paper-with-me

홈 › Papers

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification

2025-06-17 · Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

Shortcut learning undermines model generalization to out-of-distribution data. While the literature attributes shortcuts to biases in superficial features, we show that imbalances in the semantic distribution of sample embeddings induce spurious semantic correlations, compromising model robustness. To address this issue, we propose SCISSOR (Semantic Cluster Intervention for Suppressing ShORtcut), a Siamese network-based debiasing approach that remaps the semantic space by discouraging latent clusters exploited as shortcuts. Unlike prior data-debiasing approaches, SCISSOR eliminates the need for data augmentation and rewriting. We evaluate SCISSOR on 6 models across 4 benchmarks: Chest-XRay and Not-MNIST in computer vision, and GYAFC and Yelp in NLP tasks. Compared to several baselines, SCISSOR reports +5.3 absolute points in F1 score on GYAFC, +7.3 on Yelp, +7.7 on Chest-XRay, and +1 on Not-MNIST. SCISSOR is also highly advantageous for lightweight models with ~9.5% improvement on F1 for ViT on computer vision datasets and ~11.9% for BERT on NLP. Our study redefines the landscape of model generalization by addressing overlooked semantic biases, establishing SCISSOR as a foundational framework for mitigating shortcut learning and fostering more robust, bias-resistant AI systems.

📄 PDF Abstract BibTeX arXiv:2506.14587

Code (1)

shuoyangtum/scissor 공식 구현 pytorch

Tasks

Data AugmentationRobust classification

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
BERT BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the…

Similar Papers 제목 키워드 기반

LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

2025-06-27 · Boyuan Sun, Jiaxing Zhao, Xihan Wei, Qibin Hou

In this paper, we present LLaVA-Scissor, a training-free token compression strategy designed for video multimodal large language models. Previous methods mostly attempt to compress tokens based on attention scores, but f…

Question AnsweringVideo Question AnsweringVideo Understanding

Quantifying scale-free behaviors in Rock-Paper-Scissors Models as a function of Mobility

2025-04-20 · D. Bazeia, M. Bongestab, M. J. B. Ferreira, B. F. de Oliveira 외

We investigate the scale-free behavior of the spatial rock-paper-scissors model with May-Leonard dynamics, analyzing specific quantifiers that engender the power-law feature. The main results show that an important param…

The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks

2026-06-21 · Yuhang Jiang, Xiaojing Chen arxiv

Input Diversity (DI), a random resize and pad applied at each attack iteration, is a near-default ingredient of transfer-based attacks, widely assumed to improve transferability. We show this assumption is regime-depende…

GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery

2024-11-04 · Bhupendra Solanki, Ashwin Nair, Mainak Singha, Souradeep Mukhopadhyay 외

Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown class…

Language ModelingLanguage Modelling

Mitigating Political Bias in Language Models Through Reinforced Calibration

2021-04-30 · Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu 외

Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings. In this paper, we describe me…

reinforcement-learningReinforcement Learning (RL)Word Embeddings