Copertina

Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Alwis, Praditha, Chandra, Soumyadeep, Ravikumar, Deepak, Roy, Kaushik
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation
di: Soufleri, Efstathia, et al.
Pubblicazione: (2024)

The Easy Path to Robustness: Coreset Selection using Sample Hardness
di: Ramesh, Pranav, et al.
Pubblicazione: (2025)

REMAP: Regularized Matching and Partial Alignment of Video Embeddings
di: Chandra, Soumyadeep, et al.
Pubblicazione: (2025)

Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment
di: Qin, Huaiyuan, et al.
Pubblicazione: (2026)

Coresets from Trajectories: Selecting Data via Correlation of Loss Differences
di: Nagaraj, Manish, et al.
Pubblicazione: (2025)

Best of Both Worlds: Hybrid SNN-ANN Architecture for Event-based Optical Flow Estimation
di: Negi, Shubham, et al.
Pubblicazione: (2023)

Towards Visual Syntactical Understanding
di: Chowdhury, Sayeed Shafayet, et al.
Pubblicazione: (2024)

Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection
di: Zhou, Meilun, et al.
Pubblicazione: (2025)

Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation
di: Stone, Rebecca S, et al.
Pubblicazione: (2022)

Average Calibration Error: A Differentiable Loss for Improved Reliability in Image Segmentation
di: Barfoot, Theodore, et al.
Pubblicazione: (2024)

A Safety-Adapted Loss for Pedestrian Detection in Automated Driving
di: Lyssenko, Maria, et al.
Pubblicazione: (2024)

Finding the Muses: Identifying Coresets through Loss Trajectories
di: Nagaraj, Manish, et al.
Pubblicazione: (2025)

Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning
di: Moser, Brian B., et al.
Pubblicazione: (2024)

Neural Field Classifiers via Target Encoding and Classification Loss
di: Yang, Xindi, et al.
Pubblicazione: (2024)

Loss-Free Machine Unlearning
di: Foster, Jack, et al.
Pubblicazione: (2024)

A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions
di: Pihlgren, Gustav Grund, et al.
Pubblicazione: (2023)

SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion Models
di: Roy, Arani, et al.
Pubblicazione: (2025)

ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
di: Rivkin, Dmitriy, et al.
Pubblicazione: (2026)

Decoupled Kullback-Leibler Divergence Loss
di: Cui, Jiequan, et al.
Pubblicazione: (2023)

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss
di: Yu, Yunrui, et al.
Pubblicazione: (2025)

Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss
di: Zhou, Yucheng, et al.
Pubblicazione: (2026)

Detection of Cyberbullying in GIF using AI
di: Dave, Pal, et al.
Pubblicazione: (2025)

Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods
di: Hayun, Omer Ben, et al.
Pubblicazione: (2026)

Towards a Trustworthy Anomaly Detection for Critical Applications through Approximated Partial AUC Loss
di: Bougaham, Arnaud, et al.
Pubblicazione: (2025)

Batch Loss Score for Dynamic Data Pruning
di: Zhou, Qing, et al.
Pubblicazione: (2026)

Long-Tail Learning with Rebalanced Contrastive Loss
di: De Alvis, Charika, et al.
Pubblicazione: (2023)

Variation-Bounded Loss for Noise-Tolerant Learning
di: Wang, Jialiang, et al.
Pubblicazione: (2025)

A Unified Contrastive Loss for Self-Training
di: Gauffre, Aurelien, et al.
Pubblicazione: (2024)

Joint Asymmetric Loss for Learning with Noisy Labels
di: Wang, Jialiang, et al.
Pubblicazione: (2025)

DCT-CryptoNets: Scaling Private Inference in the Frequency Domain
di: Roy, Arjun, et al.
Pubblicazione: (2024)

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

RobustNeRF: Ignoring Distractors with Robust Losses
di: Sabour, Sara, et al.
Pubblicazione: (2023)

Understanding and Improving Training-free Loss-based Diffusion Guidance
di: Shen, Yifei, et al.
Pubblicazione: (2024)

Exploiting Boundary Loss for the Hierarchical Panoptic Segmentation of Plants and Leaves
di: Darbyshire, Madeleine, et al.
Pubblicazione: (2024)

Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning
di: Roy, Arani, et al.
Pubblicazione: (2025)

A Multi-Loss Strategy for Vehicle Trajectory Prediction: Combining Off-Road, Diversity, and Directional Consistency Losses
di: Rahimi, Ahmad, et al.
Pubblicazione: (2024)

IMPACT: A Generic Semantic Loss for Multimodal Medical Image Registration
di: Boussot, Valentin, et al.
Pubblicazione: (2025)

AugLoss: A Robust Augmentation-based Fine Tuning Methodology
di: Otstot, Kyle, et al.
Pubblicazione: (2022)

Task-based Loss Functions in Computer Vision: A Comprehensive Review
di: Elharrouss, Omar, et al.
Pubblicazione: (2025)

Reproducible Evaluation of Data Augmentation and Loss Functions for Brain Tumor Segmentation
di: B, Saumya
Pubblicazione: (2025)