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

This paper contributes a new high quality dataset for person re-identification, named "Market-1501". Generally, current datasets: 1) are limited in scale, 2) consist of hand-drawn bboxes, which are unavailable under realistic settings, 3) have only one ground truth and one query image for each identity (close environment). To tackle these problems, the proposed Market-1501 dataset is featured in three aspects. First, it contains over 32,000 annotated bboxes, plus a distractor set of over 500K images, making it the largest person re-id dataset to date. Second, images in Market-1501 dataset are produced using the Deformable Part Model (DPM) as pedestrian detector. Third, our dataset is collected in an open system, where each identity has multiple images under each camera. As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor. We view person re-identification as a special task of image search. In experiment, we show that the proposed descriptor yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large-scale 500k dataset.

/pdf/scalable-person-re-identification-a-benchmark-iiee63lja2.pdf

Scalable Person Re-identification: A Benchmark

The author's preface gives an outline: "This book is about weakconvergence methods in metric spaces, with applications sufficient to show their power and utility. The Introduction motivates the definitions and indicates how the theory will yield solutions to problems arising outside it. Chapter 1 sets out the basic general theorems, which are then specialized in Chapter 2 to the space C[0, l ] of continuous functions on the unit interval and in Chapter 3 to the space D [0, 1 ] of functions with discontinuities of the first kind. The results of the first three chapters are used in Chapter 4 to derive a variety of limit theorems for dependent sequences of random variables. " The book develops and expands on Donsker's 1951 and 1952 papers on the invariance principle and empirical distributions. The basic random variables remain real-valued although, of course, measures on C[0, l ] and D[0, l ] are vitally used. Within this framework, there are various possibilities for a different and apparently better treatment of the material. More of the general theory of weak convergence of probabilities on separable metric spaces would be useful. Metrizability of the convergence is not brought up until late in the Appendix. The close relation of the Prokhorov metric and a metric for convergence in probability is (hence) not mentioned (see V. Strassen, Ann. Math. Statist. 36 (1965), 423-439; the reviewer, ibid. 39 (1968), 1563-1572). This relation would illuminate and organize such results as Theorems 4.1, 4.2 and 4.4 which give isolated, ad hoc connections between weak convergence of measures and nearness in probability. In the middle of p. 16, it should be noted that C*(S) consists of signed measures which need only be finitely additive if 5 is not compact. On p. 239, where the author twice speaks of separable subsets having nonmeasurable cardinal, he means "discrete" rather than "separable." Theorem 1.4 is Ulam's theorem that a Borel probability on a complete separable metric space is tight. Theorem 1 of Appendix 3 weakens completeness to topological completeness. After mentioning that probabilities on the rationals are tight, the author says it is an

Convergence of probability measures

Recent advances in convolutional neural networks

The PASCAL Visual Object Classes Challenge

Color constancy aims to restore the constant colors of a scene under different illuminants. However, due to the existence of camera spectral sensitivity, the network trained on a certain sensor, cannot work well on others. Also, since the training datasets are collected in certain environments, the diversity of illuminants is limited for complex real world prediction. In this paper, we tackle these problems via two aspects. First, we propose cross-sensor self-supervised training to train the network. In detail, we consider both the general sRGB images and the white-balanced RAW images from current available datasets as the white-balanced agents. Then, we train the network by randomly sampling the artificial illuminants in a sensor-independent manner for scene relighting and supervision. Second, we analyze a previous cascaded framework and present a more compact and accurate model by sharing the backbone parameters with learning attention specifically. Experiments show that our cross-sensor model and single-sensor model outperform other state-of-the-art methods by a large margin on cross and single sensor evaluations, respectively, with only 16% parameters of the previous best model.

