Interfacing Foundation Models' Embeddings

• URL: http://arxiv.org/abs/2312.07532v2
• Date: Mon, 15 Jul 2024 04:18:26 GMT
• Title: Interfacing Foundation Models' Embeddings
• Authors: Xueyan Zou, Linjie Li, Jianfeng Wang, Jianwei Yang, Mingyu Ding, Junyi Wei, Zhengyuan Yang, Feng Li, Hao Zhang, Shilong Liu, Arul Aravinthan, Yong Jae Lee, Lijuan Wang,
• Abstract summary: We present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and granularity. In light of the interleaved embedding space, we introduce FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleaved segmentation and retrieval.
• Score: 131.0352288172788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and granularity. As shown in the teaser figure, a lightweight transformer interface without tuning any foundation model weights is enough for segmentation, grounding, and retrieval in an interleaved manner. The proposed interface has the following favorable attributes: (1) Generalizable. It applies to various tasks spanning retrieval, segmentation, etc., under the same architecture and weights. (2) Interleavable. With the benefit of multi-task multi-modal training, the proposed interface creates an interleaved shared embedding space. (3) Extendable. The proposed interface is adaptive to new tasks, and new models. In light of the interleaved embedding space, we introduce FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleaved segmentation and retrieval. We are the first work aligning foundations models' embeddings for interleave understanding. Meanwhile, our approach achieves state-of-the-art performance on FIND-Bench and competitive performance on standard retrieval and segmentation settings.

Related papers

• Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning [64.1745161657794]
  Domain-Incremental Learning (DIL) involves the progressive adaptation of a model to new concepts across different domains. Recent advances in pre-trained models provide a solid foundation for DIL. However, learning new concepts often results in the catastrophic forgetting of pre-trained knowledge. We propose DUal ConsolidaTion (Duct) to unify and consolidate historical knowledge.
  arXiv  Detail & Related papers  (2024-10-01T17:58:06Z)
• Dual-Personalizing Adapter for Federated Foundation Models [35.863585349109385]
  We propose a new setting, termed test-time personalization, which concentrates on the targeted local task and extends to other tasks that exhibit test-time distribution shifts. Specifically, a dual-personalizing adapter architecture (FedDPA) is proposed, comprising a global adapter and a local adapter for addressing test-time distribution shifts and personalization. The effectiveness of the proposed method has been evaluated on benchmark datasets across different NLP tasks.
  arXiv  Detail & Related papers  (2024-03-28T08:19:33Z)
• Task-Specific Adaptation of Segmentation Foundation Model via Prompt Learning [7.6136466242670435]
  We propose a task-specific adaptation of the segmentation foundation model via prompt learning tailored to the Segment Anything Model (SAM) Our method involves a prompt learning module which adjusts input prompts into the embedding space to better align with peculiarities of the target task. Experimental results on various customized segmentation scenarios demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-03-14T09:13:51Z)
• Semantic-SAM: Segment and Recognize Anything at Any Granularity [83.64686655044765]
  We introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. We consolidate multiple datasets across three granularities and introduce decoupled classification for objects and parts. For the multi-granularity capability, we propose a multi-choice learning scheme during training, enabling each click to generate masks at multiple levels.
  arXiv  Detail & Related papers  (2023-07-10T17:59:40Z)
• End-to-End Hierarchical Relation Extraction for Generic Form Understanding [0.6299766708197884]
  We present a novel deep neural network to jointly perform both entity detection and link prediction. Our model extends the Multi-stage Attentional U-Net architecture with the Part-Intensity Fields and Part-Association Fields for link prediction. We demonstrate the effectiveness of the model on the Form Understanding in Noisy Scanned Documents dataset.
  arXiv  Detail & Related papers  (2021-06-02T06:51:35Z)
• Reviving Iterative Training with Mask Guidance for Interactive Segmentation [8.271859911016719]
  Recent works on click-based interactive segmentation have demonstrated state-of-the-art results by using various inference-time optimization schemes. We propose a simple feedforward model for click-based interactive segmentation that employs the segmentation masks from previous steps. We find that the models trained on a combination of COCO and LVIS with diverse and high-quality annotations show performance superior to all existing models.
  arXiv  Detail & Related papers  (2021-02-12T15:44:31Z)
• Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation [144.50154657257605]
  We propose an efficient framework to simultaneously search for all main components including backbone, segmentation branches, and feature fusion module. Our searched architecture, namely Auto-Panoptic, achieves the new state-of-the-art on the challenging COCO and ADE20K benchmarks.
  arXiv  Detail & Related papers  (2020-10-30T08:34:35Z)
• BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation [84.2925550033094]
  Few-shot segmentation focuses on the generalization of models to segment unseen object instances with limited training samples. We propose a framework, BriNet, to bridge the gaps between the extracted features of the query and support images. The effectiveness of our framework is demonstrated by experimental results, which outperforms other competitive methods.
  arXiv  Detail & Related papers  (2020-08-14T07:45:50Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.