paper-with-me

Papers

Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition

2022-11-14 · Farid Alijani, Esa Rahtu

In this paper, we present a comprehensive study on the utility of deep convolutional neural networks with two state-of-the-art pooling layers which are placed after convolutional layers and fine-tuned in an end-to-end manner for visual place recognition task in challenging conditions, including seasonal and illumination variations. We compared extensively the performance of deep learned global features with three different loss functions, e.g. triplet, contrastive and ArcFace, for learning the parameters of the architectures in terms of fraction of the correct matches during deployment. To verify effectiveness of our results, we utilized two real world datasets in place recognition, both indoor and outdoor. Our investigation demonstrates that fine tuning architectures with ArcFace loss in an end-to-end manner outperforms other two losses by approximately 1~4% in outdoor and 1~2% in indoor datasets, given certain thresholds, for the visual place recognition tasks.

📄 PDF Abstract BibTeX arXiv:2211.07696

Code (0)

등록된 구현이 없습니다.

Tasks

TripletVisual Place Recognition

Methods 이 논문이 사용한 방법론

ArcFace ArcFace, or Additive Angular Margin Loss, is a loss function used in face recognition tasks. The softmax is traditionally used…

Similar Papers 제목 키워드 기반

SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning

2026-03-18 · Xi Ye, Wenjia Yang, Yangyang Xu, Xiaoyang Liu 외 arxiv

Image-conditioned video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term temporal coherence, especially after fine-tun…

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning

2026-05-31 · Huy Nghiem, Sy-Tuyen Ho, Sarah Wiegreffe, Hal Daumé arxiv

Emergent misalignment (EM) occurs when narrow finetuning causes a model to behave dangerously outside the finetuning task. Standard training signals can miss this shift, making reliable detection costly if it depends on …

InternLM2 Technical Report

2024-03-26 · Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen 외

The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI). However, replicating such advancements in open-source models has been c…

4kLong-Context Understanding

How to Train Your Long-Context Visual Document Model

2026-02-16 · Austin Veselka arxiv

We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-document visual question answering with measured transfer to long-context text. Whi…

Visual Question Answering

Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models

2024-08-13 · Kaiser Sun, Mark Dredze

The development of large language models leads to the formation of a pre-train-then-align paradigm, in which the model is typically pre-trained on a large text corpus and undergoes a tuning stage to align the model with …

Sensitivity