Active learning (AL) can significantly reduce the overall amount of training data required to achieve near-optimal performance. Despite the notable advancements in active learning for image recognition, there remains a lack of a lightweight active learning method specifically designed for object detection. In this paper, we embark on an investigation into the uncertainty of predicted instances’ boxes within the object detection process, addressing three distinct types of uncertainty related to position, size, and category in object detection. We define proposals after regression as instances and feature instances belong to one object as instances bags. We estimate image uncertainty by calculating the position, size, and category variances of these instance bags. In object detection tasks, experiments validate that the proposed method significantly reduces computational complexity and outperforms state-of-the-art methods by a substantial margin.

Learning generative image models from various domains efficiently needs transferring knowledge from an image synthesis model trained on a large dataset. We present a recipe for learning vision transformers by generative knowledge transfer. We base our framework on generative vision transformers representing an image as a sequence of visual tokens with the autoregressive or non-autoregressive transformers. To adapt to a new domain, we employ prompt tuning, which prepends learnable tokens called prompts to the image token sequence and introduces a new prompt design for our task. We study on a variety of visual domains with varying amounts of training images. We show the effectiveness of knowledge transfer and a significantly better image generation quality.11https://github.com/google-research/generative_transfer

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.

Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts. However, ambiguities inherent in natural language, and out-of-distribution effects make it hard to synthesize arbitrary image styles, leveraging a specific design pattern, texture or material. In this paper, we introduce *StyleDrop*, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model. StyleDrop is extremely versatile and captures nuances and details of a user-provided style, such as color schemes, shading, design patterns, and local and global effects. StyleDrop works by efficiently learning a new style by fine-tuning very few trainable parameters (less than 1\% of total model parameters), and improving the quality via iterative training with either human or automated feedback. Better yet, StyleDrop is able to deliver impressive results even when the user supplies only a *single* image specifying the desired style. An extensive study shows that, for the task of style tuning text-to-image models, StyleDrop on Muse convincingly outperforms other methods, including DreamBooth and textual inversion on Imagen or Stable Diffusion. More results are available at our project website: [https://styledrop.github.io](https://styledrop.github.io).

The current method obtains the frequency of occurrence of abnormal data detected in the adjacent regions through reading between the sensor and the adjacent conversion data, and uses the frequency of occurrence of abnormal data to describe the spatial correlation, according to readings of sensor data using the Bayesian analysis method of sensor to determine whether the sensor is abnormal. But this method has the problem of low detection accuracy. For this reason, this paper proposes a method to detect the fuzzy breakpoint of data in the massive dynamic data flow. Firstly, this method used the amplitude difference method to determine the abnormal data amplitude and the discrete point difference of data fuzzy breakpoint, and then used the wavelet transform to extract the features of inflection point of the data fuzzy breakpoint. Combined with the features of inflection point of the extracted data fuzzy breakpoint, we carried out the support vector machine classification, and detected the data fuzzy breakpoints in the massive dynamic data flow. Experimental results show that the proposed method can effectively improve the accuracy of fuzzy breakpoint detection.

Many algorithms for data mining or indexing time series data do not operate directly on the raw data, but instead they use alternative representations that include transforms, quantization, approximation, and multi-resolution abstractions. Choosing the best representation and abstraction level for a given task/dataset is arguably the most critical step in time series data mining. In this work, we investigate the problem of discovering the natural intrinsic representation model, dimensionality and alphabet cardinality of a time series. The ability to automatically discover these intrinsic features has implications beyond selecting the best parameters for particular algorithms, as characterizing data in such a manner is useful in its own right and an important sub-routine in algorithms for classification, clustering and outlier discovery. We will frame the discovery of these intrinsic features in the Minimal Description Length framework. Extensive empirical tests show that our method is simpler, more general and more accurate than previous methods, and has the important advantage of being essentially parameter-free.

The discovery of repeated structure, i.e. motifs/near-duplicates, is often the first step in exploratory data mining. As such, the last decade has seen extensive research efforts in motif discovery algorithms for text, DNA, time series, protein sequences, graphs, images, and video. Surprisingly, there has been less attention devoted to finding repeated patterns in audio sequences, in spite of their ubiquity in science and entertainment. While there is significant work for the special case of motifs in music, virtually all this work makes many assumptions about data (often to the point of being genre specific) and thus these algorithms do not generalize to audio sequences containing animal vocalizations, industrial processes, or a host of other domains that we may wish to explore. In this work we introduce a novel technique for finding audio motifs. Our method does not require any domain-specific tuning and is essentially parameter-free. We demonstrate our algorithm on very diverse domains, finding audio motifs in laboratory mice vocalizations, wild animal sounds, music, and human speech. Our experiments demonstrate that our ideas are effective in discovering objectively correct or subjectively plausible motifs. Moreover, we show our novel probabilistic early abandoning approach is efficient, being two to three orders of magnitude faster than brute-force search, and thus faster than real-time for most problems.

Time series classification has been an active area of research in the data mining community for over a decade, and significant progress has been made in the tractability and accuracy of learning. However, virtually all work assumes a one-time training session in which labeled examples of all the concepts to be learned are provided. This assumption may be valid in a handful of situations, but it does not hold in most medical and scientific applications where we initially may have only the vaguest understanding of what concepts can be learned. Based on this observation, we propose a never-ending learning framework for time series in which an agent examines an unbounded stream of data and occasionally asks a teacher (which may be a human or an algorithm) for a label. We demonstrate the utility of our ideas with experiments in domains as diverse as medicine, entomology, wildlife monitoring, and human behavior analyses.

Monitoring animals by the sounds they produce is an important and challenging task, whether the application is outdoors in a natural habitat, or in the controlled environment of a laboratory setting. In the former case the density and diversity of animal sounds can act as a measure of biodiversity. In the latter case, researchers often create control and treatment groups of animals, expose them to different interventions, and test for different outcomes. One possible manifestation of different outcomes may be changes in the bioacoustics of the animals. With such a plethora of important applications, there have been significant efforts to build bioacoustic classification tools. However, we argue that most current tools are severely limited. They often require the careful tuning of many parameters (and thus huge amounts of training data), they are too computationally expensive for deployment in resource-limited sensors, they are specialized for a very small group of species, or they are simply not accurate enough to be useful. In this work we introduce a novel bioacoustic recognition/classification framework that mitigates or solves all of the above problems. We propose to classify animal sounds in the visual space, by treating the texture of their spectrograms as an acoustic fingerprint using a recently introduced parameter-free texture measure as a distance measure. We further show that by searching for the most representative acoustic fingerprint we can significantly outperform other techniques in terms of speed and accuracy.

Most algorithms for mining or indexing time series data do not operate directly on the original data, but instead they consider alternative representations that include transforms, quantization, approximation, and multi-resolution abstractions. Choosing the best representation and abstraction level for a given task/dataset is arguably the most critical step in time series data mining. In this paper, we investigate techniques to discover the natural intrinsic representation model, dimensionality and alphabet cardinality of a time series. The ability to discover these intrinsic features has implications beyond selecting the best parameters for particular algorithms, as characterizing data in such a manner is useful in its own right and an important sub-routine in algorithms for classification, clustering and outlier discovery. We will frame the discovery of these intrinsic features in the Minimal Description Length (MDL) framework. Extensive empirical tests show that our method is simpler, more general and significantly more accurate than previous methods, and has the important advantage of being essentially parameter-free.