Instance-level segmentation for autonomous driving using deep densely connected MRFs, boosting KITTI benchmark performance.

Ziyu Zhang, Sanja Fidler, Raquel Urtasun

Proposes Quantized CNN (Q-CNN) achieving 4-6× speed-up and 15-20× compression with only 1% accuracy loss.

Jiaxiang Wu, Cong Leng, Yuhang Wang et al.

ShapeNet is a large-scale, richly-annotated 3D model repository with over 3 million models, supporting semantic, geometric, and physical annotations for shape understanding.

Angel X. Chang, Thomas Funkhouser, Leonidas Guibas et al.

Proposes Minimum Risk Training (MRT) for end-to-end neural machine translation, outperforming maximum likelihood estimation with up to +8.61 BLEU points.

Shiqi Shen, Yong Cheng, Zhongjun He et al.

Proposes PPDB-based universal paraphrastic sentence embeddings; simple models outperform LSTMs in cross-domain tasks.

John Wieting, Mohit Bansal, Kevin Gimpel et al.

Proposes NetVLAD, an end-to-end trainable CNN with a differentiable VLAD layer, achieving significant improvements in large-scale place recognition.

Relja Arandjelović, Petr Gronat, Akihiko Torii et al.

Multi-scale context aggregation using dilated convolutions improves semantic segmentation accuracy.

Fisher Yu, Vladlen Koltun

Recurrent neural network-based session recommender, outperforming traditional methods with 20%+ improvements in Recall@20.

Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas et al.

Introduced Bilateral Inception module for superpixel CNNs, enhancing semantic segmentation accuracy.

Raghudeep Gadde, Varun Jampani, Martin Kiefel et al.

Neural Programmer-Interpreter (NPI) combines LSTM core, persistent program memory, and environment encoders to enable multi-task program learning and generalization.

Scott Reed, Nando de Freitas

OpenMax layer combined with Meta-Recognition estimates unknown class probability, improving open set recognition and rejecting fooling/adversarial samples.

Abhijit Bendale, Terrance Boult

Frank-Wolfe variants achieve global linear convergence, effective for flow polytope constraints.

Simon Lacoste-Julien, Martin Jaggi

Proposes Structural-RNN (S-RNN), combining high-level spatio-temporal graphs with RNNs, improving modeling of human motion and object interactions.

Ashesh Jain, Amir R. Zamir, Silvio Savarese et al.

Proposal Flow leverages multi-scale object proposals and geometric constraints for image correspondence, outperforming existing semantic flow methods.

Bumsub Ham, Minsu Cho, Cordelia Schmid et al.

Defensive distillation cuts adversarial success from 95.89% to 0.45%.

Nicolas Papernot, Patrick McDaniel, Xi Wu et al.

Introduces a polynomial-time algorithm for optimizing star-convex functions, overcoming gradient dependence and smoothness constraints.

Jasper C. H. Lee, Paul Valiant

Geometric analysis reveals that wider neural networks have higher probability of initializing in basins with low objective values, facilitating optimization.

Itay Safran, Ohad Shamir

Semantic segmentation using CNN and Domain Transform, achieving 66.35% mIOU with improved boundary precision.

Liang-Chieh Chen, Jonathan T. Barron, George Papandreou et al.

Neural Module Networks combine deep learning with linguistic structure, achieving top results on VQA datasets.

Jacob Andreas, Marcus Rohrbach, Trevor Darrell et al.

Introduces Boundary Neural Field (BNF) to enhance semantic segmentation by integrating boundary cues with FCN predictions.

Gedas Bertasius, Jianbo Shi, Lorenzo Torresani