VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework
- URL: http://arxiv.org/abs/2502.00711v1
- Date: Sun, 02 Feb 2025 07:54:55 GMT
- Title: VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework
- Authors: Chunbai Zhang, Chao Wang, Yang Zhou, Yan Peng,
- Abstract summary: Visual reasoning refers to the task of solving questions about visual information.
We propose VIKSER (Visual Knowledge-Driven Self-Reinforcing Reasoning Framework) for visual reasoning tasks.
- Score: 8.629074194407611
- License:
- Abstract: Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing efforts are constrained by limited reasoning interpretability, while hindering by the phenomenon of underspecification in the question text. Additionally, the absence of fine-grained visual knowledge limits the precise understanding of subject behavior in visual reasoning tasks. To address these issues, we propose VIKSER (Visual Knowledge-Driven Self-Reinforcing Reasoning Framework). Specifically, VIKSER, trained using knowledge distilled from large language models, extracts fine-grained visual knowledge with the assistance of visual relationship detection techniques. Subsequently, VIKSER utilizes fine-grained visual knowledge to paraphrase the question with underspecification. Additionally, we design a novel prompting method called Chain-of-Evidence (CoE), which leverages the power of ``evidence for reasoning'' to endow VIKSER with interpretable reasoning capabilities. Meanwhile, the integration of self-reflection technology empowers VIKSER with the ability to learn and improve from its mistakes. Experiments conducted on widely used datasets demonstrate that VIKSER achieves new state-of-the-art (SOTA) results in relevant tasks.
Related papers
- DRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests [69.00444996464662]
We present DrivingVQA, a new benchmark derived from driving theory tests to evaluate visual chain-of-thought reasoning in complex real-world scenarios.
Our experiments reveal that open-source and proprietary LVLMs struggle with visual chain-of-thought reasoning under zero-shot settings.
We investigate training strategies that leverage relevant entities to improve visual reasoning.
arXiv Detail & Related papers (2025-01-08T18:31:16Z) - CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs [74.36850397755572]
CATCH addresses issues related to visual defects that cause diminished fine-grained feature perception and cumulative hallucinations in open-ended scenarios.
It is applicable to various visual question-answering tasks without requiring any specific data or prior knowledge, and generalizes robustly to new tasks without additional training.
arXiv Detail & Related papers (2024-11-19T18:27:31Z) - Visual In-Context Learning for Large Vision-Language Models [62.5507897575317]
In Large Visual Language Models (LVLMs) the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities.
We introduce a novel Visual In-Context Learning (VICL) method comprising Visual Demonstration Retrieval, Intent-Oriented Image Summarization, and Intent-Oriented Demonstration Composition.
Our approach retrieves images via ''Retrieval & Rerank'' paradigm, summarises images with task intent and task-specific visual parsing, and composes language-based demonstrations.
arXiv Detail & Related papers (2024-02-18T12:43:38Z) - Knowledge-augmented Few-shot Visual Relation Detection [25.457693302327637]
Visual Relation Detection (VRD) aims to detect relationships between objects for image understanding.
Most existing VRD methods rely on thousands of training samples of each relationship to achieve satisfactory performance.
We devise a knowledge-augmented, few-shot VRD framework leveraging both textual knowledge and visual relation knowledge.
arXiv Detail & Related papers (2023-03-09T15:38:40Z) - Can Pre-trained Vision and Language Models Answer Visual
Information-Seeking Questions? [50.29862466940209]
We introduce InfoSeek, a visual question answering dataset tailored for information-seeking questions.
We analyze various pre-trained visual question answering models and gain insights into their characteristics.
We show that accurate visual entity recognition can be used to improve performance on InfoSeek by retrieving relevant documents.
arXiv Detail & Related papers (2023-02-23T00:33:54Z) - GAMR: A Guided Attention Model for (visual) Reasoning [7.919213739992465]
Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes.
We present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR)
GAMR posits that the brain solves complex visual reasoning problems dynamically via sequences of attention shifts to select and route task-relevant visual information into memory.
arXiv Detail & Related papers (2022-06-10T07:52:06Z) - Visual Probing: Cognitive Framework for Explaining Self-Supervised Image
Representations [12.485001250777248]
Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors.
Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models.
We show the effectiveness and applicability of those analogs in the context of explaining self-supervised representations.
arXiv Detail & Related papers (2021-06-21T12:40:31Z) - Reasoning over Vision and Language: Exploring the Benefits of
Supplemental Knowledge [59.87823082513752]
This paper investigates the injection of knowledge from general-purpose knowledge bases (KBs) into vision-and-language transformers.
We empirically study the relevance of various KBs to multiple tasks and benchmarks.
The technique is model-agnostic and can expand the applicability of any vision-and-language transformer with minimal computational overhead.
arXiv Detail & Related papers (2021-01-15T08:37:55Z) - KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual
Commonsense Reasoning [4.787501955202053]
In visual commonsense reasoning (VCR) task, a machine must answer correctly and then provide a rationale justifying its answer.
We propose a novel Knowledge Enhanced Visual-and-Linguistic BERT (KVL-BERT for short) model.
Besides taking visual and linguistic contents as input, external commonsense knowledge extracted from ConceptNet is integrated into the multi-layer Transformer.
arXiv Detail & Related papers (2020-12-13T08:22:33Z) - Visual Relationship Detection with Visual-Linguistic Knowledge from
Multimodal Representations [103.00383924074585]
Visual relationship detection aims to reason over relationships among salient objects in images.
We propose a novel approach named Visual-Linguistic Representations from Transformers (RVL-BERT)
RVL-BERT performs spatial reasoning with both visual and language commonsense knowledge learned via self-supervised pre-training.
arXiv Detail & Related papers (2020-09-10T16:15:09Z)
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.