Learning Enriched Illuminants for Cross and Single Sensor Color Constancy

We introduce a new measure on secrecy, which is established based on rate-distortion theory. It is named \emph{security rate}, which is the minimum (infimum) of the additional rate needed to reconstruct the source within target distortion level with any positive probability for wiretapper. It denotes the minimum distance in information metric (bits) from what wiretapper has received to any decrypted reconstruction (where decryption is defined as reconstruction within target distortion level with some positive possibility). By source coding theorem, it is equivalent to a distortion-based equivocation $\mathop{\min}\limits _{p\left(v^{n}|s^{n},m\right):Ed\left(S^{n},V^{n}\right)\le D_{E}}\frac{1}{n}I\left(S^{n};V^{n}|M\right)$ which can be seen as a direct extension of equivocation $\frac{1}{n}H\left(S^{n}|M\right)$ to lossy decryption case, given distortion level $D_{E}$ and the received (encrypted) message $M$ of wiretapper. In this paper, we study it in Shannon cipher system with lossless communication, where a source is transmitted from sender to legitimate receiver secretly and losslessly, and also eavesdropped by a wiretapper. We characterize the admissible region of secret key rate, coding rate of the source, wiretapper distortion, and security rate (distortion-based equivocation). Since the security rate equals the distortion-based equivocation, and the equivocation is a special case of the distortion-based equivocation (with Hamming distortion measure and $D_{E}=0$), this gives an answer for the meaning of the maximum equivocation.

Secrecy Communication with Security Rate Measure.

An embodiment of the invention discloses a method for detecting frame types and a device The method includes detecting playing time of each frame; and determining that a current frame is a bidirectional prediction coded frame B if the playing time of the current frame is shorter than the maximum playing time of a received frame By the aid of the method in the technical scheme, coding sequence of frames in different types and the relationship between former datum quantities and latter datum quantities of the frames in different types are combined, the frame types are judged under the condition without decoding or clearing load, influence of attenuation factors is eliminated, and accuracy of detection of the frame types is improved

Method for detecting frame types and device

Segment anything model (SAM) has achieved great success in the field of natural image segmentation. Nevertheless, SAM tends to classify shadows as background, resulting in poor segmentation performance for shadow detection task. In this paper, we propose an simple but effective approach for fine tuning SAM to detect shadows. Additionally, we also combine it with long short-term attention mechanism to extend its capabilities to video shadow detection. Specifically, we first fine tune SAM by utilizing shadow data combined with sparse prompts and apply the fine-tuned model to detect a specific frame (e.g., first frame) in the video with a little user assistance. Subsequently, using the detected frame as a reference, we employ a long short-term network to learn spatial correlations between distant frames and temporal consistency between contiguous frames, thereby achieving shadow information propagation across frames. Extensive experimental results demonstrate that our method outperforms the state-of-the-art techniques, with improvements of 17.2% and 3.3% in terms of MAE and IoU, respectively, validating the effectiveness of our method.

Detect Any Shadow: Segment Anything for Video Shadow Detection

Existing face forgery detection models try to discriminate fake images by detecting only spatial artifacts (e.g., generative artifacts, blending) or mainly temporal artifacts (e.g., flickering, discontinuity). They may experience significant performance degradation when facing out-domain artifacts. In this paper, we propose to capture both spatial and temporal artifacts in one model for face forgery detection. A simple idea is to leverage a spatiotemporal model (3D ConvNet). However, we find that it may easily rely on one type of artifact and ignore the other. To address this issue, we present a novel training strategy called AltFreezing for more general face forgery detection. The AltFreezing aims to encourage the model to detect both spatial and temporal artifacts. It divides the weights of a spatiotemporal network into two groups: spatial-related and temporal-related. Then the two groups of weights are alternately frozen during the training process so that the model can learn spatial and temporal features to distinguish real or fake videos. Furthermore, we introduce various video-level data augmentation methods to improve the generalization capability of the forgery detection model. Extensive experiments show that our framework outperforms existing methods in terms of generalization to unseen manipulations and datasets. Code is available at https: //github.com/ZhendongWang6/AltFreezing.

Houqiang Li

Papers

Learning Enriched Illuminants for Cross and Single Sensor Color Constancy

Secrecy Communication with Security Rate Measure.

Method for detecting frame types and device

Detect Any Shadow: Segment Anything for Video Shadow Detection

AltFreezing for More General Video Face Forgery Detection