Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
University of Tehran（德黑兰大学）；Monash University（莫纳什大学）；INSERM（法国国家健康与医学研究院）；Sorbonne Universités（索邦大学）；Institut de la Vision（视觉研究所）；CNRS（法国国家科学研究中心）；Université de Toulouse（图卢兹大学）
Saeed Reza Kheradpisheh, Masoud Ghodrati, Mohammad Ganjtabesh, Timothée Masquelier
Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations.
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Yandex（扬德克斯）；University of Oxford（牛津大学）
Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example. However, their methods requires a slow and memory-consuming optimization process. We propose here an alternative approach that moves the computational burden to a learning stage. Given a single example of a texture, our approach trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer artistic style from a given image to any other image. The resulting networks are remarkably light-we…
Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality. Feed-forward absolute camera pose regression methods directly output poses by a network, but suffer from low accuracy. Meanwhile, scene coordinate based methods are accurate, but need iterative RANSAC post-processing, which brings challenges to efficient end-to-end training and inference. In order to have the best of both worlds, we propose a feed-forward method termed SC-wLS that exploits all scene coordinate estimates for weighted least squares pose …
University of California, Merced（加利福尼亚大学默塞德分校）；Adobe Research（Adobe研究院）
Recent progresses on deep discriminative and generative modeling have shown promising results on texture synthesis. However, existing feed-forward based methods trade off generality for efficiency, which suffer from many issues, such as shortage of generality (i.e., build one network per texture), lack of diversity (i.e., always produce visually identical output) and suboptimality (i.e., generate less satisfying visual effects). In this work, we focus on solving these issues for improved texture synthesis. We propose a deep generative feed-forward network which enables efficient synthesis of m…
Training deep learning models on embedded devices is typically avoided since this requires more memory, computation and power over inference. In this work, we focus on lowering the amount of memory needed for storing all activations, which are required during the backward pass to compute the gradients. Instead, during the forward pass, static Synthetic Gradient Modules (SGMs) predict gradients for each layer. This allows training the model in a feed-forward manner without having to store all activations. We tested our method on a robot grasping scenario where a robot needs to learn to grasp ne…
The strong performance of vision transformers on image classification and other vision tasks is often attributed to the design of their multi-head attention layers. However, the extent to which attention is responsible for this strong performance remains unclear. In this short report, we ask: is the attention layer even necessary? Specifically, we replace the attention layer in a vision transformer with a feed-forward layer applied over the patch dimension. The resulting architecture is simply a series of feed-forward layers applied over the patch and feature dimensions in an alternating fashi…
Brain is an organ that controls activities of all the parts of the body. Recognition of automated brain tumor in Magnetic resonance imaging (MRI) is a difficult task due to complexity of size and location variability. This automatic method detects all the type of cancer present in the body. Previous methods for tumor are time consuming and less accurate. In the present work, statistical analysis morphological and thresholding techniques are used to process the images obtained by MRI. Feed-forward back-prop neural network is used to classify the performance of tumors part of the image. This met…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Yandex；University of Oxford（牛津大学）
The recent work of Gatys et al., who characterized the style of an image by the statistics of convolutional neural network filters, ignited a renewed interest in the texture generation and image stylization problems. While their image generation technique uses a slow optimization process, recently several authors have proposed to learn generator neural networks that can produce similar outputs in one quick forward pass. While generator networks are promising, they are still inferior in visual quality and diversity compared to generation-by-optimization. In this work, we advance them in two sig…
RoMa-$Ω$: What Feed-Forward 3D Models Know About Image Matching
Chalmers University of Technology（查尔姆斯理工大学）；Mobile Perception Lab, ShanghaiTech University（上海科技大学移动感知实验室）；LIGM, Ecole des Ponts, Univ. Gustave Eiffel, CNRS（LIGM，巴黎高科路桥学校，古斯塔夫·埃菲尔大学，法国国家科学研究中心）
