Do Pre-trained Vision-Language Models Encode Object States?

• URL: http://arxiv.org/abs/2409.10488v1
• Date: Mon, 16 Sep 2024 17:22:18 GMT
• Title: Do Pre-trained Vision-Language Models Encode Object States?
• Authors: Kaleb Newman, Shijie Wang, Yuan Zang, David Heffren, Chen Sun,
• Abstract summary: We investigate if vision-language models (VLMs) learn to encode object states on web-scale data. We evaluate nine open-source VLMs, including models trained with contrastive and generative objectives. We identify three areas for improvements for better encode object states.
• Score: 13.4206464539947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a whole apple into a sliced apple). Our paper aims to investigate if VLMs pre-trained on web-scale data learn to encode object states, which can be extracted with zero-shot text prompts. We curate an object state recognition dataset ChangeIt-Frames, and evaluate nine open-source VLMs, including models trained with contrastive and generative objectives. We observe that while these state-of-the-art vision-language models can reliably perform object recognition, they consistently fail to accurately distinguish the objects' physical states. Through extensive experiments, we identify three areas for improvements for VLMs to better encode object states, namely the quality of object localization, the architecture to bind concepts to objects, and the objective to learn discriminative visual and language encoders on object states. Data and code are released.

Related papers

• Towards Interpreting Visual Information Processing in Vision-Language Models [24.51408101801313]
  Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM.
  arXiv  Detail & Related papers  (2024-10-09T17:55:02Z)
• Learning Visual Grounding from Generative Vision and Language Model [29.2712567454021]
  Visual grounding tasks aim to localize image regions based on natural language references. We find that grounding knowledge already exists in generative VLM and can be elicited by proper prompting. Our results demonstrate the promise of generative VLM to scale up visual grounding in the real world.
  arXiv  Detail & Related papers  (2024-07-18T20:29:49Z)
• ClawMachine: Fetching Visual Tokens as An Entity for Referring and Grounding [67.63933036920012]
  Existing methods, including proxy encoding and geometry encoding, incorporate additional syntax to encode the object's location. This study presents ClawMachine, offering a new methodology that notates an entity directly using the visual tokens. ClawMachine unifies visual referring and grounding into an auto-regressive format and learns with a decoder-only architecture.
  arXiv  Detail & Related papers  (2024-06-17T08:39:16Z)
• OSCaR: Object State Captioning and State Change Representation [52.13461424520107]
  This paper introduces the Object State Captioning and State Change Representation (OSCaR) dataset and benchmark. OSCaR consists of 14,084 annotated video segments with nearly 1,000 unique objects from various egocentric video collections. It sets a new testbed for evaluating multimodal large language models (MLLMs)
  arXiv  Detail & Related papers  (2024-02-27T01:48:19Z)
• Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge [62.981429762309226]
  The ability to actively ground task instructions from an egocentric view is crucial for AI agents to accomplish tasks or assist humans virtually. We propose to improve phrase grounding models' ability on localizing the active objects by: learning the role of objects undergoing change and extracting them accurately from the instructions. We evaluate our framework on Ego4D and Epic-Kitchens datasets.
  arXiv  Detail & Related papers  (2023-10-23T16:14:05Z)
• Physically Grounded Vision-Language Models for Robotic Manipulation [59.143640049407104]
  We propose PhysObjects, an object-centric dataset of 39.6K crowd-sourced and 417K automated physical concept annotations. We show that fine-tuning a vision-language model on PhysObjects improves its understanding of physical object concepts. We incorporate this physically grounded VLM in an interactive framework with a large language model-based robotic planner.
  arXiv  Detail & Related papers  (2023-09-05T20:21:03Z)
• DesCo: Learning Object Recognition with Rich Language Descriptions [93.8177229428617]
  Recent development in vision-language approaches has instigated a paradigm shift in learning visual recognition models from language supervision. We propose a new description-conditioned (DesCo) paradigm of learning object recognition models with rich language descriptions.
  arXiv  Detail & Related papers  (2023-06-24T21:05:02Z)
• Paparazzi: A Deep Dive into the Capabilities of Language and Vision Models for Grounding Viewpoint Descriptions [4.026600887656479]
  We investigate whether a state-of-the-art language and vision model, CLIP, is able to ground perspective descriptions of a 3D object. We present an evaluation framework that uses a circling camera around a 3D object to generate images from different viewpoints. We find that a pre-trained CLIP model performs poorly on most canonical views.
  arXiv  Detail & Related papers  (2023-02-13T15:18:27Z)
• LanguageRefer: Spatial-Language Model for 3D Visual Grounding [72.7618059299306]
  We develop a spatial-language model for a 3D visual grounding problem. We show that our model performs competitively on visio-linguistic datasets proposed by ReferIt3D.
  arXiv  Detail & Related papers  (2021-07-07T18:55:03Z)

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.