Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTriplet is All You Need with Random Mappings for Unsupervised Visual Representation Learning
231
0
0.0
(
0
)
Added by
Wenbin Li
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Contrastive self-supervised learning (SSL) has achieved great success in unsupervised visual representation learning by maximizing the similarity between two augmented views of the same image (positive pairs) and simultaneously contrasting other different images (negative pairs). However, this type of methods, such as SimCLR and MoCo, relies heavily on a large number of negative pairs and thus requires either large batches or memory banks. In contrast, some recent non-contrastive SSL methods, such as BYOL and SimSiam, attempt to discard negative pairs by introducing asymmetry and show remarkable performance. Unfortunately, to avoid collapsed solutions caused by not using negative pairs, these methods require sophisticated asymmetry designs. In this paper, we argue that negative pairs are still necessary but one is sufficient, i.e., triplet is all you need. A simple triplet-based loss can achieve surprisingly good performance without requiring large batches or asymmetry. Moreover, we observe that unsupervised visual representation learning can gain significantly from randomness. Based on this observation, we propose a simple plug-in RandOm MApping (ROMA) strategy by randomly mapping samples into other spaces and enforcing these randomly projected samples to satisfy the same correlation requirement. The proposed ROMA strategy not only achieves the state-of-the-art performance in conjunction with the triplet-based loss, but also can further effectively boost other SSL methods.
rate research
Read More
We provide a construction for categorical representation learning and introduce the foundations of $textit{categorifier}$. The central theme in representation learning is the idea of $textbf{everything to vector}$. Every object in a dataset $mathcal{S}$ can be represented as a vector in $mathbb{R}^n$ by an $textit{encoding map}$ $E: mathcal{O}bj(mathcal{S})tomathbb{R}^n$. More importantly, every morphism can be represented as a matrix $E: mathcal{H}om(mathcal{S})tomathbb{R}^{n}_{n}$. The encoding map $E$ is generally modeled by a $textit{deep neural network}$. The goal of representation learning is to design appropriate tasks on the dataset to train the encoding map (assuming that an encoding is optimal if it universally optimizes the performance on various tasks). However, the latter is still a $textit{set-theoretic}$ approach. The goal of the current article is to promote the representation learning to a new level via a $textit{category-theoretic}$ approach. As a proof of concept, we provide an example of a text translator equipped with our technology, showing that our categorical learning model outperforms the current deep learning models by 17 times. The content of the current article is part of the recent US patent proposal (patent application number: 63110906).
Region proposal mechanisms are essential for existing deep learning approaches to object detection in images. Although they can generally achieve a good detection performance under normal circumstances, their recall in a scene with extreme cases is unacceptably low. This is mainly because bounding box annotations contain much environment noise information, and non-maximum suppression (NMS) is required to select target boxes. Therefore, in this paper, we propose the first anchor-free and NMS-free object detection model called weakly supervised multimodal annotation segmentation (WSMA-Seg), which utilizes segmentation models to achieve an accurate and robust object detection without NMS. In WSMA-Seg, multimodal annotations are proposed to achieve an instance-aware segmentation using weakly supervised bounding boxes; we also develop a run-data-based following algorithm to trace contours of objects. In addition, we propose a multi-scale pooling segmentation (MSP-Seg) as the underlying segmentation model of WSMA-Seg to achieve a more accurate segmentation and to enhance the detection accuracy of WSMA-Seg. Experimental results on multiple datasets show that the proposed WSMA-Seg approach outperforms the state-of-the-art detectors.
We present a novel attention-based mechanism for learning enhanced point features for tasks such as point cloud classification and segmentation. Our key message is that if the right attention point is selected, then one point is all you need -- not a sequence as in a recurrent model and not a pre-selected set as in all prior works. Also, where the attention point is should be learned, from data and specific to the task at hand. Our mechanism is characterized by a new and simple convolution, which combines the feature at an input point with the feature at its associated attention point. We call such a point a directional attention point (DAP), since it is found by adding to the original point an offset vector that is learned by maximizing the task performance in training. We show that our attention mechanism can be easily incorporated into state-of-the-art point cloud classification and segmentation networks. Extensive experiments on common benchmarks such as ModelNet40, ShapeNetPart, and S3DIS demonstrate that our DAP-enabled networks consistently outperform the respective original networks, as well as all other competitive alternatives, including those employing pre-selected sets of attention points.
Disentangled generative models are typically trained with an extra regularization term, which encourages the traversal of each latent factor to make a distinct and independent change at the cost of generation quality. When traversing the latent space of generative models trained without the disentanglement term, the generated samples show semantically meaningful change, raising the question: do generative models know disentanglement? We propose an unsupervised and model-agnostic method: Disentanglement via Contrast (DisCo) in the Variation Space. DisCo consists of: (i) a Navigator providing traversal directions in the latent space, and (ii) a $Delta$-Contrastor composed of two shared-weight Encoders, which encode image pairs along these directions to disentangled representations respectively, and a difference operator to map the encoded representations to the Variation Space. We propose two more key techniques for DisCo: entropy-based domination loss to make the encoded representations more disentangled and the strategy of flipping hard negatives to address directions with the same semantic meaning. By optimizing the Navigator to discover disentangled directions in the latent space and Encoders to extract disentangled representations from images with Contrastive Learning, DisCo achieves the state-of-the-art disentanglement given pretrained non-disentangled generative models, including GAN, VAE, and Flow. Project page at https://github.com/xrenaa/DisCo.
We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named TimeSformer, adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Our experimental study compares different self-attention schemes and suggests that divided attention, where temporal attention and spatial attention are separately applied within each block, leads to the best video classification accuracy among the design choices considered. Despite the radically new design, TimeSformer achieves state-of-the-art results on several action recognition benchmarks, including the best reported accuracy on Kinetics-400 and Kinetics-600. Finally, compared to 3D convolutional networks, our model is faster to train, it can achieve dramatically higher test efficiency (at a small drop in accuracy), and it can also be applied to much longer video clips (over one minute long). Code and models are available at: https://github.com/facebookresearch/TimeSformer.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
