paper-with-me

Papers

Logits-Based Finetuning

2025-05-30 · Jingyao Li, Senqiao Yang, Sitong Wu, Han Shi, Chuanyang Zheng, Hong Xu, Jiaya Jia

The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, which tend to learn shortcuts instead of comprehensive representations. In this work, we find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We deeply explore the main contributors of OOD detection and find that reconstruction-based pretext tasks have the potential to provide a generally applicable and efficacious prior, which benefits the model in learning intrinsic data distributions of the ID dataset. Specifically, we take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD). Without bells and whistles, MOOD outperforms previous SOTA of one-class OOD detection by 5.7%, multi-class OOD detection by 3.0%, and near-distribution OOD detection by 2.1%. It even defeats the 10-shot-per-class outlier exposure OOD detection, although we do not include any OOD samples for our detection. Codes are available at https://github.com/JulietLJY/MOOD.

📄 PDF Abstract BibTeX arXiv:2505.24461

Code (1)

dvlab-research/logits-based-finetuning 공식 구현 pytorch

Tasks

Out of Distribution (OOD) Detection

Similar Papers 제목 키워드 기반

Joint-Optimized Unsupervised Adversarial Domain Adaptation in Remote Sensing Segmentation with Prompted Foundation Model

2024-11-08 · Shuchang Lyu, Qi Zhao, Guangliang Cheng, Yiwei He 외

Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation (UDA-RSSeg) addresses the challenge of adapting a model trained on source domain data to target domain samples, thereby minimizing the need for anno…

DecoderDomain AdaptationSemantic SegmentationUnsupervised Domain Adaptation

Intermediate direct preference optimization

2024-08-06 · Atsushi Kojima

We propose the intermediate direct preference optimization (DPO) method to calculate the DPO loss at selected intermediate layers as an auxiliary loss for finetuning large language models (LLMs). The conventional DPO met…

Model Editing with Canonical Examples

2024-02-09 · John Hewitt, Sarah Chen, Lanruo Lora Xie, Edward Adams 외

We introduce model editing with canonical examples, a setting in which (1) a single learning example is provided per desired behavior, (2) evaluation is performed exclusively out-of-distribution, and (3) deviation from a…

Language ModellingmodelModel Editing

Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency

2026-04-27 · Yiran Huang, Lukas Thede, Massimiliano Mancini, Wenjia Xu 외 arxiv

While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment challenges on resource-constrained edge devices. Current parameter r…

Knowledge Distillation

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

2025-10-19 · Zongjian Li, Zheyuan Liu, Qihui Zhang, Bin Lin 외 arxiv

Instruction-based image editing has achieved remarkable progress; however, models solely trained via supervised fine-tuning often overfit to annotated patterns, hindering their ability to explore and generalize beyond tr…

Image Editing