Buchumschlag

Don't Fear Peculiar Activation Functions: EUAF and Beyond

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Qianchao, Zhang, Shijun, Zeng, Dong, Xie, Zhaoheng, Guo, Hengtao, Fan, Feng-Lei, Zeng, Tieyong
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution
von: Wang, Hongjun, et al.
Veröffentlicht: (2024)

Vision Transformers Don't Need Trained Registers
von: Jiang, Nick, et al.
Veröffentlicht: (2025)

Retinal Vessel Segmentation via Neuron Programming
von: Wu, Tingting, et al.
Veröffentlicht: (2024)

Deep ReLU Networks Have Surprisingly Simple Polytopes
von: Fan, Feng-Lei, et al.
Veröffentlicht: (2023)

Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs
von: Jiao, Pengkun, et al.
Veröffentlicht: (2025)

Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
von: Nzoyem, Roussel Desmond, et al.
Veröffentlicht: (2026)

Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
von: Kwon, Mincheol, et al.
Veröffentlicht: (2026)

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
von: Woo, Sangmin, et al.
Veröffentlicht: (2024)

Large Pre-Training Datasets Don't Always Guarantee Robustness after Fine-Tuning
von: Hwang, Jaedong, et al.
Veröffentlicht: (2024)

Don't Play Favorites: Minority Guidance for Diffusion Models
von: Um, Soobin, et al.
Veröffentlicht: (2023)

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
von: Zhao, Kairan, et al.
Veröffentlicht: (2026)

Don't Judge by the Look: Towards Motion Coherent Video Representation
von: Zhang, Yitian, et al.
Veröffentlicht: (2024)

When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
von: Goodge, Adam, et al.
Veröffentlicht: (2024)

World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty
von: Mei, Zhiting, et al.
Veröffentlicht: (2025)

Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-training
von: Zeng, Shuang, et al.
Veröffentlicht: (2023)

I Detect What I Don't Know: Incremental Anomaly Learning with Stochastic Weight Averaging-Gaussian for Oracle-Free Medical Imaging
von: Yadav, Nand Kumar, et al.
Veröffentlicht: (2025)

Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images
von: Yu, Zhuoran, et al.
Veröffentlicht: (2023)

Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos
von: Kalluri, Tarun, et al.
Veröffentlicht: (2024)

Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series
von: Loeffler, Christoffer, et al.
Veröffentlicht: (2022)

Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
von: Parmar, Mihir, et al.
Veröffentlicht: (2022)

Don't Guess, Escalate: Towards Explainable Uncertainty-Calibrated AI Forensic Agents
von: Boato, Giulia, et al.
Veröffentlicht: (2025)

A 3D SAM-Based Progressive Prompting Framework for Multi-Task Segmentation of Radiotherapy-induced Normal Tissue Injuries in Limited-Data Settings
von: Jiang, Caiwen, et al.
Veröffentlicht: (2026)

Don't Fight Hallucinations, Use Them: Estimating Image Realism using NLI over Atomic Facts
von: Rykov, Elisei, et al.
Veröffentlicht: (2025)

A Heterogeneous Graph Neural Network Fusing Functional and Structural Connectivity for MCI Diagnosis
von: Yin, Feiyu, et al.
Veröffentlicht: (2024)

Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
von: Xing, Youguang, et al.
Veröffentlicht: (2025)

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
von: Ray, Rahul D
Veröffentlicht: (2026)

When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering
von: Wu, Tao, et al.
Veröffentlicht: (2025)

TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection
von: Jiang, Lei, et al.
Veröffentlicht: (2025)

Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now
von: Sarkar, Ayush, et al.
Veröffentlicht: (2023)

Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning
von: Zeng, Xingchen, et al.
Veröffentlicht: (2024)

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
von: Guo, Guangfu, et al.
Veröffentlicht: (2026)

Deep Learning Methods for Calibrated Photometric Stereo and Beyond
von: Ju, Yakun, et al.
Veröffentlicht: (2022)

Emotion Recognition with Facial Attention and Objective Activation Functions
von: Miskow, Andrzej, et al.
Veröffentlicht: (2024)

Category Query Learning for Human-Object Interaction Classification
von: Xie, Chi, et al.
Veröffentlicht: (2023)

Prompt Group-Aware Training for Robust Text-Guided Nuclei Segmentation
von: Wu, Yonghuang, et al.
Veröffentlicht: (2026)

SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-training
von: Zeng, Shuang, et al.
Veröffentlicht: (2025)

Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
von: Zeng, Xinyu, et al.
Veröffentlicht: (2026)

Agglomerating Large Vision Encoders via Distillation for VFSS Segmentation
von: Zeng, Chengxi, et al.
Veröffentlicht: (2025)

FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training
von: Zeng, Qian, et al.
Veröffentlicht: (2024)

CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection
von: Dai, Boyang, et al.
Veröffentlicht: (2026)