扩散概率模型已被证明在几个竞争性图像综合基准上产生最先进的结果，但缺乏低维，可解释的潜在空间，并且在一代中慢慢。另一方面，变形AutoEncoders（VAES）通常可以访问低维潜空间，但表现出差的样品质量。尽管最近的进步，VAE通常需要潜在代码的高维层次结构来产生高质量样本。我们呈现DiffUsevae，一种新的生成框架，它在扩散模型框架内集成了VAE，并利用这一点以设计用于扩散模型的新型条件参数化。我们表明所得模型可以在采样效率方面提高无条件扩散模型，同时还配备了具有低维VAE的扩散模型推断潜码。此外，我们表明所提出的模型可以产生高分辨率样本，并展示与标准基准上的最先进模型相当的合成质量。最后，我们表明所提出的方法可用于可控制的图像合成，并且还展示了图像超分辨率和去噪等下游任务的开箱即用功能。为了重现性，我们的源代码将公开可用于\ url {https://github.com/kpandey008/diffusevae}。

Attention mechanisms form a core component of several successful deep learning architectures, and are based on one key idea: ''The output depends only on a small (but unknown) segment of the input.'' In several practical applications like image captioning and language translation, this is mostly true. In trained models with an attention mechanism, the outputs of an intermediate module that encodes the segment of input responsible for the output is often used as a way to peek into the `reasoning` of the network. We make such a notion more precise for a variant of the classification problem that we term selective dependence classification (SDC) when used with attention model architectures. Under such a setting, we demonstrate various error modes where an attention model can be accurate but fail to be interpretable, and show that such models do occur as a result of training. We illustrate various situations that can accentuate and mitigate this behaviour. Finally, we use our objective definition of interpretability for SDC tasks to evaluate a few attention model learning algorithms designed to encourage sparsity and demonstrate that these algorithms help improve interpretability.

The paper presents a cross-domain review analysis on four popular review datasets: Amazon, Yelp, Steam, IMDb. The analysis is performed using Hadoop and Spark, which allows for efficient and scalable processing of large datasets. By examining close to 12 million reviews from these four online forums, we hope to uncover interesting trends in sales and customer sentiment over the years. Our analysis will include a study of the number of reviews and their distribution over time, as well as an examination of the relationship between various review attributes such as upvotes, creation time, rating, and sentiment. By comparing the reviews across different domains, we hope to gain insight into the factors that drive customer satisfaction and engagement in different product categories.

Despite recent progress towards scaling up multimodal vision-language models, these models are still known to struggle on compositional generalization benchmarks such as Winoground. We find that a critical component lacking from current vision-language models is relation-level alignment: the ability to match directional semantic relations in text (e.g., "mug in grass") with spatial relationships in the image (e.g., the position of the mug relative to the grass). To tackle this problem, we show that relation alignment can be enforced by encouraging the directed language attention from 'mug' to 'grass' (capturing the semantic relation 'in') to match the directed visual attention from the mug to the grass. Tokens and their corresponding objects are softly identified using the cross-modal attention. We prove that this notion of soft relation alignment is equivalent to enforcing congruence between vision and language attention matrices under a 'change of basis' provided by the cross-modal attention matrix. Intuitively, our approach projects visual attention into the language attention space to calculate its divergence from the actual language attention, and vice versa. We apply our Cross-modal Attention Congruence Regularization (CACR) loss to UNITER and improve on the state-of-the-art approach to Winoground.

The tropical cyclone formation process is one of the most complex natural phenomena which is governed by various atmospheric, oceanographic, and geographic factors that varies with time and space. Despite several years of research, accurately predicting tropical cyclone formation remains a challenging task. While the existing numerical models have inherent limitations, the machine learning models fail to capture the spatial and temporal dimensions of the causal factors behind TC formation. In this study, a deep learning model has been proposed that can forecast the formation of a tropical cyclone with a lead time of up to 60 hours with high accuracy. The model uses the high-resolution reanalysis data ERA5 (ECMWF reanalysis 5th generation), and best track data IBTrACS (International Best Track Archive for Climate Stewardship) to forecast tropical cyclone formation in six ocean basins of the world. For 60 hours lead time the models achieve an accuracy in the range of 86.9% - 92.9% across the six ocean basins. The model takes about 5-15 minutes of training time depending on the ocean basin, and the amount of data used and can predict within seconds, thereby making it suitable for real-life usage.

