最近的工作表明，学习的图像压缩策略可以倾销标准的手工制作压缩算法，这些压缩算法已经开发了几十年的速率 - 失真折衷的研究。随着计算机视觉的不断增长的应用，来自可压缩表示的高质量图像重建通常是次要目标。压缩，可确保计算机视觉任务等高精度，例如图像分割，分类和检测，因此具有跨各种设置的显着影响的可能性。在这项工作中，我们开发了一个框架，它产生适合人类感知和机器感知的压缩格式。我们表明可以了解到表示，同时优化核心视觉任务的压缩和性能。我们的方法允许直接从压缩表示培训模型，并且这种方法会产生新任务和低拍学习设置的性能。我们呈现出与标准高质量JPG相比细分和检测性能提高的结果，但是在每像素的比特方面，表示表示的表示性比率为4至10倍。此外，与天真的压缩方法不同，在比标准JEPG的十倍小的级别，我们格式培训的分段和检测模型仅在性能下遭受轻微的降级。

Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational requirements, introduce invariance and prevent over-training. These benefits of pooling come at the cost of reduced localization accuracy. We introduce a novel architecture which includes an efficient 'position refinement' model that is trained to estimate the joint offset location within a small region of the image. This refinement model is jointly trained in cascade with a state-of-the-art ConvNet model [21] to achieve improved accuracy in human joint location estimation. We show that the variance of our detector approaches the variance of human annotations on the FLIC [20] dataset and outperforms all existing approaches on the MPII-human-pose dataset [1].

Periocular refers to the region of the face that surrounds the eye socket. This is a feature-rich area that can be used by itself to determine the identity of an individual. It is especially useful when the iris or the face cannot be reliably acquired. This can be the case of unconstrained or uncooperative scenarios, where the face may appear partially occluded, or the subject-to-camera distance may be high. However, it has received revived attention during the pandemic due to masked faces, leaving the ocular region as the only visible facial area, even in controlled scenarios. This paper discusses the state-of-the-art of periocular biometrics, giving an overall framework of its most significant research aspects.

Detecting actions in untrimmed videos should not be limited to a small, closed set of classes. We present a simple, yet effective strategy for open-vocabulary temporal action detection utilizing pretrained image-text co-embeddings. Despite being trained on static images rather than videos, we show that image-text co-embeddings enable openvocabulary performance competitive with fully-supervised models. We show that the performance can be further improved by ensembling the image-text features with features encoding local motion, like optical flow based features, or other modalities, like audio. In addition, we propose a more reasonable open-vocabulary evaluation setting for the ActivityNet data set, where the category splits are based on similarity rather than random assignment.

Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks including zero-shot classification, retrieval, linear probing, and end-to-end fine-tuning. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures and similar training recipes. We open-source our evaluation workflow and all models, including the largest public CLIP models, to ensure reproducibility and make scaling laws research more accessible. Source code and instructions to reproduce this study will be available at https://github.com/LAION-AI/scaling-laws-openclip

Electronic Health Records (EHRs) hold detailed longitudinal information about each patient's health status and general clinical history, a large portion of which is stored within the unstructured text. Temporal modelling of this medical history, which considers the sequence of events, can be used to forecast and simulate future events, estimate risk, suggest alternative diagnoses or forecast complications. While most prediction approaches use mainly structured data or a subset of single-domain forecasts and outcomes, we processed the entire free-text portion of EHRs for longitudinal modelling. We present Foresight, a novel GPT3-based pipeline that uses NER+L tools (i.e. MedCAT) to convert document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events such as disorders, medications, symptoms and interventions. Since large portions of EHR data are in text form, such an approach benefits from a granular and detailed view of a patient while introducing modest additional noise. On tests in two large UK hospitals (King's College Hospital, South London and Maudsley) and the US MIMIC-III dataset precision@10 of 0.80, 0.81 and 0.91 was achieved for forecasting the next biomedical concept. Foresight was also validated on 34 synthetic patient timelines by 5 clinicians and achieved relevancy of 97% for the top forecasted candidate disorder. Foresight can be easily trained and deployed locally as it only requires free-text data (as a minimum). As a generative model, it can simulate follow-on disorders, medications and interventions for as many steps as required. Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk estimation, virtual trials and clinical research to study the progression of diseases, simulate interventions and counterfactuals, and for educational purposes.

In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it to answer knowledge-intensive queries. REVEAL consists of four key components: the memory, the encoder, the retriever and the generator. The large-scale memory encodes various sources of multimodal world knowledge (e.g. image-text pairs, question answering pairs, knowledge graph triplets, etc) via a unified encoder. The retriever finds the most relevant knowledge entries in the memory, and the generator fuses the retrieved knowledge with the input query to produce the output. A key novelty in our approach is that the memory, encoder, retriever and generator are all pre-trained end-to-end on a massive amount of data. Furthermore, our approach can use a diverse set of multimodal knowledge sources, which is shown to result in significant gains. We show that REVEAL achieves state-of-the-art results on visual question answering and image captioning.

Likelihood-based deep generative models have recently been shown to exhibit pathological behaviour under the manifold hypothesis as a consequence of using high-dimensional densities to model data with low-dimensional structure. In this paper we propose two methodologies aimed at addressing this problem. Both are based on adding Gaussian noise to the data to remove the dimensionality mismatch during training, and both provide a denoising mechanism whose goal is to sample from the model as though no noise had been added to the data. Our first approach is based on Tweedie's formula, and the second on models which take the variance of added noise as a conditional input. We show that surprisingly, while well motivated, these approaches only sporadically improve performance over not adding noise, and that other methods of addressing the dimensionality mismatch are more empirically adequate.

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach that is building wider attention Transformers. We demonstrate that wide single layer Transformer models can compete with or outperform deeper ones in a variety of Natural Language Processing (NLP) tasks when both are trained from scratch. The impact of changing the model aspect ratio on Transformers is then studied systematically. This ratio balances the number of layers and the number of attention heads per layer while keeping the total number of attention heads and all other hyperparameters constant. On average, across 4 NLP tasks and 10 attention types, single layer wide models perform 0.3% better than their deep counterparts. We show an in-depth evaluation and demonstrate how wide models require a far smaller memory footprint and can run faster on commodity hardware, in addition, these wider models are also more interpretable. For example, a single layer Transformer on the IMDb byte level text classification has 3.1x faster inference latency on a CPU than its equally accurate deeper counterpart, and is half the size. We therefore put forward wider and shallower models as a viable and desirable alternative for small models on NLP tasks, and as an important area of research for domains beyond this.

病理学家通过检查载玻片上的针头活检的组织来诊断和坡度前列腺癌。癌症的严重程度和转移风险取决于格里森等级，这是基于前列腺癌腺体的组织和形态的分数。为了进行诊断检查，病理学家首先将腺体定位在整个活检核心中，如果发现癌症 - 他们分配了Gleason等级。尽管严格的诊断标准，但这种耗时的过程仍会出现错误和明显的观察者间变异性。本文提出了一个自动化的工作流程，该工作流程遵循病理学家的\ textit {modus operandi}，对整个幻灯片图像（WSI）的多尺度斑块进行隔离和分类。分别对基质和腺体边界； （2）分类器网络以高放大倍数将良性与癌症分离； （3）另一个分类器可以在低放大倍率下预测每个癌症的等级。总的来说，此过程为前列腺癌分级提供了一种特定于腺体的方法，我们将其与其他基于机器学习的分级方法进行比较。