The paper is clearly written, everything proposed in the paper makes sense and seems like a natural thing to do (I had been working on the same problem, so I am entirely in favor of the pursued direction). This is not only important for giving credit to earlier works. A more crucial question in connection with these works, is whether the structured layer adds something on top of the ability of a cnn to compute embeddings for image segmentation. In experiments that I have been working on it has been really hard to beat a well-tuned, plain convnet trained with a siamese loss, and introducing a spectral normalization layer only added complications. It would be really useful if the authors could do this comparison on top of a strong baseline (e.g. the methods mentioned above) and indicate whether the resulting embeddings ( eigenvectors) are any better than those delivered from the original baselines.

Strengths of the paper are listed as follows: S1. The paper tackles the important problem of scene de-biasing for action recognition. It is of high concern for computer vision community to sanity check whether the proposed models (really) learn the dynamics of actions, and not just learn to leverage spurious bias such as the co-occurrence of the scene between actions. The authors develop a sensible solution, forcing the model to consider the human region for recognition, trying to reduce the sensitivity of action representation to the surrounding context. This is achieved by borrowing ideas from adversarial learning, that is, the scene recognition ability of action code is altered by directly using gradient reversal [8], a well-known domain confusion method in the literature since 2015.

Weaknesses: 1. Novelty - The contributions of the paper in terms of novelty are: (i) The idea of using OT based distribution matching loss, (ii) theoretical results showing that such loss results in lower error, (iii) empirical results showing that such a loss indeed results in lower error. For the crowd counting community, this may be considered as considerable contributions. However, the paper does not address if this is of interest to the broader vision/ml community - which is expected for a Neurips kind of venue. For example, the authors could have considered a broader set of applications like object detection for evaluating their method. Further, the authors should have given a better background for the recent works that have focussed on improving representation of ground-truth [2,9,10] for training the networks.

This paper presents a Simple and effective unsupervised adaptation method for Robust Object Detection (SimROD). To overcome the challenging issues of domain shift and pseudo-label noise, our method integrates a novel domain-centric augmentation method, a gradual self-labeling adaptation procedure, and a teacher-guided fine-tuning mechanism. Using our method, target domain samples can be leveraged to adapt object detection models without changing the model architecture or generating synthetic data. When applied to image corruptions and high-level cross-domain adaptation benchmarks, our method outperforms prior baselines on multiple domain adaptation benchmarks. SimROD achieves new state-of-the-art on standard real-to-synthetic and cross-camera setup benchmarks. On the image corruption benchmark, models adapted with our method achieved a relative robustness improvement of 15-25% AP50 on Pascal-C and 5-6% AP on COCO-C and Cityscapes-C. On the cross-domain benchmark, our method outperformed the best baseline performance by up to 8% AP50 on Comic dataset and up to 4% on Watercolor dataset.

This is the official PyTorch reimplementation of Polygon-RNN (CVPR 2018). This repository allows you to train new Polygon-RNN models, and run our demo tool on local machines. To get the code, please signup here. We will be using GitHub to keep track of issues with the code and to update on availability of newer versions (also available on website and through e-mail to signed up users). Note: Benchmarked forward pass speed for the tool (with 5 first points and 1 beam size) is 0.3 seconds per interaction on a TitanXp Note: Shared Encoder refers to sharing the Resnet between the graph network and the convLSTM network.

Our Brain-Inspired Computing group at IBM Research-Almaden will be presenting at the 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018) our most recent paper titled "A Low Power, High Throughput, Fully Event-Based Stereo System." The paper describes an end-to-end stereo vision system that uses exclusively spiking neural network computation and can run on neuromorphic hardware with a live streaming spiking input. Inspired by the human vision system, it uses a cluster of IBM TrueNorth chips and a pair of digital retina sensors (also known as Dynamic Vision Sensors, DVS) to extract the depth of rapidly moving objects in a scene. Our system captures scenes in 3D with low power, low latency and high throughput, which has the potential to advance the design of intelligent systems. FIGURE 1: A fully event-based stereo vision system comprised of a pair of Dynamic Vision Sensors (left) which sends their output to a cluster of TrueNorth processors (right).

A Loss.jpg Detector Source for the highly popular Android application known as "Is this loss?" T2F Text to face generation using Deep Learning. This project combines two of the recent architectures StackGAN and ProGAN for synthesizing faces from textual descriptions. Discover Feature Relationships Attempt to discover 1D relationships between all columns in a DataFrame using scikit-learn (RandomForests) and standard correlation tests (Pearson, Spearman and Kendall via Pandas). Guided Attention Inference Network An implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018).

Neural networks are known to be vulnerable to adversarial examples. In this note, we evaluate the two white-box defenses that appeared at CVPR 2018 and find they are ineffective: when applying existing techniques, we can reduce the accuracy of the defended models to 0%.