Unsupervised joint semantic instance segmentation, 4D reconstruction, and scene flow from multi-view video of multi-person dynamic scenes, with reported ~40% gains over prior methods.
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
7 Pith papers cite this work, alongside 500 external citations. Polarity classification is still indexing.
7
Pith papers citing it
500
external citations · Pith
abstract
Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between each task's loss. Tuning these weights by hand is a difficult and expensive process, making multi-task learning prohibitive in practice. We propose a principled approach to multi-task deep learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. This allows us to simultaneously learn various quantities with different units or scales in both classification and regression settings. We demonstrate our model learning per-pixel depth regression, semantic and instance segmentation from a monocular input image. Perhaps surprisingly, we show our model can learn multi-task weightings and outperform separate models trained individually on each task.
representative citing papers
Frozen embeddings from a pretrained heterogeneous graph transformer over a 6.9M-node metabolic-engineering knowledge graph predict fermentation titers at R²=0.41, outperforming tabular baselines (R²=0.24).
CITYMPC, a cVAE model, predicts full per-path multipath component parameters from POV images and height maps alone, matching ray-tracing accuracy with 1.29 dB power MAE and 7.25 ns delay MAE across 427k links in five cities while releasing the dataset as a benchmark.
ReCal introduces hierarchical reward decomposition and distribution-aware optimization to address ambiguous credit assignment and optimization bias in RL-based LLM routing.
Skeleton data from hand gestures is fused into RGB images and classified by an e2eET multi-stream CNN, yielding competitive accuracy on five datasets and real-time operation on consumer hardware.
CovNorm reduces parameters in domain-adaptive layers via two PCAs and a mini-adaptation layer, enabling efficient multi-domain learning with performance close to full fine-tuning.
Uncertainty-aware neural networks using Gaussian negative log-likelihood and dropout are applied to predict intrinsic magnetic properties and coercivity via graph neural networks in permanent magnet research.
citing papers explorer
-
U4D: Unsupervised 4D Dynamic Scene Understanding
Unsupervised joint semantic instance segmentation, 4D reconstruction, and scene flow from multi-view video of multi-person dynamic scenes, with reported ~40% gains over prior methods.
-
Canopy: A Heterograph Foundation Model for Metabolic Engineering
Frozen embeddings from a pretrained heterogeneous graph transformer over a 6.9M-node metabolic-engineering knowledge graph predict fermentation titers at R²=0.41, outperforming tabular baselines (R²=0.24).
-
CITYMPC: A Large-Scale Physics-Informed Benchmark and Tool for Generative Complete Multipath Wireless Channel Modeling
CITYMPC, a cVAE model, predicts full per-path multipath component parameters from POV images and height maps alone, matching ray-tracing accuracy with 1.29 dB power MAE and 7.25 ns delay MAE across 427k links in five cities while releasing the dataset as a benchmark.
-
ReCal: Reward Calibration for RL-based LLM Routing
ReCal introduces hierarchical reward decomposition and distribution-aware optimization to address ambiguous credit assignment and optimization bias in RL-based LLM routing.
-
Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN
Skeleton data from hand gestures is fused into RGB images and classified by an e2eET multi-stream CNN, yielding competitive accuracy on five datasets and real-time operation on consumer hardware.
-
Efficient Multi-Domain Network Learning by Covariance Normalization
CovNorm reduces parameters in domain-adaptive layers via two PCAs and a mini-adaptation layer, enabling efficient multi-domain learning with performance close to full fine-tuning.
-
Modelling magnetic material properties with uncertainty-aware neural networks
Uncertainty-aware neural networks using Gaussian negative log-likelihood and dropout are applied to predict intrinsic magnetic properties and coercivity via graph neural networks in permanent magnet research.