Related papers: Solution for OOD-CV UNICORN Challenge 2024 Object Detection Assistance LLM Counting Ability Improvement

Solution for OOD-CV UNICORN Challenge 2024 Object Detection Assistance LLM Counting Ability Improvement

URL: http://arxiv.org/abs/2410.16287v1
Date: Sat, 05 Oct 2024 15:11:47 GMT
Title: Solution for OOD-CV UNICORN Challenge 2024 Object Detection Assistance LLM Counting Ability Improvement
Authors: Zhouyang Chi, Qingyuan Jiang, Yang Yang,
Abstract summary: This report provides a detailed description of the method that we explored and proposed in the ECCV OOD-CV UNICORN Challenge 2024. The dataset of this competition are OODCA-VQA and SketchyQA. Our approach ranked second in the final test with a score of 0.86.
Score: 6.621745547882088
License:
Abstract: This report provide a detailed description of the method that we explored and proposed in the ECCV OOD-CV UNICORN Challenge 2024, which focusing on the robustness of responses from large language models. The dataset of this competition are OODCA-VQA and SketchyQA. In order to test the robustness of the model. The organizer extended two variants of the dataset OODCV-Counterfactual and Sketchy-Challenging. There are several difficulties with these datasets. Firstly, the Sketchy-Challenging dataset uses some rarer item categories to test the model's generalization ability. Secondly, in the OODCV-Counterfactual dataset, the given problems often have inflection points and computational steps, requiring the model to recognize them during the inference process. In order to address this issue, we propose a simple yet effective approach called Object Detection Assistance Large Language Model(LLM) Counting Ability Improvement(ODAC), which focuses on using the object detection model to assist the LLM. To clarify, our approach contains two main blocks: (1)Object Detection Assistance. (2) Counterfactual Specific prompt. Our approach ranked second in the final test with a score of 0.86.

Related papers

First Place Solution to the ECCV 2024 BRAVO Challenge: Evaluating Robustness of Vision Foundation Models for Semantic Segmentation [1.8570591025615457]
We present the first place solution to the ECCV 2024 BRAVO Challenge. A model is trained on Cityscapes and its robustness is evaluated on several out-of-distribution datasets. This approach outperforms more complex existing approaches, and achieves first place in the challenge.
arXiv Detail & Related papers (2024-09-25T16:15:06Z)
Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
arXiv Detail & Related papers (2024-04-04T15:36:53Z)
Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization [34.85353544844499]
We present the first dataset with fine-grained factual error annotations named DIASUMFACT. We define fine-grained factual error detection as a sentence-level multi-label classification problem. We propose an unsupervised model ENDERANKER via candidate ranking using pretrained encoder-decoder models.
arXiv Detail & Related papers (2023-05-26T00:18:33Z)
1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track [71.12470906323298]
Generalize-then-Adapt (G&A) framework is composed of a two-stage domain generalization part and a one-stage domain adaptation part. The proposed G&A framework help us achieve the first place on the object detection leaderboard of the OOD-CV challenge.
arXiv Detail & Related papers (2023-01-12T03:50:46Z)
Exploring Multi-Modal Representations for Ambiguity Detection & Coreference Resolution in the SIMMC 2.0 Challenge [60.616313552585645]
We present models for effective Ambiguity Detection and Coreference Resolution in Conversational AI. Specifically, we use TOD-BERT and LXMERT based models, compare them to a number of baselines and provide ablation experiments. Our results show that (1) language models are able to exploit correlations in the data to detect ambiguity; and (2) unimodal coreference resolution models can avoid the need for a vision component.
arXiv Detail & Related papers (2022-02-25T12:10:02Z)
Efficient Person Search: An Anchor-Free Approach [86.45858994806471]
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN. In this work, we present an anchor-free approach to efficiently tackling this challenging task, by introducing the following dedicated designs.
arXiv Detail & Related papers (2021-09-01T07:01:33Z)
Dynamic Refinement Network for Oriented and Densely Packed Object Detection [75.29088991850958]
We present a dynamic refinement network that consists of two novel components, i.e., a feature selection module (FSM) and a dynamic refinement head (DRH) Our FSM enables neurons to adjust receptive fields in accordance with the shapes and orientations of target objects, whereas the DRH empowers our model to refine the prediction dynamically in an object-aware manner. We perform quantitative evaluations on several publicly available benchmarks including DOTA, HRSC2016, SKU110K, and our own SKU110K-R dataset.
arXiv Detail & Related papers (2020-05-20T11:35:50Z)
One-Shot Object Detection without Fine-Tuning [62.39210447209698]
We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module. We also propose novel training strategies that effectively improve detection performance. Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
arXiv Detail & Related papers (2020-05-08T01:59:23Z)

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