We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operate on certain models exclusively and for certain problems exclusively, or only for small-scale datasets; while some features, such as batch-normalization and residual-connections, are applicable to the majority of models, tasks, and datasets. We assume that such universal features include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT) and Mish-activation. We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP (65.7% AP50) for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100. Source code is at this https URL

YOLOv4: Optimal Speed and Accuracy of Object Detection

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we identify the \emph{small data pitfall} that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K. Specifically, we show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1\%, 84.3\%, and 85.0\% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at https://github.com/Hao840/vanillaKD.

VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale

Pre-trained models for Natural Languages (NL) have been recently shown to transfer well to Programming Languages (PL) and largely benefit different intelligence code-related tasks, such as code search, clone detection, programming translation and code document generation. However, existing pre-trained methods for programming languages are mainly conducted by masked language modeling and next sentence prediction at token or graph levels. This restricted form limits their performance and transferability since PL and NL have different syntax rules and the downstream tasks require a multimodal representation. Here we introduce C3P, a Contrastive Code-Comment Pre-training approach, to solve various downstream tasks by pre-training the multi-representation features on both programming and natural syntax. The model encodes the code syntax and natural language description (comment) by two encoders and the encoded embeddings are projected into a multi-modal space for learning the latent representation. In the latent space, C3P jointly trains the code and comment encoders by the symmetric loss function, which aims to maximize the cosine similarity of the correct code-comment pairs while minimizing the similarity of unrelated pairs. We verify the empirical performance of the proposed pre-trained models on multiple downstream code-related tasks. The comprehensive experiments demonstrate that C3P outperforms previous work on the understanding tasks of code search and code clone, as well as the generation tasks of programming translation and document generation. Furthermore, we validate the transferability of C3P to the new programming language which is not seen in the pre-training stage. The results show our model surpasses all supervised methods and in some programming language cases even outperforms prior pre-trained approaches. Code is available at https://github.com/TerryPei/C3P.

Contrastive Code-Comment Pre-training

We show that the two point correlation matrix M = ( h σ i σ j i ) 1 ≤ i,j ≤ N of the Sherrington-Kirkpatrick model with zero external ﬁeld satisﬁes lim N →∞ k M − (1 + β 2 − β G ) − 1 k op = 0 in probability, in the full high temperature regime β < 1. Here, G denotes the GOE interaction matrix of the model.

The Two Point Function of the SK Model without External Field at High Temperature

Forgery facial images and videos have increased the concern of digital security. It leads to the significant development of detecting forgery data recently. However, the data, especially the videos published on the Internet, are usually compressed with lossy compression algorithms such as H.264. The compressed data could significantly degrade the performance of recent detection algorithms. The existing anti-compression algorithms focus on enhancing the performance in detecting heavily compressed data but less consider the compression adaption to the data from various compression levels. We believe creating a forgery detection model that can handle the data compressed with unknown levels is important. To enhance the performance for such models, we consider the weak compressed and strong compressed data as two views of the original data and they should have similar representation and relationships with other samples. We propose a novel anti-compression forgery detection framework by maintaining closer relations within data under different compression levels. Specifically, the algorithm measures the pair-wise similarity within data as the relations, and forcing the relations of weak and strong compressed data close to each other, thus improving the discriminate power for detecting strong compressed data. To achieve a better strong compressed data relation guided by the less compressed one, we apply video level contrastive learning for weak compressed data, which forces the model to produce similar representations within the same video and far from the negative samples. The experiment results show that the proposed algorithm could boost performance for strong compressed data while improving the accuracy rate when detecting the clean data.

Anti-Compression Contrastive Facial Forgery Detection

Entanglement witnesses (EWs) are a fundamental tool for the detection of entanglement. We investigate the inertias of bipartite EWs constructed by the partial transpose of NPT states. Fur-thermore, we ﬁnd out most of the inertias of the partial transpose of the two-qutrit bipartite NPT states. As an application, we extend our results to high dimensional states.

Chang Xu

Papers

VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale

Contrastive Code-Comment Pre-training

The Two Point Function of the SK Model without External Field at High Temperature

Anti-Compression Contrastive Facial Forgery Detection

Inertia of two-qutrit entanglement witnesses