paper-with-me

홈 › Papers

Overcoming Shortcut Problem in VLM for Robust Out-of-Distribution Detection

2025-01-01 · CVPR 2025 1 · Zhuo Xu, Xiang Xiang, Yifan Liang

Vision-language models (VLMs), such as CLIP, have shown remarkable capabilities in downstream tasks. However, the coupling of semantic information between the foreground and the background in images leads to significant shortcut issues that adversely affect out-of-distribution (OOD) detection abilities. When confronted with a background OOD sample, VLMs are prone to misidentifying it as in-distribution (ID) data. In this paper, we analyze the OOD problem from the perspective of shortcuts in VLMs and propose OSPCoOp which includes background decoupling and mask-guided region regularization. We first decouple images into ID-relevant and ID-irrelevant regions and utilize the latter to generate a large number of augmented OOD background samples as pseudo-OOD supervision. We then use the masks from background decoupling to adjust the model's attention, minimizing its focus on ID-irrelevant regions. To assess the model's robustness against background interference, we introduce a new OOD evaluation dataset, ImageNet-Bg, which solely consists of background images with all ID-relevant regions removed. Our method demonstrates exceptional performance in few-shot scenarios, achieving strong results even in one-shot setting, and outperforms existing methods. The code and proposed ImageNet-Bg are available at https://github.com/HAIV-Lab/OSPCoOp_Imagenet-bg.

📄 PDF Abstract BibTeX

Code (1)

haiv-lab/ospcoop_imagenet-bg 공식 구현 pytorch

Tasks

Out-of-Distribution DetectionOut of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection

2025-08-14 · Yihua Wang, Qi Jia, Cong Xu, Feiyu Chen 외 arxiv

Multimodal sarcasm detection is a complex task that requires distinguishing subtle complementary signals across modalities while filtering out irrelevant information. Many advanced methods rely on learning shortcuts from…

Emotion RecognitionSarcasm Detection

Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidance

2026-08-14 · Taraneh Younesian, Steve Azzolin, Antonio Longa, Francesco Ferrini 외 arxiv

Graph Neural Networks (GNNs) can solve prediction tasks by unintentionally exploiting shortcuts---that is, edges, nodes, and features that correlate with but are not causal for the prediction---which compromise their rel…

Active Learning

Overcoming Statistical Shortcuts for Open-ended Visual Counting

2020-06-17 · Corentin Dancette, Remi Cadene, Xinlei Chen, Matthieu Cord

Machine learning models tend to over-rely on statistical shortcuts. These spurious correlations between parts of the input and the output labels does not hold in real-world settings. We target this issue on the recent op…

Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain

2022-07-20 · Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta, Mauricio Munoz 외

Shortcut learning occurs when a deep neural network overly relies on spurious correlations in the training dataset in order to solve downstream tasks. Prior works have shown how this impairs the compositional generalizat…

Shortcut Learning in Medical Image Segmentation

2024-03-11 · Manxi Lin, Nina Weng, Kamil Mikolaj, Zahra Bashir 외

Shortcut learning is a phenomenon where machine learning models prioritize learning simple, potentially misleading cues from data that do not generalize well beyond the training set. While existing research primarily inv…

image-classificationImage ClassificationImage SegmentationMedical Image Segmentation+2