Jerome Quenum

Tsung-Han Wu, Giscard Biamby, Jerome Quenum et al.

Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to process a large number of visual tokens does not guarantee effective retrieval and reasoning for multi-image question answering (MIQA), especially in real-world applications like photo album searches or satellite imagery analysis. In this work, we first assess the limitations of current benchmarks for long-context LMMs. We address these limitations by introducing a new vision-centric, long-context benchmark, "Visual Haystacks (VHs)". We comprehensively evaluate both open-source and proprietary models on VHs, and demonstrate that these models struggle when reasoning across potentially unrelated images, perform poorly on cross-image reasoning, as well as exhibit biases based on the placement of key information within the context window. Towards a solution, we introduce MIRAGE (Multi-Image Retrieval Augmented Generation), an open-source, lightweight visual-RAG framework that processes up to 10k images on a single 40G A100 GPU -- far surpassing the 1k-image limit of contemporary models. MIRAGE demonstrates up to 13% performance improvement over existing open-source LMMs on VHs, sets a new state-of-the-art on the RetVQA multi-image QA benchmark, and achieves competitive performance on single-image QA with state-of-the-art LMMs. Our dataset, model, and code are available at: https://visual-haystacks.github.io.

Jerome Quenum, Iryna Zenyuk, Daniela Ushizima

Lithium metal battery (LMB) has the potential to be the next-generation battery system because of its high theoretical energy density. However, defects known as dendrites are formed by heterogeneous lithium (Li) plating, which hinders the development and utilization of LMBs. Non-destructive techniques to observe the dendrite morphology often use X-ray computed tomography (XCT) to provide cross-sectional views. To retrieve three-dimensional structures inside a battery, image segmentation becomes essential to quantitatively analyze XCT images. This work proposes a new semantic segmentation approach using a transformer-based neural network called TransforCNN that is capable of segmenting out dendrites from XCT data. In addition, we compare the performance of the proposed TransforCNN with three other algorithms, such as U-Net, Y-Net, and E-Net, consisting of an Ensemble Network model for XCT analysis. Our results show the advantages of using TransforCNN when evaluating over-segmentation metrics, such as mean Intersection over Union (mIoU) and mean Dice Similarity Coefficient (mDSC) as well as through several qualitatively comparative visualizations.

Jerome Quenum, Kehan Wang, Avideh Zakhor

Object detection in Ultra High-Resolution (UHR) images has long been a challenging problem in computer vision due to the varying scales of the targeted objects. When it comes to barcode detection, resizing UHR input images to smaller sizes often leads to the loss of pertinent information, while processing them directly is highly inefficient and computationally expensive. In this paper, we propose using semantic segmentation to achieve a fast and accurate detection of barcodes of various scales in UHR images. Our pipeline involves a modified Region Proposal Network (RPN) on images of size greater than 10k$\times$10k and a newly proposed Y-Net segmentation network, followed by a post-processing workflow for fitting a bounding box around each segmented barcode mask. The end-to-end system has a latency of 16 milliseconds, which is $2.5\times$ faster than YOLOv4 and $5.9\times$ faster than Mask R-CNN. In terms of accuracy, our method outperforms YOLOv4 and Mask R-CNN by a $mAP$ of 5.5% and 47.1% respectively, on a synthetic dataset. We have made available the generated synthetic barcode dataset and its code at http://www.github.com/viplabB/SBD/.

Jerome Quenum, Wen-Han Hsieh, Tsung-Han Wu et al.

Segmentation models can recognize a pre-defined set of objects in images. However, models that can reason over complex user queries that implicitly refer to multiple objects of interest are still in their infancy. Recent advances in reasoning segmentation--generating segmentation masks from complex, implicit query text--demonstrate that vision-language models can operate across an open domain and produce reasonable outputs. However, our experiments show that such models struggle with complex remote-sensing imagery. In this work, we introduce LISAt, a vision-language model designed to describe complex remote-sensing scenes, answer questions about them, and segment objects of interest. We trained LISAt on a new curated geospatial reasoning-segmentation dataset, GRES, with 27,615 annotations over 9,205 images, and a multimodal pretraining dataset, PreGRES, containing over 1 million question-answer pairs. LISAt outperforms existing geospatial foundation models such as RS-GPT4V by over 10.04 % (BLEU-4) on remote-sensing description tasks, and surpasses state-of-the-art open-domain models on reasoning segmentation tasks by 143.36 % (gIoU). Our model, datasets, and code are available at https://lisat-bair.github.io/LISAt/

Dantong Niu, Yuvan Sharma, Giscard Biamby et al.

In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at several tasks, including image captioning and visual question answering; yet leveraging these models remains an open question for robotics. Prior LMMs for robotics applications have been extensively trained on language and action data, but their ability to generalize in different settings has often been less than desired. To address this, we introduce LLARVA, a model trained with a novel instruction tuning method that leverages structured prompts to unify a range of robotic learning tasks, scenarios, and environments. Additionally, we show that predicting intermediate 2-D representations, which we refer to as "visual traces", can help further align vision and action spaces for robot learning. We generate 8.5M image-visual trace pairs from the Open X-Embodiment dataset in order to pre-train our model, and we evaluate on 12 different tasks in the RLBench simulator as well as a physical Franka Emika Panda 7-DoF robot. Our experiments yield strong performance, demonstrating that LLARVA - using 2-D and language representations - performs well compared to several contemporary baselines, and can generalize across various robot environments and configurations.