSR platform including fetch-and-carry actions, where it achieves a task success rate of 82% despite the zero-shot transfer setting. Demonstration videos, code, and more materials are available at https://kkrr10.github.io/dm2rm/.
Abstract:Domestic service robots (DSRs) that support people in everyday environments have been widely investigated. However, their ability to predict and describe future risks resulting from their own actions remains insufficient. In this study, we focus on the linguistic explainability of DSRs. Most existing methods do not explicitly model the region of possible collisions; thus, they do not properly generate descriptions of these regions. In this paper, we propose the Nearest Neighbor Future Captioning Model that introduces the Nearest Neighbor Language Model for future captioning of possible collisions, which enhances the model output with a nearest neighbors retrieval mechanism. Furthermore, we introduce the Collision Attention Module that attends regions of possible collisions, which enables our model to generate descriptions that adequately reflect the objects associated with possible collisions. To validate our method, we constructed a new dataset containing samples of collisions that can occur when a DSR places an object in a simulation environment. The experimental results demonstrated that our method outperformed baseline methods, based on the standard metrics. In particular, on CIDEr-D, the baseline method obtained 25.09 points, whereas our method obtained 33.08 points.
Abstract:The transparent formulation of explanation methods is essential for elucidating the predictions of neural networks, which are typically black-box models. Layer-wise Relevance Propagation (LRP) is a well-established method that transparently traces the flow of a model's prediction backward through its architecture by backpropagating relevance scores. However, the conventional LRP does not fully consider the existence of skip connections, and thus its application to the widely used ResNet architecture has not been thoroughly explored. In this study, we extend LRP to ResNet models by introducing Relevance Splitting at points where the output from a skip connection converges with that from a residual block. Our formulation guarantees the conservation property throughout the process, thereby preserving the integrity of the generated explanations. To evaluate the effectiveness of our approach, we conduct experiments on ImageNet and the Caltech-UCSD Birds-200-2011 dataset. Our method achieves superior performance to that of baseline methods on standard evaluation metrics such as the Insertion-Deletion score while maintaining its conservation property. We will release our code for further research at https://5ei74r0.github.io/lrp-for-resnet.page/
Abstract:Rearranging objects (e.g. vase, door) back in their original positions is one of the most fundamental skills for domestic service robots (DSRs). In rearrangement tasks, it is crucial to detect the objects that need to be rearranged according to the goal and current states. In this study, we focus on Rearrangement Target Detection (RTD), where the model generates a change mask for objects that should be rearranged. Although many studies have been conducted in the field of Scene Change Detection (SCD), most SCD methods often fail to segment objects with complex shapes and fail to detect the change in the angle of objects that can be opened or closed. In this study, we propose a Co-Scale Cross-Attentional Transformer for RTD. We introduce the Serial Encoder which consists of a sequence of serial blocks and the Cross-Attentional Encoder which models the relationship between the goal and current states. We built a new dataset consisting of RGB images and change masks regarding the goal and current states. We validated our method on the dataset and the results demonstrated that our method outperformed baseline methods on $F_1$-score and mean IoU.
Abstract:We consider the task of generating segmentation masks for the target object from an object manipulation instruction, which allows users to give open vocabulary instructions to domestic service robots. Conventional segmentation generation approaches often fail to account for objects outside the camera's field of view and cases in which the order of vertices differs but still represents the same polygon, which leads to erroneous mask generation. In this study, we propose a novel method that generates segmentation masks from open vocabulary instructions. We implement a novel loss function using optimal transport to prevent significant loss where the order of vertices differs but still represents the same polygon. To evaluate our approach, we constructed a new dataset based on the REVERIE dataset and Matterport3D dataset. The results demonstrated the effectiveness of the proposed method compared with existing mask generation methods. Remarkably, our best model achieved a +16.32% improvement on the dataset compared with a representative polygon-based method.
Abstract:Establishing an automatic evaluation metric that closely aligns with human judgments is essential for effectively developing image captioning models. Recent data-driven metrics have demonstrated a stronger correlation with human judgments than classic metrics such as CIDEr; however they lack sufficient capabilities to handle hallucinations and generalize across diverse images and texts partially because they compute scalar similarities merely using embeddings learned from tasks unrelated to image captioning evaluation. In this study, we propose Polos, a supervised automatic evaluation metric for image captioning models. Polos computes scores from multimodal inputs, using a parallel feature extraction mechanism that leverages embeddings trained through large-scale contrastive learning. To train Polos, we introduce Multimodal Metric Learning from Human Feedback (M$^2$LHF), a framework for developing metrics based on human feedback. We constructed the Polaris dataset, which comprises 131K human judgments from 550 evaluators, which is approximately ten times larger than standard datasets. Our approach achieved state-of-the-art performance on Composite, Flickr8K-Expert, Flickr8K-CF, PASCAL-50S, FOIL, and the Polaris dataset, thereby demonstrating its effectiveness and robustness.
Abstract:Domestic service robots offer a solution to the increasing demand for daily care and support. A human-in-the-loop approach that combines automation and operator intervention is considered to be a realistic approach to their use in society. Therefore, we focus on the task of retrieving target objects from open-vocabulary user instructions in a human-in-the-loop setting, which we define as the learning-to-rank physical objects (LTRPO) task. For example, given the instruction "Please go to the dining room which has a round table. Pick up the bottle on it," the model is required to output a ranked list of target objects that the operator/user can select. In this paper, we propose MultiRankIt, which is a novel approach for the LTRPO task. MultiRankIt introduces the Crossmodal Noun Phrase Encoder to model the relationship between phrases that contain referring expressions and the target bounding box, and the Crossmodal Region Feature Encoder to model the relationship between the target object and multiple images of its surrounding contextual environment. Additionally, we built a new dataset for the LTRPO task that consists of instructions with complex referring expressions accompanied by real indoor environmental images that feature various target objects. We validated our model on the dataset and it outperformed the baseline method in terms of the mean reciprocal rank and recall@k. Furthermore, we conducted physical experiments in a setting where a domestic service robot retrieved everyday objects in a standardized domestic environment, based on users' instruction in a human--in--the--loop setting. The experimental results demonstrate that the success rate for object retrieval achieved 80%. Our code is available at https://github.com/keio-smilab23/MultiRankIt.
Abstract:This paper focuses on the DialFRED task, which is the task of embodied instruction following in a setting where an agent can actively ask questions about the task. To address this task, we propose DialMAT. DialMAT introduces Moment-based Adversarial Training, which incorporates adversarial perturbations into the latent space of language, image, and action. Additionally, it introduces a crossmodal parallel feature extraction mechanism that applies foundation models to both language and image. We evaluated our model using a dataset constructed from the DialFRED dataset and demonstrated superior performance compared to the baseline method in terms of success rate and path weighted success rate. The model secured the top position in the DialFRED Challenge, which took place at the CVPR 2023 Embodied AI workshop.