Reflections on glossy objects contain valuable and hidden information about the surrounding environment. By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e.g. from reflections on the human eye. However, this task is challenging because reflections depend jointly on object geometry, material properties, the 3D environment, and the observer viewing direction. Our approach converts glossy objects with unknown geometry into radiance-field cameras to image the world from the object's perspective. Our key insight is to convert the object surface into a virtual sensor that captures cast reflections as a 2D projection of the 5D environment radiance field visible to the object. We show that recovering the environment radiance fields enables depth and radiance estimation from the object to its surroundings in addition to beyond field-of-view novel-view synthesis, i.e. rendering of novel views that are only directly-visible to the glossy object present in the scene, but not the observer. Moreover, using the radiance field we can image around occluders caused by close-by objects in the scene. Our method is trained end-to-end on multi-view images of the object and jointly estimates object geometry, diffuse radiance, and the 5D environment radiance field.

Human activity recognition (HAR) using drone-mounted cameras has attracted considerable interest from the computer vision research community in recent years. A robust and efficient HAR system has a pivotal role in fields like video surveillance, crowd behavior analysis, sports analysis, and human-computer interaction. What makes it challenging are the complex poses, understanding different viewpoints, and the environmental scenarios where the action is taking place. To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Attention (SWTA) module to utilize sparsely sampled video frames for obtaining global weighted temporal attention. The proposed SWTA is comprised of two parts. First, temporal segment network that sparsely samples a given set of frames. Second, weighted temporal attention, which incorporates a fusion of attention maps derived from optical flow, with raw RGB images. This is followed by a basenet network, which comprises a convolutional neural network (CNN) module along with fully connected layers that provide us with activity recognition. The SWTA network can be used as a plug-in module to the existing deep CNN architectures, for optimizing them to learn temporal information by eliminating the need for a separate temporal stream. It has been evaluated on three publicly available benchmark datasets, namely Okutama, MOD20, and Drone-Action. The proposed model has received an accuracy of 72.76%, 92.56%, and 78.86% on the respective datasets thereby surpassing the previous state-of-the-art performances by a margin of 25.26%, 18.56%, and 2.94%, respectively.

The Conditional Neural Process (CNP) family of models offer a promising direction to tackle few-shot problems by achieving better scalability and competitive predictive performance. However, the current CNP models only capture the overall uncertainty for the prediction made on a target data point. They lack a systematic fine-grained quantification on the distinct sources of uncertainty that are essential for model training and decision-making under the few-shot setting. We propose Evidential Conditional Neural Processes (ECNP), which replace the standard Gaussian distribution used by CNP with a much richer hierarchical Bayesian structure through evidential learning to achieve epistemic-aleatoric uncertainty decomposition. The evidential hierarchical structure also leads to a theoretically justified robustness over noisy training tasks. Theoretical analysis on the proposed ECNP establishes the relationship with CNP while offering deeper insights on the roles of the evidential parameters. Extensive experiments conducted on both synthetic and real-world data demonstrate the effectiveness of our proposed model in various few-shot settings.

Drone-camera based human activity recognition (HAR) has received significant attention from the computer vision research community in the past few years. A robust and efficient HAR system has a pivotal role in fields like video surveillance, crowd behavior analysis, sports analysis, and human-computer interaction. What makes it challenging are the complex poses, understanding different viewpoints, and the environmental scenarios where the action is taking place. To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Fusion (SWTF) module to utilize sparsely sampled video frames for obtaining global weighted temporal fusion outcome. The proposed SWTF is divided into two components. First, a temporal segment network that sparsely samples a given set of frames. Second, weighted temporal fusion, that incorporates a fusion of feature maps derived from optical flow, with raw RGB images. This is followed by base-network, which comprises a convolutional neural network module along with fully connected layers that provide us with activity recognition. The SWTF network can be used as a plug-in module to the existing deep CNN architectures, for optimizing them to learn temporal information by eliminating the need for a separate temporal stream. It has been evaluated on three publicly available benchmark datasets, namely Okutama, MOD20, and Drone-Action. The proposed model has received an accuracy of 72.76%, 92.56%, and 78.86% on the respective datasets thereby surpassing the previous state-of-the-art performances by a significant margin.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.