Cover Image

Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sikar, Daniel, Garcez, Artur d'Avila, Weyde, Tillman
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When to Accept Automated Predictions and When to Defer to Human Judgment?
by: Sikar, Daniel, et al.
Published: (2024)

Contrastive vision-language learning with paraphrasing and negation
by: Ngan, Kwun Ho, et al.
Published: (2025)

Know What You do Not Know: Verbalized Uncertainty Estimation Robustness on Corrupted Images in Vision-Language Models
by: Borszukovszki, Mirko, et al.
Published: (2025)

Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework
by: Bhatt, Neel P., et al.
Published: (2024)

Specifying What You Know or Not for Multi-Label Class-Incremental Learning
by: Zhang, Aoting, et al.
Published: (2025)

Does CLIP Know My Face?
by: Hintersdorf, Dominik, et al.
Published: (2022)

Generative Models: What Do They Know? Do They Know Things? Let's Find Out!
by: Du, Xiaodan, et al.
Published: (2023)

Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
by: Alwis, Praditha, et al.
Published: (2026)

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

Knowing the Unknown: Interpretable Open-World Object Detection via Concept Decomposition Model
by: Lv, Xueqiang, et al.
Published: (2026)

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition
by: Xu, Jiawen, et al.
Published: (2024)

FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time Series
by: Su, Qiqi, et al.
Published: (2023)

Rethinking Attention: Polynomial Alternatives to Softmax in Transformers
by: Saratchandran, Hemanth, et al.
Published: (2024)

You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models
by: Slyman, Eric, et al.
Published: (2024)

Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning
by: Zhou, Hongkuan, et al.
Published: (2025)

Evaluation of autonomous systems under data distribution shifts
by: Sikar, Daniel, et al.
Published: (2024)

PDEInvBench: A Comprehensive Dataset and Design Space Exploration of Neural Networks for PDE Inverse Problems
by: Goel, Divyam, et al.
Published: (2026)

Does FLUX Already Know How to Perform Physically Plausible Image Composition?
by: Lu, Shilin, et al.
Published: (2025)

Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
by: Verma, Gaurav, et al.
Published: (2024)

$ε$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
by: Wang, Jialiang, et al.
Published: (2025)

Softmax-free Linear Transformers
by: Lu, Jiachen, et al.
Published: (2022)

"I Know It When I See It": Mood Spaces for Connecting and Expressing Visual Concepts
by: Yang, Huzheng, et al.
Published: (2025)

Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
by: Oh, Yoojin, et al.
Published: (2025)

Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space
by: Franzen, Daniel, et al.
Published: (2026)

DragGANSpace: Latent Space Exploration and Control for GANs
by: Odendaal, Kirsten, et al.
Published: (2025)

Analytical Softmax Temperature Setting from Feature Dimensions for Model- and Domain-Robust Classification
by: Hasegawa, Tatsuhito, et al.
Published: (2025)

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
by: Ren, Baochang, et al.
Published: (2025)

Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications
by: Olivi, Leonardo, et al.
Published: (2025)

Real-Time Damage Detection in Fiber Lifting Ropes Using Lightweight Convolutional Neural Networks
by: Jalonen, Tuomas, et al.
Published: (2023)

Explorations in Texture Learning
by: Hoak, Blaine, et al.
Published: (2024)

What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?
by: Tu, Weijie, et al.
Published: (2024)

An Adaptive Tangent Feature Perspective of Neural Networks
by: LeJeune, Daniel, et al.
Published: (2023)

Understanding Neural Network Systems for Image Analysis using Vector Spaces and Inverse Maps
by: Pattichis, Rebecca, et al.
Published: (2024)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
by: Zhang, Yue, et al.
Published: (2026)

Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimation
by: Kinoshita, Genki, et al.
Published: (2023)

Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers
by: Bill, Eric Tillman, et al.
Published: (2025)

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
by: Wang, Ziqiao, et al.
Published: (2025)

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

Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentations
by: Mitcheff, Mahsa, et al.
Published: (2025)

Revealing the Utilized Rank of Subspaces of Learning in Neural Networks
by: Garg, Isha, et al.
Published: (2024)