RWalk combines EWC++ and Path Integral, using Riemannian geometry to improve incremental learning by balancing forgetting and intransigence.

Arslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan et al.

Proposed multi-task multi-modal CNN predicts steering and speed, using visual and feedback data, achieving high accuracy.

Zhengyuan Yang, Yixuan Zhang, Jerry Yu et al.

MobileNetV2 introduces inverted residuals and linear bottlenecks, achieving 72.0% Top-1 accuracy on ImageNet with only 3.4M parameters and 300M MAdd.

Mark Sandler, Andrew Howard, Menglong Zhu et al.

Deep MIL ranking-based weakly supervised anomaly detection achieves 0.85 AUC on a 128-hour surveillance dataset.

Waqas Sultani, Chen Chen, Mubarak Shah

Deep features as perceptual metrics outperform traditional methods, validated on large-scale human judgment datasets across architectures and supervision levels.

Richard Zhang, Phillip Isola, Alexei A. Efros et al.

The C++-based SABCEMM simulator enables large-scale agent-based economic market modeling with efficient random number integration.

Torsten Trimborn, Philipp Otte, Simon Cramer et al.

Unified 3D deformation model captures face, hands, and body movements without markers, enabling multi-scale human motion tracking.

Hanbyul Joo, Tomas Simon, Yaser Sheikh

This paper clarifies bias issues in MMD-GAN training, introduces Kernel Inception Distance for evaluation, and demonstrates improved stability and efficiency.

Mikołaj Bińkowski, Danica J. Sutherland, Michael Arbel et al.

Proposes panoptic segmentation (PS) task combining semantic and instance segmentation, introducing the PQ metric for unified evaluation.

Alexander Kirillov, Kaiming He, Ross Girshick et al.

DeepMind Control Suite offers standardized continuous control benchmarks with MuJoCo, supporting multiple algorithms and task types for RL research.

Yuval Tassa, Yotam Doron, Alistair Muldal et al.

Deep autoencoder-based Koopman embedding with frequency parameterization enables linearization of nonlinear systems with continuous spectra.

Bethany Lusch, J. Nathan Kutz, Steven L. Brunton

Proposes a noise-tolerant loss function based on Mean Absolute Error (MAE), theoretically proven to enable risk minimization to learn true classifiers under label noise in multi-class classification.

Aritra Ghosh, Himanshu Kumar, P. S. Sastry

Proposes a method to map natural language to math expressions, improving arithmetic problem-solving accuracy.

Subhro Roy, Dan Roth

Proposes SuperPoint, a self-supervised interest point detector/describer using Homographic Adaptation, outperforming SIFT/ORB in real-time.

Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

Introduces NarrativeQA dataset emphasizing deep story comprehension; models struggle with long, complex narratives.

Tomáš Kočiský, Jonathan Schwarz, Phil Blunsom et al.

SchNet is a deep learning architecture for molecules and materials, accurately predicting chemical properties.

Kristof T. Schütt, Huziel E. Sauceda, Pieter-Jan Kindermans et al.

A few dozen poisoned samples can implant a backdoor with over 90% attack success.

Xinyun Chen, Chang Liu, Bo Li et al.

This study compares traditional, GAN-based, and neural network learned data augmentation, achieving up to 91.5% accuracy on ImageNet subsets.

Luis Perez, Jason Wang

MINOS is a high-speed multimodal indoor simulator leveraging large datasets to evaluate deep RL navigation in complex environments, highlighting current limitations and benefits of multi-sensory fusion.

Manolis Savva, Angel X. Chang, Alexey Dosovitskiy et al.

AlphaZero uses neural networks and Monte Carlo tree search to surpass human champions in chess, shogi, and Go within 24 hours of self-play training.

David Silver, Thomas Hubert, Julian Schrittwieser et al.