REVIEW 6 cited by
Auxiliary Tasks in Multi-task Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Auxiliary Tasks in Multi-task Learning
read the original abstract
Multi-task convolutional neural networks (CNNs) have shown impressive results for certain combinations of tasks, such as single-image depth estimation (SIDE) and semantic segmentation. This is achieved by pushing the network towards learning a robust representation that generalizes well to different atomic tasks. We extend this concept by adding auxiliary tasks, which are of minor relevance for the application, to the set of learned tasks. As a kind of additional regularization, they are expected to boost the performance of the ultimately desired main tasks. To study the proposed approach, we picked vision-based road scene understanding (RSU) as an exemplary application. Since multi-task learning requires specialized datasets, particularly when using extensive sets of tasks, we provide a multi-modal dataset for multi-task RSU, called synMT. More than 2.5 $\cdot$ 10^5 synthetic images, annotated with 21 different labels, were acquired from the video game Grand Theft Auto V (GTA V). Our proposed deep multi-task CNN architecture was trained on various combination of tasks using synMT. The experiments confirmed that auxiliary tasks can indeed boost network performance, both in terms of final results and training time.
Forward citations
Cited by 6 Pith papers
-
Learn2Chat: Rethinking Dyadic Talking Heads via Interaction-Modulated Monologic Priors
Dyadic head motion is generated by modulating frozen monologic speech-to-motion priors with interaction latents predicted from paired audio via monologic-anchored factorization and cross-attentive dual-stream encoding.
-
HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training
HilDA pre-trains LiDAR backbones via multi-layer and global distillation from vision models plus temporal occupancy diffusion, yielding SOTA results on detection, flow, and occupancy tasks.
-
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 ...
-
Adaptive Interpolation-Synthesis for Motion In-Betweening on Keyframe-Based Animation
The Adaptive Interpolation-Synthesis method uses a domain-aligned keypose schedule and adaptive layer to achieve state-of-the-art motion in-betweening with 3.5x speedup when integrated in Autodesk Maya.
-
Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection
A frequency-aware triple-branch network with mutual information-based decoupling and fusion losses achieves state-of-the-art deepfake detection across six benchmarks.
-
MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification
MultiDepth is a multi-task CNN architecture that adds depth-interval classification as an auxiliary task to stabilize and improve regression-based single-image depth estimation on the KITTI dataset.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.